ainote

Soft-delete a task by ID. Destructive but reversible within 30 days (TaskCleanupJob purges trash daily at 2am KST). Returns 404 if the task does not exist or is not owned by the authenticated user.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Task ID to delete"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

List notes/papers from AI Note. Supports keyword search across title and content, category filtering, pagination, and sorting. Returns id/title/content_preview/category_id/created_at. Use this when the user asks 'find my note about X', 'what did I write on Y', or wants to search their knowledge base.

{
  "type": "object",
  "properties": {
    "search": {
      "type": "string",
      "description": "Keyword to match in paper title or content (case-insensitive partial match)"
    },
    "category_id": {
      "type": "string",
      "description": "Filter by category UUID"
    },
    "paper_category_id": {
      "type": "string",
      "description": "Filter by paper-specific folder UUID"
    },
    "source_type": {
      "type": "string",
      "description": "Filter by source type (e.g., 'manual', 'youtube', 'url', 'clipboard')"
    },
    "limit": {
      "type": "number",
      "description": "Maximum number of papers to return (default: 25, max: 200)"
    },
    "offset": {
      "type": "number",
      "description": "Number to skip for pagination (default: 0)"
    },
    "sort_by": {
      "type": "string",
      "enum": [
        "created_at",
        "updated_at",
        "title"
      ],
      "description": "Sort field (default: updated_at)"
    },
    "sort_order": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ],
      "description": "Sort order (default: desc)"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

List the authenticated user's projects (L2 intent layer), or fetch one by id. Each entry includes riskiest_assumption — the single highest-priority unverified assumption (or, if all are verified, the highest-criticality one).

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Fetch a single project by UUID. Omit to list all."
    },
    "status": {
      "type": "string",
      "enum": [
        "active",
        "paused",
        "archived"
      ],
      "description": "Filter by status. Omit to list all statuses."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Create or update a project (L2 intent layer). Omit `id` to create, pass it to update. There is no delete tool — use status: 'archived' to retire a project.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Project UUID to update. Omit to create a new project."
    },
    "name": {
      "type": "string",
      "description": "Project name (required to create)."
    },
    "intent": {
      "type": "string",
      "description": "Why this project exists, in one paragraph. Pass 'null' to clear."
    },
    "success_criteria": {
      "type": "string",
      "description": "What observable outcome counts as success. Pass 'null' to clear."
    },
    "status": {
      "type": "string",
      "enum": [
        "active",
        "paused",
        "archived"
      ],
      "description": "active | paused | archived."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Create or update an assumption under a project (L2 intent layer). Omit `id` to create, pass it to update. There is no delete tool. 🔴 `verdict` is REJECTED with an error if passed — verdict is confirmed only through a human judgment decision (see judgment_submit). This tool can only shape the assumption itself: what is being assumed, how critical it is, and what evidence would settle it.

{
  "type": "object",
  "properties": {
    "project_id": {
      "type": "string",
      "description": "Project UUID this assumption belongs to (required)."
    },
    "id": {
      "type": "string",
      "description": "Assumption UUID to update. Omit to create a new assumption."
    },
    "statement": {
      "type": "string",
      "description": "What is being assumed true (required to create)."
    },
    "criticality": {
      "type": "integer",
      "enum": [
        1,
        2,
        3
      ],
      "description": "1=critical if wrong … 3=minor."
    },
    "evidence_condition": {
      "type": "string",
      "description": "What would be observed to settle this assumption. Pass 'null' to clear."
    },
    "bmc_block": {
      "type": "string",
      "enum": [
        "key_partners",
        "key_activities",
        "key_resources",
        "value_propositions",
        "customer_relationships",
        "channels",
        "customer_segments",
        "cost_structure",
        "revenue_streams",
        "null"
      ],
      "description": "Optional Business Model Canvas block this assumption belongs to. Pass 'null' to clear."
    }
  },
  "required": [
    "project_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Request a human judgment (L3 layer) by attaching evidence — approval, evidence, or verdict. This is the ONLY door an agent has into the judgment queue. 🔴 `decision` is REJECTED with an error if passed — judgments are always created with decision='pending'. Only a human decides them (from the /command queue). Use judgment_list afterwards to check whether this judgment has since been decided. risk_tier controls urgency: 1=destructive (blocks execution until decided), 2=reversible (may auto-proceed after a wait window), 3=informational (auto-expires after 24h).

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "enum": [
        "approval",
        "evidence",
        "verdict"
      ],
      "description": "approval | evidence | verdict."
    },
    "risk_tier": {
      "type": "integer",
      "enum": [
        1,
        2,
        3
      ],
      "description": "1=destructive 2=reversible 3=informational. Default: 2."
    },
    "summary": {
      "type": "string",
      "description": "One sentence: what is being judged (required)."
    },
    "evidence": {
      "type": "object",
      "description": "Free-form evidence attached to the request — links, numbers, diff summaries."
    },
    "project_id": {
      "type": "string",
      "description": "Optional project this judgment relates to."
    },
    "subject_type": {
      "type": "string",
      "enum": [
        "Assumption",
        "Task"
      ],
      "description": "Optional. Pair with subject_id. Only Assumption or Task are allowed."
    },
    "subject_id": {
      "type": "string",
      "description": "Optional. UUID of the Assumption or Task this judgment is about."
    }
  },
  "required": [
    "kind",
    "summary"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

List the authenticated user's own judgments (L3 layer) — use this to check your own blocking status (risk_tier 1 pending = execution blocked). Default order matches the /command queue: risk_tier ascending, then arrival order.

