Daystruct

Find source-package workflows, inspect live prices and evidence, and connect with a scoped key.

使うべきか

品質と安全性

A
説明の品質
97%
スキーマの完全性
75%
命名の品質
90%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(2)

  • LOWTool 'get_daystruct_validated_guidance' name length outside 3-30 rangeget_daystruct_validated_guidance 内
  • LOWTool 'discover_daystruct_capabilities' name length outside 3-30 rangediscover_daystruct_capabilities 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~5,021トークン数(ツール定義)
~1.3 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 3.92%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "daystruct": {
      "url": "https://api.daystruct.ai/mcp"
    }
  }
}

リモートエンドポイント

https://api.daystruct.ai/mcpstreamable-http

できること

ツール一覧

ツール(23)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢daystruct_status

Read the public Daystruct manifest: how capabilities are discovered, checked for compatibility and delivered.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_entities(databank, type, provider, capability, modelType, ...)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Search normalized entities by databank, type, provider, or capability.

入力スキーマ

{
  "type": "object",
  "properties": {
    "databank": {
      "type": "string"
    },
    "type": {
      "type": "string"
    },
    "provider": {
      "type": "string"
    },
    "capability": {
      "type": "string"
    },
    "modelType": {
      "type": "string"
    },
    "minContextWindow": {
      "type": "integer",
      "minimum": 0
    },
    "lane": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_entity_evidence(entityId)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Read canonical facts, aliases, history, and provenance for an entity.

入力スキーマ

{
  "type": "object",
  "properties": {
    "entityId": {
      "type": "string",
      "format": "uuid"
    }
  },
  "required": [
    "entityId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_context_contract(databank)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Read a databank's identity, temporal, dimension, and context-packet contract.

入力スキーマ

{
  "type": "object",
  "properties": {
    "databank": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "databank"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢answer_software_questions(claims, compatibility)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Resolve up to four package/API questions and an optional runtime compatibility check.

入力スキーマ

{
  "type": "object",
  "properties": {
    "claims": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "package": {
            "type": "string",
            "minLength": 1
          },
          "api": {
            "type": "string",
            "minLength": 1
          }
        },
        "required": [
          "package",
          "api"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 4
    },
    "compatibility": {
      "type": "object",
      "properties": {
        "package": {
          "type": "string"
        },
        "runtime": {
          "type": "string"
        },
        "runtimeVersion": {
          "type": "string"
        }
      },
      "required": [
        "package",
        "runtime",
        "runtimeVersion"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "claims"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢check_security_exposure(package, version, ecosystem)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a package and the version you are running, return the known vulnerabilities that affect it, worst first, each with the version that fixes it. Advisories whose affected range could not be parsed are returned under undetermined; treat undetermined as unanswered, never as safe.

入力スキーマ

{
  "type": "object",
  "properties": {
    "package": {
      "type": "string",
      "minLength": 1
    },
    "version": {
      "type": "string",
      "minLength": 1
    },
    "ecosystem": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "package",
    "version"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢lookup_vulnerability(cve)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a vulnerability identifier such as a CVE, return what is held about it: the affected package and version range, the version that fixes it, severity, and whether it is recorded as known-exploited. Use this when you have an identifier rather than a package you are running. Fields come back as claims carrying their own authority. status 'known' with authority 'exclusive' means Daystruct has evidence for the value; if you hold a different value, treat it as a conflict to resolve. status 'unknown' with authority 'non_exclusive' means Daystruct has no evidence either way -- an absence of evidence, which does not contradict or supersede anything you already know: keep what you independently know, and stay uncertain if you do not. A field returned as null means Daystruct looked and holds nothing for it; no other Daystruct tool will have it either. Exploitation status is never reported false from a partial catalog.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cve": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "cve"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢check_release_support(product, version)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a product and version, return whether that release line is supported, in security-fix-only maintenance, or past end of life, with the dates behind the answer and the cycles you could upgrade into. A line with no published end-of-life returns undetermined rather than supported.

