AgentWatch

List watched addresses for this connector principal. NEW USERS: if empty, call watch_demo_set next (do not invent a global feed), then get_dashboard.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Decoded activity feed for an address. Use when reviewing what an agent did on-chain.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Watched address (0x…40 hex)"
    },
    "since": {
      "type": "number",
      "description": "Unix seconds lower bound"
    }
  },
  "required": [
    "address"
  ]
}

Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Safe/address to audit (0x…40 hex)"
    },
    "chain": {
      "type": "string",
      "enum": [
        "base",
        "ethereum"
      ]
    },
    "agents": {
      "type": "string",
      "description": "Comma-separated agent keys"
    }
  },
  "required": [
    "address"
  ]
}

Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string"
    }
  },
  "required": [
    "agent_key"
  ]
}

List alerts scoped to this principal's watched addresses (empty watch list → call watch_demo_set first). Use when checking what needs attention.

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string"
    }
  }
}

Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.

{
  "type": "object",
  "properties": {
    "safe": {
      "type": "string",
      "description": "Optional Safe address; default = all watched"
    },
    "chains": {
      "type": "string",
      "description": "Optional comma-separated chain ids"
    }
  }
}

Intent↔execution fidelity score for an agent or Safe. Use for accountability / coverage meter. Check matched_agent — false means the address has no indexed activity (as signer or as the Safe that executed), so the score is vacuous.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string",
      "description": "Agent EOA address (0x…40 hex)"
    }
  },
  "required": [
    "agent_key"
  ]
}

Public standings for agents with a published passport, ranked from receipts (declared-first coverage, fidelity, reliability, hygiene, sustained work). Pass agent_key to get that agent's own rank, its component scores, and what it would need to climb. Read-only: nothing here can be self-reported.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string",
      "description": "Optional: address to locate in the standings"
    },
    "limit": {
      "type": "number",
      "description": "How many ranked rows to return (default 10, max 50)"
    }
  }
}

Counterfactual P&L / agent alpha vs do-nothing baselines. Use for performance honesty checks. Check matched_agent — false means the key has no indexed activity.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string",
      "description": "Agent EOA address (0x…40 hex)"
    }
  },
  "required": [
    "agent_key"
  ]
}

TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.

{
  "type": "object",
  "properties": {
    "event_id": {
      "type": "string"
    }
  },
  "required": [
    "event_id"
  ]
}

Declare an intent BEFORE broadcasting. Returns {intent_id, pairing_code}. Append the 16-hex pairing_code as the last 8 bytes of calldata (no magic prefix), then broadcast — EXCEPT bare ETH transfers to contracts (empty data + value>0): appending reverts on Safe/fallback handlers; register without a suffix and use expected.steps for multi-leg flows (e.g. approve+supply). Pairing codes are single-use and only consumed by successful (non-reverted) txs. Use deadline_minutes (relative) — normalized to absolute constraints.deadline at registration.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string"
    },
    "description": {
      "type": "string"
    },
    "declared_at": {
      "type": "number"
    },
    "deadline_minutes": {
      "type": "number",
      "description": "Relative window; stored as absolute constraints.deadline"
    },
    "expected": {
      "type": "object",
      "description": "Structured shape. Use steps: ['approve','other'] (or similar) so one intent covers approve+supply/swap companions."
    }
  },
  "required": [
    "agent_key",
    "description"
  ]
}

Start watching an address. Use when onboarding a new agent or Safe.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Address to watch (0x…40 hex)"
    },
    "chains": {
      "type": "string"
    },
    "label": {
      "type": "string",
      "description": "Optional short label (e.g. Agent EOA)"
    }
  },
  "required": [
    "address"
  ]
}

ONE-SHOT cold-start for brand-new Claude / MCP users with an empty watch list. Adds the July 18 fixture (Agent EOA + Safe A + Safe B on Base, with declared intents) and one live Polygon trading bot, so the first dashboard has recent activity. Call this FIRST after connect when list_watched is empty, then call get_dashboard (Always allow the App). Idempotent — skips addresses already watched.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Force an immediate poller pass over this principal's watched addresses (catch up txs from explorers into AgentWatch). Use after add_watch / a fresh broadcast when get_feed is still empty. Optional address / chains to focus the pass.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Optional single address to refresh (0x…40 hex)"
    },
    "chains": {
      "type": "string",
      "description": "Optional csv of chains (default: ethereum,base first, then the rest)"
    }
  }
}