{
  "type": "object",
  "properties": {
    "decision": {
      "type": "string",
      "enum": [
        "pending",
        "approved",
        "rejected",
        "deferred",
        "superseded",
        "expired"
      ],
      "description": "Filter by decision. Omit for all."
    },
    "kind": {
      "type": "string",
      "enum": [
        "approval",
        "evidence",
        "verdict"
      ],
      "description": "Filter by kind."
    },
    "risk_tier": {
      "type": "integer",
      "enum": [
        1,
        2,
        3
      ],
      "description": "Filter by risk_tier."
    },
    "project_id": {
      "type": "string",
      "description": "Filter by project UUID."
    },
    "subject_type": {
      "type": "string",
      "enum": [
        "Assumption",
        "Task"
      ],
      "description": "Filter by subject type."
    },
    "subject_id": {
      "type": "string",
      "description": "Filter by subject UUID (pair with subject_type)."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 50, max 200)."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Soft-delete a dev document by title or UUID. Reversible from trash. Pass `category` when multiple docs share the same title across subcategories (memory/claude/cursor/env/docs).

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Document title"
    },
    "id": {
      "type": "string",
      "description": "Document UUID"
    },
    "category": {
      "type": "string",
      "description": "Subcategory to disambiguate title"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Get instructions for setting up AI Note MCP in Claude Desktop, Cursor, or other MCP clients. No authentication required.

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Create a new private vault as a GitHub repository under the user's account. Requires the user to have completed the GitHub App install flow first.

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Vault display name. The GitHub repo name (slug) is derived from it unless `slug` is given."
    },
    "slug": {
      "type": "string",
      "description": "Optional explicit repo slug (ASCII lowercase-hyphen). Required when `name` has no ASCII letters or digits — e.g. a Korean-only name — because GitHub repo names are ASCII-only."
    },
    "description": {
      "type": "string",
      "description": "Optional GitHub repo description."
    }
  },
  "required": [
    "name"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Wrapper around vault file sync. action=list|pull|push to work against the primary vault. list/pull are paginated — narrow with `path`/`since` and follow `next_cursor` instead of pulling the whole vault. For push: WAF-bypass via `content_b64` or `content: '__B64__:...'` prefix (mirrors sync_push).

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "pull",
        "push"
      ],
      "description": "Sync action. Default list."
    },
    "path": {
      "type": "string",
      "description": "Relative path filter or target file path."
    },
    "content": {
      "type": "string",
      "description": "Required for push (or `content_b64`). Prefix with '__B64__:' for WAF bypass."
    },
    "content_b64": {
      "type": "string",
      "description": "Optional: base64-encoded content (use INSTEAD of `content`) for WAF-bypass on large bodies. Server decodes before storing."
    },
    "since": {
      "type": "string",
      "description": "ISO 8601 timestamp for incremental pull."
    },
    "limit": {
      "type": "integer",
      "description": "Max entries per page. list: default 200, max 1000. pull: default 25, max 100."
    },
    "cursor": {
      "type": "string",
      "description": "Pass `next_cursor` from the previous response to fetch the next page."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Push a markdown file into the primary vault. Optional CAS via base_sha to detect concurrent multi-PC writes (Layer 3 of multi-PC sync plan). WAF-bypass tip: large bodies (~10KB+) that get false-positive blocked at Cloudflare can be sent via `content_b64` (base64-encoded) OR `content` prefixed with `__B64__:` instead. When the push CREATES a new .md file, the response may carry `dedup_candidates` — existing memory files that look similar (keyword + title similarity, no LLM). It is an advisory, not a rejection: YOU decide to merge into one of them (re-push that path), drop this write as a duplicate (skip), or keep it as a new memory (store).

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Relative file path (e.g., 'global/MEMORY.md', 'launchcrew/firebase.md'). No leading slash, no '..'."
    },
    "content": {
      "type": "string",
      "description": "Full file content (markdown text). Alternatively prefix with '__B64__:' followed by base64 payload for WAF bypass."
    },
    "content_b64": {
      "type": "string",
      "description": "Optional: base64-encoded file content (use INSTEAD of `content`). For WAF-bypass on large bodies. Server decodes before storing. If both supplied, content_b64 wins."
    },
    "base_sha": {
      "type": "string",
      "description": "Optional: git_sha the client last observed for this path. When present, server compares with current git_sha and returns -32009 conflict on mismatch (with current content for 3-way diff). Omit for legacy LWW behavior (response will include a `warning` field nudging clients to upgrade)."
    },
    "device_id": {
      "type": "string",
      "description": "Optional: client device identifier (e.g., from ~/.claude/ainote-sync/device.id). Stored on FileIndex so future conflict responses can report which device last wrote the path."
    },
    "force": {
      "type": "boolean",
      "description": "Optional: when true, skip CAS check even if base_sha is supplied. Use only for intentional overwrites; presence is auditable via warning logs."
    },
    "resolves_conflict_id": {
      "type": "string",
      "description": "Optional: UUID of a vault_conflicts row this push resolves. When supplied, server validates ownership/unresolved/path/sha and atomically marks the conflict as resolution=clean inside the same transaction as the file_indices write. Validation failure rolls back the whole push and returns -32009 stale_conflict_id."
    },
    "supports_superseded": {
      "type": "boolean",
      "description": "Optional capability opt-in. When true AND resolves_conflict_id points at an already-resolved conflict whose (path, remote_sha) matches this push, the server returns a NORMAL 200 with resource_data {status:'superseded', reason:'resolved_elsewhere', applied:false, git_sha:<current remote>} instead of a -32009 error, so the client pulls to converge. Omit (default) to keep the legacy -32009 contract."
    }
  },
  "required": [
    "path"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Push MANY files into the primary vault in ONE call. Use this instead of looping sync_push whenever you have more than a couple of changed paths — the cost of sync_push is round trips, not bytes. Per-item semantics are identical to sync_push (Layer 3 base_sha CAS, superseded contract, content_b64 WAF fallback). Partial success is normal and returns HTTP 200: read `results[]` and match entries by `path`, NOT by position. A conflict result always carries `remote_sha` + `conflict_reason` so you can go straight to sync_merge. Request-level failures (duplicate paths in one batch, idempotency key reused with a different payload, >200 items, >4MB) return 4xx and apply NOTHING. Each item MUST carry `content_sha` (SHA1 hex of the decoded body, same algorithm as git_sha) — it powers both the integrity check and the retry-safe `skipped_identical` result. Newly created .md items may carry `dedup_candidates` (same merge/skip/store advisory as sync_push); a batch creating more than 10 new files skips the check entirely and reports `dedup_skipped: "bulk"`.

