yandex-wiki-search-mcp
@dlbolshov
About yandex-wiki-search-mcp
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.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"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"
}
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
Connect Claude, Cursor, Windsurf, or any MCP client to Yandex Wiki β full-text search plus full page and grid (dynamic table) management. 27 tools with typed input/output schemas and safety annotations.
Highlights
- π Full-text search across the whole wiki (up to 50 results) β the same backend that powers the Wiki web search bar
- π Pages: create, update, append (top / bottom / anchor), clone, delete + recover, comments, file uploads
- π Grids: 11 write tools for rows, columns, cells, copy, sort
- π Server-side read-only mode (
WIKI_READ_ONLY=true) β write tools simply aren't registered, so the agent can't bypass it - π§© Typed surface: every tool ships input and output JSON schemas plus read-only / destructive / idempotent hints
- π YFM helpers: write tools return
yfm_warningswhen markup won't render as intended, and awiki-mcp://yfm-cheatsheetresource maps GitHub-flavored habits to Yandex Wiki equivalents - π³ 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)
| Tool | What it does |
|---|---|
page_search | Full-text search across the entire Wiki (pages and files), up to 50 ranked results with snippets |
page_get | Get a page by page_id or slug (accepts full Wiki URLs too) |
page_get_descendants | Traverse a page subtree β one flat list of {id, slug} from all nesting levels; fetch_all drains the cursor in one call |
page_get_comments | List page comments (fetch_all supported) |
page_get_resources | List page resources (attachments + grids) with server-side title search (fetch_all supported) |
page_get_attachments | List page attachments (fetch_all supported) |
page_get_grids | List grids attached to a page (fetch_all supported) |
grid_get | Get a grid by grid_id with row/column/revision filters |
Pages: write (8)
| Tool | What it does |
|---|---|
page_create | Create a page |
page_update | Update page title and/or full content |
page_append_content | Append content to top, bottom, or a named anchor |
page_clone | Copy a page to a new slug β the copy gets a new id; children, comments, and history stay with the original. The API has no true move/rename |
page_add_comment | Add a comment or reply in a thread |
page_delete | Delete a page and receive a recovery token |
page_recover | Recover a deleted page by recovery token |
page_upload_attachment | Upload a local file in chunks and attach it to a page β not registered under OAUTH_ENABLED=true, where "local" would mean the shared server's filesystem |
Grids: write (11)
| Tool | What it does |
|---|---|
grid_create | Create a grid on a page |
grid_update | Update grid title and/or default sort |
grid_copy | Copy a grid to an existing target page (async operation) |
grid_delete | Delete a grid |
grid_add_rows | Add rows at a position or after a given row |
grid_update_cells | Update individual cells by row + column |
grid_delete_rows | Delete rows |
grid_move_row | Move a row |
grid_add_columns | Add typed columns |
grid_delete_columns | Delete columns by slug |
grid_move_column | Move a column |
Grid mutations use optimistic locking β fetch the grid first and pass its latest revision.
Docker: ghcr.io/dlbolshov/yandex-wiki-search-mcp:latest Β· PyPI: yandex-wiki-search-mcp Β· License: Apache-2.0
Basic information
More Memory & Knowledge MCP servers
Mcp Knowledge Graph
shanehollomanMCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
Tempreon
TempreonPerson-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions β captured in one assistant, available in all of them.
Notion MCP Server
suekouA Model Context Protocol server for connecting Notion to MCP-compatible clients
Groundwork
Rarefied-EarthGroundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
Obsidian MCP Server
StevenStavrakisA simple MCP server for Obsidian
Comments