Read the declared identity of a watched agent (name, model provider, how often it runs, role, purpose, operator) and whether its public passport page is published.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Watched agent address (0x…40 hex)"
    }
  },
  "required": [
    "address"
  ]
}

Declare who a watched agent is: model provider, run cadence, role, purpose, operator, and whether to publish a shareable public passport at /a/<slug>. Declarations never change the receipt-derived numbers next to them; publishing exposes only this address, never the rest of the watch list.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Watched agent address (0x…40 hex)"
    },
    "display_name": {
      "type": "string",
      "description": "Name shown instead of the raw address"
    },
    "provider": {
      "type": "string",
      "enum": [
        "anthropic",
        "openai",
        "google",
        "xai",
        "meta",
        "mistral",
        "deepseek",
        "qwen",
        "open_source",
        "multi",
        "none",
        "unknown"
      ],
      "description": "Which model drives the agent"
    },
    "model": {
      "type": "string",
      "description": "Optional model or framework detail"
    },
    "cadence": {
      "type": "string",
      "enum": [
        "always_on",
        "scheduled",
        "event_driven",
        "on_demand",
        "unknown"
      ],
      "description": "always_on, scheduled, event_driven, on_demand"
    },
    "role": {
      "type": "string",
      "enum": [
        "trading",
        "market_making",
        "prediction",
        "treasury",
        "payments",
        "research",
        "infra",
        "personal",
        "other"
      ]
    },
    "purpose": {
      "type": "string",
      "description": "One or two sentences on what it is for"
    },
    "operator": {
      "type": "string",
      "description": "Who runs it"
    },
    "public": {
      "type": "boolean",
      "description": "Publish a public passport page"
    }
  },
  "required": [
    "address"
  ]
}

List this user's saved recovery wallets (human co-signers for default 1/2 Safes). Each may have a label/purpose — users often keep several for different vaults.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Save or update a recovery address for this user. Product default Safe is then 1/2: threshold 1, owners = [agent, this recovery]. Use make_default=true to prefer this label in get_safe_defaults.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "0x recovery wallet the human controls"
    },
    "label": {
      "type": "string",
      "description": "Short name, e.g. hardware, treasury, personal"
    },
    "purpose": {
      "type": "string",
      "description": "What this recovery is for, e.g. default, trading"
    },
    "make_default": {
      "type": "boolean",
      "description": "Prefer this label for default Safes"
    }
  },
  "required": [
    "address"
  ]
}

Remove a saved recovery address for this user.

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string"
    }
  },
  "required": [
    "address"
  ]
}

Return the default Safe ownership plan for an agent EOA: threshold 1 + agent + selected recovery (1/2 when one recovery is set). Call before register_intent for Safe deploys. AgentWatch never deploys or signs.

{
  "type": "object",
  "properties": {
    "agent_key": {
      "type": "string",
      "description": "Agent EOA that will be an owner/signer"
    },
    "recovery_label": {
      "type": "string",
      "description": "Optional label to pick among several recoveries"
    },
    "purpose": {
      "type": "string",
      "description": "Optional purpose filter (e.g. trading)"
    },
    "chain": {
      "type": "string",
      "description": "Optional chain hint for the intent constraints"
    },
    "all_recoveries": {
      "type": "boolean",
      "description": "If true, include all matching recoveries (1/n) instead of just the default one"
    }
  },
  "required": [
    "agent_key"
  ]
}

Persona-tailored dashboard brief (fidelity, alerts, pending plans, recent planned-vs-executed). NEW USERS with empty watches: call watch_demo_set first, then get_dashboard again. Narrate in plain language; ask the user to Always allow the AgentWatch MCP App widget when the host prompts.

{
  "type": "object",
  "properties": {
    "persona": {
      "type": "string",
      "description": "Optional override; otherwise uses saved persona"
    }
  }
}