{
  "type": "object",
  "properties": {
    "items": {
      "type": "array",
      "description": "Up to 200 push items, 4MB total, one entry per unique path. Duplicate paths reject the whole batch.",
      "items": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string",
            "description": "Relative file path. No leading slash, no '..'."
          },
          "content": {
            "type": "string",
            "description": "Full file content. May use the '__B64__:' prefix like sync_push."
          },
          "content_b64": {
            "type": "string",
            "description": "Optional base64 body (use INSTEAD of content) for WAF bypass. Wins over content if both are present."
          },
          "content_sha": {
            "type": "string",
            "description": "REQUIRED. SHA1 hex of the decoded content. Mismatch fails this item only (status 'error'); equality with the current remote git_sha yields 'skipped_identical' instead of a conflict, which is what makes a crashed batch safe to retry."
          },
          "base_sha": {
            "type": "string",
            "description": "Same tri-state semantics as sync_push: omit for legacy LWW, null to assert the path does not exist yet, or the last observed git_sha for CAS."
          },
          "resolves_conflict_id": {
            "type": "string",
            "description": "Optional vault_conflicts UUID this item closes. Requires a non-null base_sha and force=false."
          },
          "force": {
            "type": "boolean",
            "description": "Optional per-item CAS bypass (audited). Suppresses the skipped_identical short-circuit."
          },
          "device_id": {
            "type": "string",
            "description": "Optional per-item device id; falls back to the batch-level device_id."
          }
        },
        "required": [
          "path",
          "content_sha"
        ]
      }
    },
    "idempotency_key": {
      "type": "string",
      "description": "REQUIRED. Opaque client-generated UUID, one per batch ATTEMPT-SET: reuse the same key when retrying the same items after a timeout (the server replays the stored results instead of re-applying), and generate a NEW key whenever the items change. Reusing a key with a different payload is a 400 collision, never a silent replay. Do not derive it from paths or content."
    },
    "device_id": {
      "type": "string",
      "description": "Optional batch-level device identifier; per-item device_id overrides it."
    },
    "supports_superseded": {
      "type": "boolean",
      "description": "Same capability opt-in as sync_push, applied to every item in the batch."
    }
  },
  "required": [
    "items",
    "idempotency_key"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Delete a file from the primary vault. Optional CAS via base_sha to detect concurrent multi-PC writes. Protected paths (global/memory/, global/skills/, global/planning/, global/intent/, global/claude-config/, handoffs/) require base_sha or explicit force:true (audited). Idempotent: deleting a non-existent path returns success with deleted:false.

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Relative file path to delete (e.g., 'global/_waf_probe.md'). No leading slash, no '..'."
    },
    "base_sha": {
      "type": "string",
      "description": "Optional: git_sha the client last observed for this path. When present, server compares with current git_sha and returns -32009 conflict on mismatch (with current content for 3-way diff)."
    },
    "device_id": {
      "type": "string",
      "description": "Optional: client device identifier for audit log (e.g., from ~/.claude/ainote-sync/device.id)."
    },
    "force": {
      "type": "boolean",
      "description": "Optional: when true, skip CAS check even if base_sha is supplied. Use only for intentional overwrites; presence is auditable via warning logs."
    }
  },
  "required": [
    "path"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Record the result of a client-side Layer 5 codex review (sync.py merge gate) as a vault_events row. Body of the review is NOT stored — only an HMAC digest of the summary so operators can correlate without exposing review content. Opt-in: server skips writes (still returns success) unless ENV['AINOTE_LAYER5_AUDIT']='on' AND a versioned HMAC secret is configured. Used by the sync.py SessionStart hook + merge command to surface 'why was this blocked?' across multi-PC sessions.

