MCP.so
ログイン

Yandex Wiki Search MCP Server

@dlbolshov

基本情報

Yandex Wiki Search MCP Server について

MCP server for Yandex Wiki with full-text search. Read and write pages, comments, attachments, and dynamic tables (grids) through 27 tools with typed input/output schemas; optional server-side read-only mode for agents.

Yandex Wiki Search MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "yandex-wiki-search": {
      "command": "uvx",
      "args": [
        "yandex-wiki-search-mcp"
      ],
      "env": {
        "WIKI_TOKEN": "YOUR_TOKEN",
        "WIKI_ORG_ID": "YOUR_ORG_ID",
        "WIKI_READ_ONLY": "true"
      }
    }
  }
}

Yandex Wiki Search MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

Connect Claude, Cursor, Windsurf, or any MCP client to Yandex Wiki — full-text search plus full page and grid (dynamic table) management. 27 tools with typed input/output schemas and safety annotations.

Highlights

  • 🔍 Full-text search across the whole wiki (up to 50 results) — the same backend that powers the Wiki web search bar
  • 📄 Pages: create, update, append (top / bottom / anchor), clone, delete + recover, comments, file uploads
  • 📊 Grids: 11 write tools for rows, columns, cells, copy, sort
  • 🔒 Server-side read-only mode (WIKI_READ_ONLY=true) — write tools simply aren't registered, so the agent can't bypass it
  • 🧩 Typed surface: every tool ships input and output JSON schemas plus read-only / destructive / idempotent hints
  • 📝 YFM helpers: write tools return yfm_warnings when markup won't render as intended, and a wiki-mcp://yfm-cheatsheet resource maps GitHub-flavored habits to Yandex Wiki equivalents
  • 🐳 Runs anywhere: stdio for desktop clients, streamable-http + Docker (with optional multi-user OAuth) for teams

Tools

27 tools. All write tools disappear when WIKI_READ_ONLY=true.

Search & read (8)

ToolWhat it does
page_searchFull-text search across the entire Wiki (pages and files), up to 50 ranked results with snippets
page_getGet a page by page_id or slug (accepts full Wiki URLs too)
page_get_descendantsTraverse a page subtree — one flat list of {id, slug} from all nesting levels; fetch_all drains the cursor in one call
page_get_commentsList page comments (fetch_all supported)
page_get_resourcesList page resources (attachments + grids) with server-side title search (fetch_all supported)
page_get_attachmentsList page attachments (fetch_all supported)
page_get_gridsList grids attached to a page (fetch_all supported)
grid_getGet a grid by grid_id with row/column/revision filters

Pages: write (8)

ToolWhat it does
page_createCreate a page
page_updateUpdate page title and/or full content
page_append_contentAppend content to top, bottom, or a named anchor
page_cloneCopy a page to a new slug — the copy gets a new id; children, comments, and history stay with the original. The API has no true move/rename
page_add_commentAdd a comment or reply in a thread
page_deleteDelete a page and receive a recovery token
page_recoverRecover a deleted page by recovery token
page_upload_attachmentUpload a local file in chunks and attach it to a page — not registered under OAUTH_ENABLED=true, where "local" would mean the shared server's filesystem

Grids: write (11)

ToolWhat it does
grid_createCreate a grid on a page
grid_updateUpdate grid title and/or default sort
grid_copyCopy a grid to an existing target page (async operation)
grid_deleteDelete a grid
grid_add_rowsAdd rows at a position or after a given row
grid_update_cellsUpdate individual cells by row + column
grid_delete_rowsDelete rows
grid_move_rowMove a row
grid_add_columnsAdd typed columns
grid_delete_columnsDelete columns by slug
grid_move_columnMove a column

Grid mutations use optimistic locking — fetch the grid first and pass its latest revision.

Docker: ghcr.io/dlbolshov/yandex-wiki-search-mcp:latest · PyPI: yandex-wiki-search-mcp · License: Apache-2.0

コメント

「メモリとナレッジ」の他のコンテンツ