AIBITIOUS 404 LAB - 32 Free Agent Experiments

32 free tools: CVE/data checks and offline agent decisions on permissions, budgets and recovery.

使うべきか

品質と安全性

B
説明の品質
98%
スキーマの完全性
79%
命名の品質
82%
ポイズニングのリスク
80%
権限の一致
90%
プロトコルへの準拠
100%

検出事項(4)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains suspicious base64-like encoded stringreceipt_chain 内
  • LOWTool 'report_missing_information' description lacks action verbreport_missing_information 内
  • LOWTool 'triage_webhook_deliveries' suggests web access but openWorldHint=falsetriage_webhook_deliveries 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

~3,691トークン数(ツール定義)
~615 B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 2.88%)

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": {
    "agent404": {
      "url": "https://aibitious.com/404/mcp/"
    }
  }
}

リモートエンドポイント

https://aibitious.com/404/mcp/streamable-http

できること

ツール一覧

ツール(33)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
⚪resolve_public_fact(identifier)

Resolve one CVE identifier (e.g. CVE-2024-3094) using NIST NVD records. This tool does not execute code, scan targets, or accept arbitrary URLs.

入力スキーマ

{
  "type": "object",
  "properties": {
    "identifier": {
      "title": "Identifier",
      "type": "string"
    }
  },
  "required": [
    "identifier"
  ],
  "title": "resolve_public_factArguments"
}
⚪report_missing_information(topic, consent_to_aggregate)

Opt-in report of a PUBLIC missing-data topic, never include private data or secrets.

入力スキーマ

{
  "type": "object",
  "properties": {
    "topic": {
      "title": "Topic",
      "type": "string"
    },
    "consent_to_aggregate": {
      "default": false,
      "title": "Consent To Aggregate",
      "type": "boolean"
    }
  },
  "required": [
    "topic"
  ],
  "title": "report_missing_informationArguments"
}
⚪json_schema_guard(document, schema)

Validate one JSON object against a SAFE subset of JSON Schema. No remote refs. Offline.

入力スキーマ

{
  "type": "object",
  "properties": {
    "document": {
      "additionalProperties": true,
      "title": "Document",
      "type": "object"
    },
    "schema": {
      "additionalProperties": true,
      "title": "Schema",
      "type": "object"
    }
  },
  "required": [
    "document",
    "schema"
  ],
  "title": "json_schema_guardArguments"
}
🟢csv_data_doctor(csv_text, key_columns, delimiter)

Find missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.

入力スキーマ

{
  "type": "object",
  "properties": {
    "csv_text": {
      "title": "Csv Text",
      "type": "string"
    },
    "key_columns": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Key Columns"
    },
    "delimiter": {
      "default": ",",
      "title": "Delimiter",
      "type": "string"
    }
  },
  "required": [
    "csv_text"
  ],
  "title": "csv_data_doctorArguments"
}
⚪invoice_math_audit(lines, currency, declared_net, declared_tax, declared_gross)

Independently recalculate invoice arithmetic, NOT legal/tax compliance. Synthetic data only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "lines": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Lines",
      "type": "array"
    },
    "currency": {
      "default": "",
      "title": "Currency",
      "type": "string"
    },
    "declared_net": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Declared Net"
    },
    "declared_tax": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Declared Tax"
    },
    "declared_gross": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Declared Gross"
    }
  },
  "required": [
    "lines"
  ],
  "title": "invoice_math_auditArguments"
}
🟡secret_pattern_shield(text)

Detect probable token patterns without returning or storing secret values. Never send real secrets.

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "title": "Text",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "title": "secret_pattern_shieldArguments"
}
⚪openapi_contract_preflight(spec)

Static OpenAPI 3.x lint: missing operation IDs, responses and malformed operations. Offline.

入力スキーマ

{
  "type": "object",
  "properties": {
    "spec": {
      "additionalProperties": true,
      "title": "Spec",
      "type": "object"
    }
  },
  "required": [
    "spec"
  ],
  "title": "openapi_contract_preflightArguments"
}
🟢mcp_registry_preflight(server)

Check a candidate MCP server.json metadata structure; this is NOT official validation.