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Vault path the review covered."
    },
    "verdict": {
      "type": "string",
      "description": "One of: pass, flag, block, error."
    },
    "summary": {
      "type": "string",
      "description": "Free-form codex output summary. Server HMACs this; raw text is NEVER stored."
    },
    "chunk_count": {
      "type": "integer",
      "description": "Optional: number of diff chunks the client fed to codex."
    },
    "duration_ms": {
      "type": "integer",
      "description": "Optional: wall-clock time of the codex review on the client."
    }
  },
  "required": [
    "path",
    "verdict"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Save a session handoff note for cross-device / cross-session continuation. Stored at handoffs/{project}-{topic}-{YYYY-MM-DD}.txt in the user's primary vault. Use the optional `time` param (HHMM, KST) to disambiguate multiple handoffs saved on the same day — it is appended to the topic slug (e.g. topic='phase-d', time='1555' → handoffs/{project}-phase-d-1555-{date}.txt).

{
  "type": "object",
  "properties": {
    "project": {
      "type": "string",
      "description": "Project slug, e.g. 'logi', 'ainote', 'krx_ai'. Lowercase, no spaces."
    },
    "topic": {
      "type": "string",
      "description": "Short topic slug for this handoff, e.g. 'phase-d-port', 'oauth-fix'. Lowercase-hyphen."
    },
    "content": {
      "type": "string",
      "description": "Full handoff text. Should follow the session-handoff skill template (현재 상태 / 작업 위치 / 수정 파일 / 결정 사항 / 다음 STEP / 알려진 이슈). WAF-bypass tip: prefix the string with '__B64__:' followed by base64-encoded payload to bypass Render/Cloudflare edge WAF for large bodies (~10KB+) that get false-positive blocked as SQLi/cmd-injection."
    },
    "content_b64": {
      "type": "string",
      "description": "Optional: base64-encoded handoff text (use INSTEAD of `content`). For WAF-bypass on large bodies. Server decodes before storing."
    },
    "date": {
      "type": "string",
      "description": "Optional override date (YYYY-MM-DD). Defaults to today in server timezone."
    },
    "time": {
      "type": "string",
      "description": "Optional time-of-day suffix in HHMM 24h format (KST), e.g. '1555'. Appended to the topic slug so multiple handoffs on the same day stay distinguishable. Omit for once-per-day saves."
    },
    "device_id": {
      "type": "string",
      "description": "Optional: client device identifier (e.g., from ~/.claude/ainote-sync/device.id). Stored on FileIndex so future conflict responses can report which device last wrote the handoff. Same field sync_push uses."
    }
  },
  "required": [
    "project",
    "topic"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Soft-delete an env_sync graph node (sets deleted_at; .live scope hides it from reads). Idempotent — re-deleting a deleted node is a no-op success.

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "format": "uuid"
    },
    "device_id": {
      "type": "string",
      "format": "uuid"
    },
    "client_hlc": {
      "type": "string"
    }
  },
  "required": [
    "node_id",
    "device_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Push a new client-encrypted secret. Ciphertext only — server never sees plaintext. Recipients must include the pushing device's own pubkey.

{
  "type": "object",
  "properties": {
    "alias": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128
    },
    "kind": {
      "type": "string",
      "enum": [
        "api_key",
        "oauth_token",
        "private_key",
        "passphrase"
      ]
    },
    "ciphertext_b64": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1048576
    },
    "recipients": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "string",
        "pattern": "^age1[a-z0-9]{58}$"
      }
    },
    "device_id": {
      "type": "string",
      "format": "uuid"
    },
    "client_hlc": {
      "type": "string"
    }
  },
  "required": [
    "alias",
    "kind",
    "ciphertext_b64",
    "recipients",
    "device_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Pull an encrypted secret blob. Response is ciphertext_b64 only — server never sees and never returns plaintext.

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "format": "uuid"
    },
    "alias": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128
    },
    "device_id": {
      "type": "string",
      "description": "Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH)."
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "oneOf": [
    {
      "required": [
        "node_id"
      ]
    },
    {
      "required": [
        "alias"
      ]
    }
  ],
  "additionalProperties": false
}

Rotate a secret: soft-delete the old node, create a new live node with the same alias and the new ciphertext+recipients. 7-day grace before hard delete of old ciphertext bytes.

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "format": "uuid"
    },
    "new_ciphertext_b64": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1048576
    },
    "new_recipients": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "string",
        "pattern": "^age1[a-z0-9]{58}$"
      }
    },
    "device_id": {
      "type": "string",
      "format": "uuid"
    },
    "client_hlc": {
      "type": "string"
    }
  },
  "required": [
    "node_id",
    "new_ciphertext_b64",
    "new_recipients",
    "device_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Ingest a batched envelope of client-recorded env_sync mutations. HLC-skew gated, partial-success on conflict.

{
  "type": "object",
  "properties": {
    "operations": {
      "type": "array",
      "minItems": 1,
      "maxItems": 100,
      "items": {
        "type": "object",
        "required": [
          "tool",
          "args",
          "hlc"
        ],
        "properties": {
          "tool": {
            "type": "string"
          },
          "args": {
            "type": "object"
          },
          "hlc": {
            "type": "string"
          },
          "client_txn_id": {
            "type": "string"
          }
        },
        "additionalProperties": false
      }
    },
    "device_id": {
      "type": "string",
      "description": "Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH)."
    }
  },
  "required": [
    "operations"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Inverse-apply a prior env_sync transaction. Safety gates: ownership, idempotency, descendant-conflict (force opt-out).

