Yandex Wiki Search MCP
未认领MCP server for Yandex Wiki: full-text search, pages, comments, attachments and dynamic tables. 27 typed tools, server-side read-only mode, Docker-ready.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'yandex-wiki-search-mcp' -- 'uvx' 'yandex-wiki-search-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
34 个工具中显示 34 个
文档中列出的工具 (34)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
grid_add_columns
Add typed columns
grid_add_rows
Add rows at a position or after a given row
grid_copy
Copy a grid to an existing target page (async operation)
grid_create
Create a grid on a page
grid_delete
Delete a grid
grid_delete_columns
Delete columns by slug
grid_delete_rows
Delete rows
grid_get
Get a grid by gridid with row/column/revision filters
grid_move_column
Move a column
grid_move_row
Move a row
grid_update
Update grid title and/or default sort
grid_update_cells
Update individual cells by row + column
grid_update.default_sort
takes [{"column": "status", "direction": "asc"}] entries; the server converts them to the wire format the API expects.
page_add_comment
Add a comment or reply in a thread
page_append_content
Append content to top, bottom, or a named anchor
page_clone
Copy a page to a new slug — the copy gets a new id; children, comments, and history stay with the original; occupied slugs are refused. The API has no true move/rename (details)
page_create
Create a page
page_delete
Delete a page and receive a recovery token
page_delete_attachment
Delete an attachment from a page
page_delete_comment
Delete a comment; returns the page's updated comment count
page_download_attachment
Download an attachment to a local file — streamed to disk with no size cap, nothing enters the conversation. Written atomically (.part → fsync → rename), refuses to overwrite unless asked, and lands with the permissions a normal write would give (0666 & ~umask, never executable); replacing a file ke
page_edit
Edit content by exact-text replacements without resending the whole page; a missing or ambiguous match fails the call before anything is written; writes back with allowmerge so a concurrent edit is merged, not overwritten
page_get
Get a page by pageid or slug (accepts full Wiki URLs too)
page_get_attachments
List page attachments (fetchall supported)
page_get_comments
List page comments (fetchall supported)
page_get_descendants
Traverse a page subtree — one flat list of {id, slug} from all nesting levels; fromroot=true walks the whole Wiki; fetchall drains the cursor in one call
page_get_grids
List grids attached to a page (fetchall supported)
page_get_resources
List page resources (attachments + grids) with server-side title search (fetchall supported)
page_read_attachment
Read an attachment's content straight into the conversation (nothing is saved anywhere) — PNG/JPEG/GIF/WebP as a native image block that vision-capable clients render, text as text (SVG included: it is XML, and an image block a vision API cannot decode fails the host's next call), other binaries as
page_recover
Recover a deleted page by recovery token
page_search
Full-text search across the entire Wiki (pages and files), ranked results with a text excerpt each; server-side filters, and cursor paging through ~100 results in the highlight mode (up to 50 in one call otherwise)
page_update
Update page title and/or full content; set or clear a redirect to another page
page_upload_attachment
Upload a local file in chunks and attach it to a page — not registered under OAUTHENABLED=true, where "local" would mean the shared server's filesystem
user_get_current
Who am I — username and homecluster (the caller's personal-section slug)