入力スキーマ

{
  "type": "object",
  "properties": {
    "server": {
      "additionalProperties": true,
      "title": "Server",
      "type": "object"
    }
  },
  "required": [
    "server"
  ],
  "title": "mcp_registry_preflightArguments"
}
⚪http_headers_audit(headers)

Assess supplied HTTP security response headers. No network or live website probe.

入力スキーマ

{
  "type": "object",
  "properties": {
    "headers": {
      "additionalProperties": {
        "type": "string"
      },
      "title": "Headers",
      "type": "object"
    }
  },
  "required": [
    "headers"
  ],
  "title": "http_headers_auditArguments"
}
🟢robots_policy_check(robots_txt, agent, path)

Evaluate supplied robots.txt for one agent/path. Not a legal scraping permission.

入力スキーマ

{
  "type": "object",
  "properties": {
    "robots_txt": {
      "title": "Robots Txt",
      "type": "string"
    },
    "agent": {
      "default": "*",
      "title": "Agent",
      "type": "string"
    },
    "path": {
      "default": "/",
      "title": "Path",
      "type": "string"
    }
  },
  "required": [
    "robots_txt"
  ],
  "title": "robots_policy_checkArguments"
}
⚪json_shape_diff(before, after)

Compare JSON object shapes for added, deleted or changed field types. Offline.

入力スキーマ

{
  "type": "object",
  "properties": {
    "before": {
      "additionalProperties": true,
      "title": "Before",
      "type": "object"
    },
    "after": {
      "additionalProperties": true,
      "title": "After",
      "type": "object"
    }
  },
  "required": [
    "before",
    "after"
  ],
  "title": "json_shape_diffArguments"
}
🟢simulate_agent_action_policy(action, rules)

Dry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.

入力スキーマ

{
  "type": "object",
  "properties": {
    "action": {
      "additionalProperties": true,
      "title": "Action",
      "type": "object"
    },
    "rules": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Rules",
      "type": "array"
    }
  },
  "required": [
    "action",
    "rules"
  ],
  "title": "simulate_agent_action_policyArguments"
}
🟢plan_workflow_recovery(steps)

Plan reverse-order compensations for a supplied workflow DAG; never execute actions.

入力スキーマ

{
  "type": "object",
  "properties": {
    "steps": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Steps",
      "type": "array"
    }
  },
  "required": [
    "steps"
  ],
  "title": "plan_workflow_recoveryArguments"
}
🟢triage_webhook_deliveries(attempts)

Find duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.

入力スキーマ

{
  "type": "object",
  "properties": {
    "attempts": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Attempts",
      "type": "array"
    }
  },
  "required": [
    "attempts"
  ],
  "title": "triage_webhook_deliveriesArguments"
}
🟢check_claim_provenance(claims, sources)

Check whether supplied claim references reach at least one declared source; not fact checking.

入力スキーマ

{
  "type": "object",
  "properties": {
    "claims": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Claims",
      "type": "array"
    },
    "sources": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Sources",
      "type": "array"
    }
  },
  "required": [
    "claims",
    "sources"
  ],
  "title": "check_claim_provenanceArguments"
}
🟢minimize_agent_data(fields, allowed_fields, max_retention_days)

Check declared fields, retention and model transfer against a supplied local policy.