{
  "type": "object",
  "properties": {
    "txn_id": {
      "type": "string",
      "format": "uuid"
    },
    "include_descendants": {
      "type": "boolean",
      "default": false
    },
    "force": {
      "type": "boolean",
      "default": false
    },
    "device_id": {
      "type": "string",
      "description": "Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH)."
    }
  },
  "required": [
    "txn_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Read tasks and task categories. action: tasks | categories (consolidated surface — same handlers as the legacy tools)

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "tasks",
        "categories"
      ],
      "description": "which operation to run"
    },
    "status": {
      "type": "string",
      "enum": [
        "pending",
        "completed"
      ],
      "description": "[tasks] Filter by task status"
    },
    "is_important": {
      "type": "boolean",
      "description": "[tasks] Filter by important tasks only"
    },
    "limit": {
      "type": "number",
      "description": "[tasks] Maximum number of tasks to return (default: 25, max: 500)"
    },
    "offset": {
      "type": "number",
      "description": "[tasks] Number of tasks to skip for pagination (default: 0). Use with limit to fetch additional pages."
    },
    "search": {
      "type": "string",
      "description": "[tasks] Search keyword in task content and notes (case-insensitive partial match)"
    },
    "location": {
      "type": "string",
      "description": "[tasks] Filter by location (partial match, e.g., '여의도', '서울')"
    },
    "category_id": {
      "type": "string",
      "description": "[tasks] Filter by category UUID"
    },
    "due_date_start": {
      "type": "string",
      "description": "[tasks] Filter tasks with due_date >= this date (ISO 8601 format)"
    },
    "due_date_end": {
      "type": "string",
      "description": "[tasks] Filter tasks with due_date <= this date (ISO 8601 format)"
    },
    "completed_date_start": {
      "type": "string",
      "description": "[tasks] Filter tasks completed >= this date (ISO 8601 format)"
    },
    "completed_date_end": {
      "type": "string",
      "description": "[tasks] Filter tasks completed <= this date (ISO 8601 format)"
    },
    "created_date_start": {
      "type": "string",
      "description": "[tasks] Filter tasks created >= this date (ISO 8601 format)"
    },
    "created_date_end": {
      "type": "string",
      "description": "[tasks] Filter tasks created <= this date (ISO 8601 format)"
    },
    "overdue": {
      "type": "boolean",
      "description": "[tasks] Filter overdue incomplete tasks (due_date < today)"
    },
    "due_today": {
      "type": "boolean",
      "description": "[tasks] Filter tasks due today"
    },
    "has_notification": {
      "type": "boolean",
      "description": "[tasks] Filter by notification enabled status"
    },
    "sort_by": {
      "type": "string",
      "enum": [
        "due_date",
        "created_at",
        "completed_at",
        "updated_at",
        "is_important"
      ],
      "description": "[tasks] Sort field (default: created_at)"
    },
    "sort_order": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ],
      "description": "[tasks] Sort order (default: desc)"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Create or update a task (non-destructive). action: create | update. Deletion is a separate tool (delete_task). (consolidated surface — same handlers as the legacy tools) Required per action — create: content | update: id.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "create",
        "update"
      ],
      "description": "which operation to run"
    },
    "content": {
      "type": "string",
      "description": "[create] Task content (required) [update] New task content"
    },
    "is_important": {
      "type": "boolean",
      "description": "[create] Mark task as important (default: false) [update] Update important status"
    },
    "due_date": {
      "type": "string",
      "description": "[create] Due date in ISO format (e.g., '2026-01-28' or '2026-01-28T15:00:00+09:00') [update] Update due date in ISO format (or 'null' to clear)"
    },
    "due_time": {
      "type": "string",
      "description": "[create] Due time in HH:MM format (e.g., '15:00'). If not provided, task is treated as all-day. [update] Update due time in HH:MM format (or 'null' to make all-day)"
    },
    "start_date": {
      "type": "string",
      "description": "[create] Start date for date range tasks in ISO format (e.g., for multi-day events) [update] Update start date in ISO format (or 'null' to clear)"
    },
    "is_all_day": {
      "type": "boolean",
      "description": "[create] Mark as all-day event — suppresses time-of-day rendering. [update] Toggle all-day mode."
    },
    "category_id": {
      "type": "string",
      "description": "[create] Category ID (UUID) to organize the task [update] Update category ID (or 'null' to remove category)"
    },
    "notes": {
      "type": "string",
      "description": "[create] Additional notes or details for the task [update] Update notes (or 'null' to clear)"
    },
    "location": {
      "type": "string",
      "description": "[create] Location where the task takes place [update] Update location (or 'null' to clear)"
    },
    "location_lat": {
      "type": "number",
      "description": "[create] GPS latitude. Pair with location_lng. [update] Update GPS latitude."
    },
    "location_lng": {
      "type": "number",
      "description": "[create] GPS longitude. Pair with location_lat. [update] Update GPS longitude."
    },
    "travel_time": {
      "type": "number",
      "description": "[create] Minutes of travel time to allow before due_date. [update] Update travel-time minutes."
    },
    "has_notification": {
      "type": "boolean",
      "description": "[create] Enable reminder notifications (default: false) [update] Enable/disable reminder notifications"
    },
    "reminder_timing": {
      "type": "integer",
      "description": "[create] Minutes before due time to send reminder (e.g., 10 for 10 minutes before). Default: 30. Only used when has_notification is true. [update] Minutes before due time to send reminder (e.g., 10 for 10 minutes before). Only used when has_notification is true."
    },
    "reminder_timings": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "[create] Multiple reminder offsets in minutes before due time (e.g., [10, 60] fires 10 min and 1 hour before). Overrides reminder_timing if provided. [update] Multiple reminder offsets in minutes before due time (e.g., [10, 60]). Pass empty array [] to clear."
    },
    "repeat_rule": {
      "type": "string",
      "description": "[create] Recurrence rule (e.g., 'daily', 'weekly', 'monthly', 'yearly', or RRULE format) [update] Update recurrence rule (or 'null' to make non-recurring)"
    },
    "id": {
      "type": "string",
      "description": "[update] Task ID (required)"
    },
    "completed_at": {
      "type": "string",
      "description": "[update] Mark as completed (ISO format) or 'null' to uncomplete"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read dev docs. action: get | list | categories | pull (consolidated surface — same handlers as the legacy tools)