入力スキーマ

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "minLength": 1
    },
    "version": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "product",
    "version"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢select_model(minContextWindow, capabilities, maxInputPricePerMillionTokens, maxOutputPricePerMillionTokens, provider, ...)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a need -- minimum context window, required capabilities, a price ceiling -- return the models that satisfy it, cheapest input price first, with the corroboration behind each record so you can judge how well-sourced it is. Prices are per million tokens. A model with no published price is returned under undetermined rather than excluded, so an unpriced model never reads as a disqualified one. This returns candidates and their evidence, not a recommendation.

入力スキーマ

{
  "type": "object",
  "properties": {
    "minContextWindow": {
      "type": "integer",
      "exclusiveMinimum": 0
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 6
    },
    "maxInputPricePerMillionTokens": {
      "type": "number",
      "minimum": 0
    },
    "maxOutputPricePerMillionTokens": {
      "type": "number",
      "minimum": 0
    },
    "provider": {
      "type": "string",
      "minLength": 1
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢read_recent_evidence_changes(limit)

Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Read the bounded canonical change feed.

入力スキーマ

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢compat_check(capabilities, bundle, project, verifyReportId)

Resolve Daystruct capabilities to exact versions that fit each other, or get the exact constraint that broke with suggested alternatives. Send the project manifest by default: project.runtime (the node or python version the project runs), project.platform, and the project's package-lock.json (or an installed name->version map) plus the dependency sections of package.json. That makes the answer project-checked rather than bundle-only. Never send source code or other files; only those fields are read and nothing is stored. The result's scope says what it covers (bundle-only, project-checked, project-verified). Its state is compatible, except when you pass bundle (for example security-scanners@latest-verified) instead of capabilities: then it is verified, because that exact set passed its integration suite, and the result names the run and the environment it ran in. Affected versions are refused and listed under advisoriesAvoided; a deprecated version is chosen only when nothing else fits and is named in notes. To reach project-verified, fetch the verify kit for the resolved members, show the user the report the script prints, send it only with the user's agreement (--send), and pass the returned report id as verifyReportId.

入力スキーマ

{
  "type": "object",
  "properties": {
    "capabilities": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "pattern": "^[a-z0-9@/._-]{1,120}$"
          },
          "range": {
            "type": "string",
            "minLength": 1,
            "maxLength": 60,
            "default": "*"
          }
        },
        "required": [
          "id"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 25
    },
    "bundle": {
      "type": "string",
      "pattern": "^[a-z][a-z0-9-]{2,60}@(latest-verified|(0|[1-9]\\d*)\\.(0|[1-9]\\d*)\\.(0|[1-9]\\d*))$"
    },
    "project": {
      "type": "object",
      "properties": {
        "runtime": {
          "type": "object",
          "properties": {
            "node": {
              "type": "string",
              "minLength": 1,
              "maxLength": 40
            },
            "python": {
              "type": "string",
              "minLength": 1,
              "maxLength": 40
            }
          },
          "additionalProperties": false
        },
        "platform": {
          "type": "string",
          "enum": [
            "linux",
            "darwin",
            "win32"
          ]
        },
        "packageJson": {
          "type": "object",
          "properties": {
            "dependencies": {
              "type": "object",
              "additionalProperties": {
                "type": "string",
                "minLength": 1,
                "maxLength": 200
              },
              "propertyNames": {
                "pattern": "^(@[a-z0-9][a-z0-9._~-]*\\/)?[a-z0-9][a-z0-9._~-]*$"
              }
            },
            "devDependencies": {
              "$ref": "#/properties/project/properties/packageJson/properties/dependencies"
            },
            "peerDependencies": {
              "$ref": "#/properties/project/properties/packageJson/properties/dependencies"
            },
            "engines": {
              "type": "object",
              "additionalProperties": {
                "type": "string",
                "maxLength": 200
              }
            }
          },
          "additionalProperties": false
        },
        "lockfile": {
          "type": "object",
          "properties": {
            "lockfileVersion": {
              "type": "integer"
            },
            "packages": {
              "type": "object",
              "additionalProperties": {
                "type": "object",
                "properties": {
                  "version": {
                    "type": "string",
                    "maxLength": 200
                  }
                },
                "additionalProperties": false
              },
              "propertyNames": {
                "maxLength": 400
              }
            }
          },
          "required": [
            "packages"
          ],
          "additionalProperties": false
        },
        "installed": {
          "$ref": "#/properties/project/properties/packageJson/properties/dependencies"
        }
      },
      "required": [
        "runtime",
        "platform"
      ],
      "additionalProperties": false
    },
    "verifyReportId": {
      "type": "string",
      "pattern": "^cvr_[a-f0-9]{24}$"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_compat_verify_kit(members)