入力スキーマ

{
  "type": "object",
  "properties": {
    "fields": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Fields",
      "type": "array"
    },
    "allowed_fields": {
      "items": {
        "type": "string"
      },
      "title": "Allowed Fields",
      "type": "array"
    },
    "max_retention_days": {
      "title": "Max Retention Days",
      "type": "integer"
    }
  },
  "required": [
    "fields",
    "allowed_fields",
    "max_retention_days"
  ],
  "title": "minimize_agent_dataArguments"
}
🟢scope_delta(payload)

Find newly granted permissions outside an approved set. Offline check. Supply payload like {"before":["read"],"after":["read","send"],"approved_additions":[]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "scope_deltaArguments"
}
🟢approval_packet(payload)

Find missing or expired fields before seeking human approval. Offline check. Supply payload like {"now_unix":100,"action":{"actor":"agent","tool":"mail.send","target":"draft1","effect":"send","reason":"owner_request","expiry_unix":200}}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "approval_packetArguments"
}
🟢budget_envelope(payload)

Check worst-case proposed cost against a local hard budget. Offline check. Supply payload like {"limit_usd":"0","spent_usd":"0","reserved_usd":"0","proposed_worst_case_usd":"0"}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "budget_envelopeArguments"
}
🟢retry_schedule(payload)

Preview capped exponential retries against a deadline. Offline check. Supply payload like {"attempts":3,"first_delay_seconds":2,"max_delay_seconds":10,"deadline_seconds":30}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "retry_scheduleArguments"
}
🟢duplicate_actions(payload)

Find duplicate attempts and conflicting key reuse. Offline check. Supply payload like {"calls":[{"idempotency_key":"k1","payload_fingerprint":"hash1"},{"idempotency_key":"k1","payload_fingerprint":"hash1"}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "duplicate_actionsArguments"
}
🟢prerequisite_gate(payload)

Check whether all declared evidence prerequisites are present. Offline check. Supply payload like {"requirements":[{"id":"deploy","evidence_refs":["ci"]}],"available_evidence":["ci"]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "prerequisite_gateArguments"
}
🟢evidence_expiry(payload)

Flag stale observations before an agent acts. Offline check. Supply payload like {"now_unix":200,"records":[{"id":"health","observed_unix":100,"ttl_seconds":120}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "evidence_expiryArguments"
}
🟢citation_matrix(payload)

Find claims with missing or unknown citation identifiers. Offline check. Supply payload like {"claims":[{"id":"claim1","citation_refs":["src1"]}],"citations":["src1"]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "citation_matrixArguments"
}
🟢schema_impact(payload)

Identify downstream consumers broken by changed fields. Offline check. Supply payload like {"before":{"id":1},"after":{},"consumers":[{"id":"client","required_fields":["id"]}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "schema_impactArguments"
}
🟢boundary_cases(payload)

Generate bounded edge cases from simple field constraints. Offline check. Supply payload like {"fields":[{"name":"count","type":"integer","minimum":0,"maximum":10}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "boundary_casesArguments"
}
🟢slo_burn(payload)

Measure error-budget burn against a supplied target. Offline check. Supply payload like {"target_percent":"99","total":1000,"bad":20,"alert_burn_rate":2}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "slo_burnArguments"
}
🟢queue_forecast(payload)

Project backlog and drain time from supplied rates. Offline check. Supply payload like {"backlog":100,"incoming_per_hour":10,"capacity_per_hour":20,"horizon_hours":4}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "queue_forecastArguments"
}
🟢permission_paths(payload)

Find sensitive targets reachable through declared capability edges. Offline check. Supply payload like {"start":"agent","edges":[{"from":"agent","to":"secret"}],"sensitive_targets":["secret"]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "permission_pathsArguments"
}
🟢context_budget(payload)

Select prioritized context chunks inside a token limit. Offline check. Supply payload like {"max_tokens":100,"chunks":[{"id":"source1","tokens":40,"priority":10}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "context_budgetArguments"
}
🟢release_gate(payload)

Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "release_gateArguments"
}
🟢manifest_drift(payload)

Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "manifest_driftArguments"
}
🟢receipt_chain(payload)

Check links in a supplied digest receipt chain. Offline check. Supply payload like {"root_sha256":"0000000000000000000000000000000000000000000000000000000000000000","receipts":[{"previous_sha256":"0000000000000000000000000000000000000000000000000000000000000000","sha256":"1111111111111111111111111111111111111111111111111111111111111111"}]}. Advisory result only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "receipt_chainArguments"
}

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 33 件