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "list",
        "categories",
        "pull"
      ],
      "description": "which operation to run"
    },
    "title": {
      "type": "string",
      "description": "[get] Document title (e.g., project-a-memory.md)"
    },
    "id": {
      "type": "string",
      "description": "[get] Document UUID"
    },
    "category": {
      "type": "string",
      "description": "[get] Subcategory (claude, cursor, etc.) to disambiguate title [list] Subcategory filter (claude, cursor, windsurf, copilot, docs, etc.). Omit to list all dev docs. [pull] Subcategory filter. Omit to pull all docs with local_path."
    },
    "include_versions": {
      "type": "boolean",
      "description": "[get] Include version history (default: false)"
    },
    "search": {
      "type": "string",
      "description": "[list] Search keyword in document title"
    },
    "content_type": {
      "type": "string",
      "enum": [
        "markdown",
        "json",
        "yaml",
        "text"
      ],
      "description": "[list] Filter by content type"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Create or update a dev doc (non-destructive). action: create | update. Deletion is a separate tool (delete_dev_doc). (consolidated surface — same handlers as the legacy tools) Required per action — create: title, content | update: content.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "create",
        "update"
      ],
      "description": "which operation to run"
    },
    "title": {
      "type": "string",
      "description": "[create] Filename as title (e.g., ainote-memory.md, project-claude.md) [update] Document title"
    },
    "content": {
      "type": "string",
      "description": "[create] Full file content (markdown, json, yaml, text) [update] New content"
    },
    "category": {
      "type": "string",
      "description": "[create] Subcategory: memory | claude | cursor | env | docs | custom. Default: docs [update] Subcategory to disambiguate title"
    },
    "content_type": {
      "type": "string",
      "enum": [
        "markdown",
        "json",
        "yaml",
        "text"
      ],
      "description": "[create] Content type. Auto-detected from title extension if omitted."
    },
    "local_path": {
      "type": "string",
      "description": "[create] Absolute path on this machine (e.g., ~/.claude/projects/-Users-seunghan/memory/MEMORY.md). Used by pull_dev_docs to restore file on other devices. Supports ~ expansion. [update] Update the local file path for multi-device sync"
    },
    "memory_type": {
      "type": "string",
      "enum": [
        "state",
        "event",
        "preference"
      ],
      "description": "[create] Memory update semantics: 'state' = latest value replaces the past (used by memory_search latest_state mode), 'event' = immutable accumulating log, 'preference' = user preference. Omit for plain documents. [update] Set the memory update semantics (state | event | preference). Pass null/empty to clear."
    },
    "id": {
      "type": "string",
      "description": "[update] Document UUID"
    },
    "mode": {
      "type": "string",
      "enum": [
        "replace",
        "append",
        "prepend"
      ],
      "description": "[update] Update mode (default: replace)"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read-only vault sync operations. action: list | pull | diff | merge | conflicts. Writes (push/delete) are separate tools — they carry CAS semantics. (consolidated surface — same handlers as the legacy tools) Required per action — diff: path | merge: path, base_text, local_text.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "pull",
        "diff",
        "merge",
        "conflicts"
      ],
      "description": "which operation to run"
    },
    "path": {
      "type": "string",
      "description": "[list] Directory to list (e.g., 'global'). Omit to list from the first page. [pull] Optional directory filter (e.g., 'global' to pull only global files) [diff] Relative vault path. [merge] Relative vault path (e.g., 'global/MEMORY.md'). [conflicts] Optional: filter to a specific path."
    },
    "limit": {
      "type": "integer",
      "description": "[list] Max entries per page. Default 200, max 1000. [pull] Max files per page. Default 25, max 100. [conflicts] Optional: max rows to return (default 50, max 200)."
    },
    "cursor": {
      "type": "string",
      "description": "[list] Pass `next_cursor` from the previous response to fetch the next page. [pull] Pass `next_cursor` from the previous response to fetch the next page."
    },
    "since": {
      "type": "string",
      "description": "[pull] ISO 8601 timestamp. Only return files updated after this time. Omit to start from the first page."
    },
    "local_text": {
      "type": "string",
      "description": "[diff] Optional: client's current text. When supplied, response includes unified diff (remote → local). [merge] Current local text on the client (post-edit). Required."
    },
    "base_text": {
      "type": "string",
      "description": "[diff] Optional: client's baseline (last-known remote). When supplied along with local_text, response includes both diffs (base → remote, base → local) so the client can render a 3-way view. [merge] Common ancestor text — what the client had cached when it started editing. Source: client state.json baseline. Required."
    },
    "base_sha": {
      "type": "string",
      "description": "[merge] Optional: git_sha the client believes is the merge base. When supplied, server verifies (informational; merge still runs)."
    },
    "device_id": {
      "type": "string",
      "description": "[merge] Optional: client device identifier. Recorded on any vault_conflict row created downstream."
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read vault metadata. action: list | clone | status (consolidated surface — same handlers as the legacy tools) Required per action — clone: name.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "clone",
        "status"
      ],
      "description": "which operation to run"
    },
    "include_commit_sha": {
      "type": "boolean",
      "description": "[list] Include each vault's latest_commit_sha (default false). Costs one GitHub API round-trip per vault, so only ask for it when you actually need the remote HEAD."
    },
    "name": {
      "type": "string",
      "description": "[clone] Vault name or slug."
    },
    "target_path": {
      "type": "string",
      "description": "[clone] Preferred local clone path for the returned instructions."
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read env-sync state. action: devices | drift | status | txn_pull. Secret reads are a separate tool (env_sync.secret_pull). (consolidated surface — same handlers as the legacy tools)