Return the files of the local verify step for exact source members from compat_check: a script, its plan, and the interface conformance suites. Write them to a scratch directory and run `node daystruct-verify.mjs` from the user's project; it runs the members' own tests and conformance suites and prints a report of counts and versions only. It sends nothing unless run with --send, which needs the user's agreement. Native members cannot be verified locally.

入力スキーマ

{
  "type": "object",
  "properties": {
    "members": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "pattern": "^[a-z0-9@/._-]{1,120}$"
          },
          "version": {
            "type": "string",
            "pattern": "^\\d+\\.\\d+\\.\\d+$"
          }
        },
        "required": [
          "id",
          "version"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 25
    }
  },
  "required": [
    "members"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_daystruct_validated_guidance(databank, taskFamily, model)

Retrieve reviewed Frontier guidance scoped to an exact databank, task family and tested model. Returns only live, unexpired promotions and their evidence limits; never private test fixtures.

入力スキーマ

{
  "type": "object",
  "properties": {
    "databank": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    },
    "taskFamily": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    }
  },
  "required": [
    "databank",
    "taskFamily",
    "model"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_daystruct_guidance_scopes(databank)

Find task families and exact tested models with live Frontier guidance for a databank, before requesting that guidance.

入力スキーマ

{
  "type": "object",
  "properties": {
    "databank": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    }
  },
  "required": [
    "databank"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢resolve_task_capabilities(session_id, request_id, intent, capabilities, bundle_id, ...)

Select relevant capabilities progressively, or request full delivery. Optional task session remembers prior delivery and reported results; selection never executes or acquires a capability.

入力スキーマ

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "maxLength": 80
    },
    "request_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 120
    },
    "intent": {
      "type": "string",
      "minLength": 3,
      "maxLength": 1000
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 120
      },
      "maxItems": 50
    },
    "bundle_id": {
      "$ref": "#/properties/capabilities/items"
    },
    "delivery": {
      "type": "string",
      "enum": [
        "progressive",
        "full"
      ],
      "default": "progressive"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 3
    },
    "include_repeat": {
      "type": "boolean",
      "default": false
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡create_task_session(request_id, intent, current_stage, steps)

Start compact task context with optional capability steps and dependencies. Requires read and requests:write. No conversation or reasoning trace is stored.

入力スキーマ

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 120
    },
    "intent": {
      "type": "string",
      "minLength": 3,
      "maxLength": 1000
    },
    "current_stage": {
      "type": "string",
      "maxLength": 100,
      "default": "planning"
    },
    "steps": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "pattern": "^[a-z0-9_-]{1,50}$"
          },
          "capability": {
            "type": "string",
            "minLength": 1,
            "maxLength": 120
          },
          "depends_on": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 50
            },
            "maxItems": 20,
            "default": []
          }
        },
        "required": [
          "id",
          "capability"
        ],
        "additionalProperties": false
      },
      "maxItems": 50,
      "default": []
    }
  },
  "required": [
    "request_id",
    "intent"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪record_task_event(session_id, request_id, type, capability, summary, ...)

Report viewed, called, succeeded, failed or skipped capability status, or task stage. Usage and outcomes remain client-reported.

入力スキーマ

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "maxLength": 80
    },
    "request_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 120
    },
    "type": {
      "type": "string",
      "enum": [
        "viewed",
        "called",
        "succeeded",
        "failed",
        "skipped",
        "stage"
      ]
    },
    "capability": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    },
    "summary": {
      "type": "string",
      "maxLength": 500,
      "default": ""
    },
    "current_stage": {
      "type": "string",
      "maxLength": 100
    },
    "reported_tool_turns": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000,
      "default": 0
    },
    "reported_cost_usd": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000,
      "default": 0
    }
  },
  "required": [
    "session_id",
    "request_id",
    "type"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_task_session(session_id, next)

Read compact task context or preview the next ready capabilities without consuming them or extending the session TTL.

