Base de Conhecimento

Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes

使うべきか

品質と安全性

B
説明の品質
93%
スキーマの完全性
62%
命名の品質
82%
ポイズニングのリスク
100%
権限の一致
90%
プロトコルへの準拠
100%

検出事項(4)

  • LOWTool 'kb_search' description lacks action verbkb_search 内
  • LOWTool 'kb_add_text' description lacks action verbkb_add_text 内
  • LOWTool 'connect' description lacks action verbconnect 内
  • LOWTool 'kb_ingest_url' suggests web access but openWorldHint=falsekb_ingest_url 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

~2,173トークン数(ツール定義)
~753 B一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 1.70%)

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": {
    "kb-mcp": {
      "url": "https://api.mcp.ai/p_kb"
    }
  }
}

リモートエンドポイント

https://api.mcp.ai/p_kbstreamable-http

できること

ツール一覧

ツール(13)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢kb_search(query, top_k, account)

Busca semântica na base de conhecimento. Devolve os trechos (chunks) mais relevantes pra usar como contexto, com nome do arquivo de origem e score. Retrieval-only: você sintetiza a resposta a partir dos trechos.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "top_k": {
      "type": "number"
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢kb_list_documents(account)

Lista os documentos da base (id, nome, status, tamanho, nº de chunks).

入力スキーマ

{
  "type": "object",
  "properties": {
    "account": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢kb_get_document(document_id, account, document_ids)

Metadados + status de um documento específico (sem o texto cru). Bulk support: accepts document_ids for batched execution.

入力スキーマ

{
  "type": "object",
  "properties": {
    "document_id": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "document_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "document_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡kb_add_text(title, text, account)

Adiciona um texto colado à base (vira um documento indexado e buscável). Útil pra notas, trechos, anotações.

入力スキーマ

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "title",
    "text"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡kb_ingest_url(url, filename, account)

Baixa um arquivo de uma URL (.md/.txt/.docx) e o indexa na base. Bom pra ingerir um documento remoto sem upload manual.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    },
    "filename": {
      "type": "string"
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🔴kb_remove_document(document_ids, account)

Remove um ou mais documentos da base (apaga o original, os chunks e o índice). Aceita uma lista de ids.

入力スキーマ

{
  "type": "object",
  "properties": {
    "document_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "document_ids"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢kb_list_accounts

Lista as bases de conhecimento conectadas neste install. Retorna cada base com id, rótulo e um flag is_default (true quando só há uma — não precisa passar `account` nas outras tools). Com várias bases, toda kb_* aceita um `account` opcional (id ou rótulo).

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢show_version

Show the current MCP platform and adapter versions.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡report_bug(message, context, conversation)

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

入力スキーマ

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string"
    },
    "context": {
      "default": "",
      "type": "string"
    },
    "conversation": {
      "default": "[]",
      "type": "string"
    }
  },
  "required": [
    "message"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢connect

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢toolkit_info

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡marketplace(action, query, mcp_id, limit, tier_slug, ...)

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

入力スキーマ

{
  "type": "object",
  "properties": {
    "action": {
      "default": "search",
      "type": "string",
      "enum": [
        "search",
        "describe",
        "install",
        "uninstall",
        "subscribe",
        "cancel",
        "resume",
        "report_bug",
        "request_mcp",
        "list_tools",
        "invoke",
        "search_prompts",
        "get_prompt",
        "publish_prompt"
      ]
    },
    "query": {
      "default": "",
      "type": "string"
    },
    "mcp_id": {
      "default": "",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "type": "number"
    },
    "tier_slug": {
      "default": "",
      "type": "string"
    },
    "immediate": {
      "default": false,
      "type": "boolean"
    },
    "cancel_reason": {
      "type": "string",
      "enum": [
        "too_expensive",
        "missing_features",
        "switched_service",
        "unused",
        "customer_service",
        "too_complex",
        "low_quality",
        "other"
      ]
    },
    "cancel_comment": {
      "default": "",
      "type": "string"
    },
    "message": {
      "default": "",
      "type": "string"
    },
    "report_context": {
      "default": "",
      "type": "string"
    },
    "conversation": {
      "default": "[]",
      "type": "string"
    },
    "request_name": {
      "default": "",
      "type": "string"
    },
    "request_details": {
      "default": "",
      "type": "string"
    },
    "tool_id": {
      "default": "",
      "type": "string"
    },
    "arguments": {
      "default": "{}",
      "type": "string"
    },
    "prompt_slug": {
      "default": "",
      "type": "string"
    },
    "prompt_vars": {
      "default": "{}",
      "type": "string"
    },
    "prompt_category": {
      "default": "",
      "type": "string"
    },
    "prompt_tool": {
      "default": "",
      "type": "string"
    },
    "prompt_title": {
      "default": "",
      "type": "string"
    },
    "prompt_description": {
      "default": "",
      "type": "string"
    },
    "prompt_body": {
      "default": "",
      "type": "string"
    },
    "prompt_targets": {
      "default": [],
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "claude",
          "chatgpt",
          "cursor",
          "lovable"
        ]
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡authenticate(token)

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

入力スキーマ

{
  "type": "object",
  "properties": {
    "token": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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 13 件
検証済みバージョンは記録されていませんツール 13 件