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "devices",
        "drift",
        "status",
        "txn_pull"
      ],
      "description": "which operation to run"
    },
    "include_stale": {
      "type": "boolean",
      "default": true,
      "description": "[devices]"
    },
    "device_id": {
      "type": "string",
      "description": "[devices] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH). [drift] [status] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH). [txn_pull] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH)."
    },
    "since_hlc": {
      "type": "string",
      "description": "[txn_pull]"
    },
    "op": {
      "type": "string",
      "enum": [
        "push",
        "install",
        "uninstall",
        "reconcile",
        "migrate",
        "rollback"
      ],
      "description": "[txn_pull]"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500,
      "description": "[txn_pull]"
    },
    "cursor": {
      "type": "string",
      "description": "[txn_pull]"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Non-destructive env-sync writes. action: enroll | request_share | heartbeat. Secret push/rotate are separate tools. (consolidated surface — same handlers as the legacy tools) Required per action — enroll: alias, age_pubkey, enrollment_token | request_share: target_device_id, secret_shares, device_id | heartbeat: device_id, installed_skills_hash, installed_hooks_hash.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "enroll",
        "request_share",
        "heartbeat"
      ],
      "description": "which operation to run"
    },
    "alias": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64,
      "description": "[enroll]"
    },
    "age_pubkey": {
      "type": "string",
      "pattern": "^age1[a-z0-9]{58}$",
      "description": "[enroll]"
    },
    "enrollment_token": {
      "type": "string",
      "minLength": 16,
      "description": "[enroll]"
    },
    "capabilities": {
      "type": "object",
      "properties": {
        "os": {
          "type": "string",
          "maxLength": 32
        },
        "claude_code_version": {
          "type": "string",
          "maxLength": 32
        },
        "transports": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "additionalProperties": true,
      "description": "[enroll]"
    },
    "device_id": {
      "type": "string",
      "description": "[enroll] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH). [request_share] The existing device performing the re-encryption (must own access to all secret_node_ids). [heartbeat]"
    },
    "target_device_id": {
      "type": "string",
      "format": "uuid",
      "description": "[request_share]"
    },
    "secret_shares": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "object",
        "required": [
          "secret_node_id",
          "re_encrypted_ciphertext_b64"
        ],
        "properties": {
          "secret_node_id": {
            "type": "string",
            "format": "uuid"
          },
          "re_encrypted_ciphertext_b64": {
            "type": "string",
            "minLength": 1,
            "maxLength": 1048576
          }
        },
        "additionalProperties": false
      },
      "description": "[request_share]"
    },
    "client_hlc": {
      "type": "string",
      "description": "[request_share]"
    },
    "installed_skills_hash": {
      "type": "string",
      "minLength": 64,
      "maxLength": 64,
      "description": "[heartbeat]"
    },
    "installed_hooks_hash": {
      "type": "string",
      "minLength": 64,
      "maxLength": 64,
      "description": "[heartbeat]"
    },
    "installed_mcp_servers_hash": {
      "type": "string",
      "minLength": 64,
      "maxLength": 64,
      "description": "[heartbeat]"
    },
    "installed_skills": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 128
      },
      "maxItems": 2000,
      "description": "[heartbeat]"
    },
    "installed_hooks": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 128
      },
      "maxItems": 2000,
      "description": "[heartbeat]"
    },
    "claude_code_version": {
      "type": "string",
      "maxLength": 32,
      "description": "[heartbeat]"
    },
    "os": {
      "type": "string",
      "maxLength": 32,
      "description": "[heartbeat]"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read knowledge-graph nodes. action: get | list (consolidated surface — same handlers as the legacy tools)