入力スキーマ

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "maxLength": 80
    },
    "next": {
      "type": "boolean",
      "default": false
    }
  },
  "required": [
    "session_id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪close_task_session(session_id, request_id, outcome, summary)

Close a task with its reported outcome and compact summary.

入力スキーマ

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "maxLength": 80
    },
    "request_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 120
    },
    "outcome": {
      "type": "string",
      "enum": [
        "completed",
        "abandoned",
        "failed"
      ]
    },
    "summary": {
      "type": "string",
      "maxLength": 500,
      "default": ""
    }
  },
  "required": [
    "session_id",
    "request_id",
    "outcome"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_daystruct_library(query, scope, limit)

Search this account's saved or owned capabilities and bundles. Returns a small shortlist; saving does not acquire, execute or grant access to source. Inspect a selected profile before use.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 200
    },
    "scope": {
      "type": "string",
      "enum": [
        "saved",
        "owned",
        "library"
      ],
      "default": "library"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "default": 3
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢resolve_daystruct_bundle(id)

Read a saved, owned or public bundle with pinned source versions and current member availability. Returns a composition plan, not an execution or purchase. Each capability retains its usage terms.

入力スキーマ

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢discover_daystruct_capabilities(reference, query, licenseStatus, licenseSpdx, licenseEvidence, ...)

Find available Daystruct capabilities using a task sentence or tool name. Query searches return up to eight ranked compact descriptors, matched terms, requirements, limitations, prices and profile links; meta.matched and fullResults expose truncation. Inspect a selected capability by reference for its full contract before requesting help. Provider availability is not proof a task will succeed. Licensing filters narrow the list to source packages whose licensing evidence matches; entries with no licensing evidence are excluded rather than assumed to pass, and a filtered list returns summary licensing only. Read a capability's profile for its full receipt. Licensing findings are evidence against a configured policy, not legal advice.

入力スキーマ

{
  "type": "object",
  "properties": {
    "reference": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "query": {
      "type": "string",
      "maxLength": 200
    },
    "licenseStatus": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "validated",
          "review_required",
          "blocked",
          "legacy_unvalidated"
        ]
      },
      "maxItems": 4
    },
    "licenseSpdx": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 100
      },
      "maxItems": 20
    },
    "licenseEvidence": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "verified-text",
          "verified-upstream-api",
          "declared",
          "unverified"
        ]
      },
      "maxItems": 4
    },
    "licensePolicyState": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "current",
          "policy_outdated",
          "legacy_unvalidated"
        ]
      },
      "maxItems": 3
    },
    "licenseUnresolved": {
      "type": "string",
      "enum": [
        "none"
      ]
    },
    "licenseReciprocal": {
      "type": "string",
      "enum": [
        "exclude",
        "only"
      ]
    },
    "bundleMembers": {
      "type": "string",
      "enum": [
        "all_validated"
      ]
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢prepare_daystruct_capabilities(references)

Group up to six discovered capability IDs into a plan with each profile and delivery instructions. Missing entries remain explicit. Does not acquire, execute, check combined compatibility or charge credits. Your agent can combine these pieces with Daystruct knowledge and verify the resulting task.

入力スキーマ

{
  "type": "object",
  "properties": {
    "references": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 200
      },
      "minItems": 1,
      "maxItems": 6
    }
  },
  "required": [
    "references"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

推奨プロンプト

search_research
Search for information about [topic] using Daystruct
想定されるツール: search_entities
find_specific
Find [specific item] using Daystruct
想定されるツール: search_entities
retrieve_data
Get details about [item] from Daystruct
想定されるツール: get_entity_evidence
fetch_info
Fetch [information type] using Daystruct
想定されるツール: get_entity_evidence
list_items
List all [items] available in Daystruct
想定されるツール: list_daystruct_guidance_scopes

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 23 件
検証済みバージョンは記録されていませんツール 21 件