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "list"
      ],
      "description": "which operation to run"
    },
    "node_id": {
      "type": "string",
      "format": "uuid",
      "description": "[get]"
    },
    "alias": {
      "type": "string",
      "maxLength": 128,
      "description": "[get]"
    },
    "node_type": {
      "type": "string",
      "enum": [
        "skill",
        "hook",
        "mcp_server",
        "secret",
        "setting_fragment"
      ],
      "description": "[get] [list]"
    },
    "device_id": {
      "type": "string",
      "description": "[get] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH). [list] Optional calling device id for audit attribution. The X-Ainote-Device-Id header is the canonical source; this argument is the backwards-compatible fallback for clients that predate the header. If both are sent and disagree, the request is rejected (DEVICE_MISMATCH)."
    },
    "updated_since_hlc": {
      "type": "string",
      "description": "[list]"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500,
      "default": 100,
      "description": "[list]"
    },
    "cursor": {
      "type": "string",
      "description": "[list] Opaque cursor (created_at ISO + id) from previous page's next_cursor"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Add or update a graph entity (non-destructive). action: add | update. Deletion is a separate tool (graph_soft_delete). (consolidated surface — same handlers as the legacy tools) Required per action — add: node_type, alias, payload, device_id | update: node_id, device_id, field_updates.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "add",
        "update"
      ],
      "description": "which operation to run"
    },
    "node_type": {
      "type": "string",
      "enum": [
        "skill",
        "hook",
        "mcp_server",
        "secret",
        "setting_fragment"
      ],
      "description": "[add]"
    },
    "alias": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128,
      "description": "[add]"
    },
    "payload": {
      "type": "object",
      "description": "[add]"
    },
    "device_id": {
      "type": "string",
      "format": "uuid",
      "description": "[add] [update]"
    },
    "client_hlc": {
      "type": "string",
      "description": "[add] [update]"
    },
    "node_id": {
      "type": "string",
      "format": "uuid",
      "description": "[update]"
    },
    "field_updates": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "object",
        "required": [
          "field",
          "value",
          "client_hlc"
        ],
        "properties": {
          "field": {
            "type": "string",
            "minLength": 1,
            "maxLength": 256
          },
          "value": {},
          "client_hlc": {
            "type": "string"
          }
        },
        "additionalProperties": false
      },
      "description": "[update]"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read session handoffs. action: get | list (consolidated surface — same handlers as the legacy tools) Required per action — get: project, topic.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "list"
      ],
      "description": "which operation to run"
    },
    "project": {
      "type": "string",
      "description": "[get] Project slug used at handoff_save time. [list] Optional project filter, e.g. 'logi' to list only logi-* handoffs."
    },
    "topic": {
      "type": "string",
      "description": "[get] Topic slug used at handoff_save time."
    },
    "date": {
      "type": "string",
      "description": "[get] Optional YYYY-MM-DD. Omit for latest."
    },
    "time": {
      "type": "string",
      "description": "[get] Optional HHMM (24h, KST) — same value passed at save time. Required to disambiguate when multiple handoffs share the same project/topic/date."
    },
    "limit": {
      "type": "integer",
      "description": "[list] Max entries to return (default 50)."
    },
    "status": {
      "type": "string",
      "description": "[list] v2 only: filter by frontmatter status (e.g. 'in_progress', 'paused', 'completed', 'blocked'). v1 handoffs without frontmatter are excluded when this filter is set."
    },
    "has_blockers": {
      "type": "boolean",
      "description": "[list] v2 only: filter by frontmatter has_blockers (true/false)."
    },
    "task_type": {
      "type": "string",
      "description": "[list] v2 only: filter by frontmatter task_type (e.g. 'feature', 'bugfix', 'refactor', 'research', 'ops')."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "[list] v2 only: AND match — entries must contain ALL given tags. Example: ['auth', 'mobile']."
    },
    "since": {
      "type": "string",
      "description": "[list] ISO8601 timestamp — only entries with updated_at >= since are returned."
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Read agent memory. action: get | search (consolidated surface — same handlers as the legacy tools) Required per action — get: source | search: query.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "get",
        "search"
      ],
      "description": "which operation to run"
    },
    "source": {
      "type": "string",
      "enum": [
        "paper",
        "vault_file"
      ],
      "description": "[get] Which store the item lives in (use the `source` field from memory_search results)"
    },
    "id": {
      "type": "string",
      "description": "[get] Item ID returned by memory_search"
    },
    "path": {
      "type": "string",
      "description": "[get] vault_file only: file path inside the vault (e.g. 'global/MEMORY.md')"
    },
    "query": {
      "type": "string",
      "description": "[search] Search text (e.g. 'render deploy key', 'ainote jwt'). May be blank only in latest_state mode."
    },
    "mode": {
      "type": "string",
      "enum": [
        "keyword",
        "latest_state"
      ],
      "description": "[search] keyword (default) or latest_state"
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "papers",
          "vault"
        ]
      },
      "description": "[search] Memory stores to search. Default: both."
    },
    "limit": {
      "type": "integer",
      "description": "[search] Max results (default 10, max 20)"
    },
    "hop": {
      "type": "integer",
      "minimum": 0,
      "maximum": 2,
      "description": "[search] Expand results by following [[wikilinks]] N hops from keyword hits (vault only). Scores decay 0.5 per hop. Default 0 (off)."
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

Obtain an MCP key. action: login | signup (consolidated surface — same handlers as the legacy tools) Required per action — login: email, password | signup: email, password.

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "login",
        "signup"
      ],
      "description": "which operation to run"
    },
    "email": {
      "type": "string",
      "description": "[login] Your account email address [signup] Email address for the new account"
    },
    "password": {
      "type": "string",
      "description": "[login] Your account password [signup] Password (minimum 6 characters)"
    },
    "name": {
      "type": "string",
      "description": "[signup] Display name (optional)"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}