yandex-wiki-search-mcp
This server is an MCP interface to Yandex Wiki, exposing 33 typed tools for searching, reading, writing, and managing wiki pages, comments, attachments, and dynamic tables (grids).
Full-text search across the entire wiki (up to 50 results per call, server-side filters by section/type/author/date, highlighting mode with cursor paging up to ~100 results)
Page reads: get pages by id/slug/URL, list descendants/subtrees, read comments, attachments, resources, and grids
Page creation and editing: create, update full content, partial edits via exact-text replacements, append to top/bottom/anchor, clone pages
Page lifecycle: delete with recovery token, recover deleted pages, set/clear redirects
Comments: list, add, reply in threads, and delete comments
Attachments: list, read content inline (images as vision blocks, text as text, binaries as base64), upload local files, download to disk, delete attachments
Grids (dynamic tables): create, update, copy, delete, add/delete/move rows, add/delete/move columns, update individual cells — with optimistic locking via revisions
User context: identify the current user, their org ids, and personal wiki section
Safety features: server-side read-only mode that omits write tools entirely, destructive-operation hints, and YFM markup warnings for written content
English | Русский
Yandex Wiki Search MCP

Connect Claude, Cursor, Windsurf, or any MCP client to Yandex Wiki: full-text search, pages, comments, attachments, and dynamic tables ("grids") — 33 tools with typed schemas.
An unofficial project — not affiliated with or endorsed by Yandex.
🔍 Full-text search across the entire wiki — the same backend that powers the Wiki web search bar, up to 50 results per query
📄 Full page lifecycle — create, update, append (top / bottom / anchor), clone, delete with a recovery token, comments, file uploads
📊 Dynamic tables (grids) — 11 write tools: rows, columns, cells, copy, sort
🔒 Server-side read-only mode —
WIKI_READ_ONLY=truesimply doesn't register write tools, so the agent can't bypass it🧩 Typed tool surface — every tool ships an input JSON schema and safety annotations (read-only / destructive / idempotent hints), and all but
page_read_attachment, which answers with a native image or resource block, an output schema too🐳 Runs anywhere — stdio for desktop clients, streamable-http + Docker (with optional multi-user OAuth) for teams
Quick start
Get a Yandex OAuth token with Wiki access (official guide) and your organization ID.
Install into your client:
The Claude Desktop badge downloads the .mcpb bundle of the latest release —
double-click it and Claude Desktop installs the server, prompting for the token
and org ID (uv must be installed).
{
"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"
}
}
}
}claude mcp add yandex-wiki-search \
-e WIKI_TOKEN=YOUR_TOKEN -e WIKI_ORG_ID=YOUR_ORG_ID -e WIKI_READ_ONLY=true \
-- uvx yandex-wiki-search-mcp{
"mcpServers": {
"yandex-wiki-search": {
"command": "docker",
"args": ["run","--rm","-i",
"-e","WIKI_TOKEN","-e","WIKI_ORG_ID","-e","WIKI_READ_ONLY=true",
"ghcr.io/dlbolshov/yandex-wiki-search-mcp:latest"],
"env": {"WIKI_TOKEN":"YOUR_TOKEN","WIKI_ORG_ID":"YOUR_ORG_ID"}
}
}
}Start withWIKI_READ_ONLY=true — the server won't even register write tools.
Flip it to false once you trust your agent with edits.
Ask your agent something — see below.
The server runs on MCP Python SDK v2. That is invisible to clients — one v2 server
answers every protocol revision back to 2024-11-05 as well as the current one, so
there is nothing to change on your side and nothing to reinstall.
The only reason to hold back is a shared environment that pins mcp<2 for something
else. 1.0.1 is the last release built on the 1.x SDK and stays on PyPI:
pip install "yandex-wiki-search-mcp<1.1"Related MCP server: mediawiki-mcp-server
What can it do
"Find our onboarding docs and summarize the key steps."
"What do we have on incident response? Open the most relevant page."
"Create a page
team/weekly-notesand append today's standup summary.""Add a row to the on-call rotation grid: alice, next week."
"Upload this PDF to the project page and link it at the bottom."
"Delete the draft page, but keep the recovery token in case I change my mind."
Tools
33 tools. All write tools disappear when WIKI_READ_ONLY=true.
Search & read (10)
Tool | What it does |
| 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 |
| Get a page by |
| Traverse a page subtree — one flat list of |
| List page comments ( |
| List page resources (attachments + grids) with server-side title search ( |
| List page attachments ( |
| 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 a base64 blob. The format is decided by the file's magic bytes, not by the wire's claim. Capped to protect the model's context window: 128 KiB for text/binary, 2 MiB for images; anything larger is refused with a pointer to |
| List grids attached to a page ( |
| Get a grid by |
| Who am I — |
Pages: write (12)
Tool | What it does |
| Create a page |
| Update page title and/or full content; set or clear a redirect to another page |
| 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 |
| Append content to top, bottom, or a named anchor |
| 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) |
| Add a comment or reply in a thread |
| Delete a comment; returns the page's updated comment count |
| Delete an attachment from a page |
| Delete a page and receive a recovery token |
| Recover a deleted page by recovery token |
| Upload a local file in chunks and attach it to a page — registered only with |
| Download an attachment to a local file — streamed to disk with no size cap, nothing enters the conversation. Written atomically ( |
Grids: write (11)
Tool | What it does |
| Create a grid on a page |
| Update grid title and/or default sort |
| Copy a grid to an existing target page (async operation) |
| Delete a grid |
| Add rows at a position or after a given row |
| Update individual cells by row + column |
| Delete rows |
| Move a row |
| Add typed columns |
| Delete columns by slug |
| Move a column |
Grid specifics:
Mutations use optimistic locking — fetch the grid first and pass the latest
revision.grid_update.default_sorttakes[{"column": "status", "direction": "asc"}]entries; the server converts them to the wire format the API expects.grid_add_columnsrequiresrequiredon every column because the real API validates it.grid_copyreturns operation metadata, not a ready copied grid object.
How it compares
Facts verified against the alternatives' docs and published code, July–August 2026;
the official hosted server's tool list captured live from mcp.wiki.yandex.net
(wiki-mcp-server 1.28.1, 2026-08-11).
yandex-wiki-search-mcp | Yandex's official MCP (hosted) | ||||
Full-text search | ✅ up to 50 results, server-side filters + highlighting | ❌ no search tool | ❌ | ✅ up to 10 results | ❌ |
Pages: create / update / append / delete + recover | ✅ all, plus partial edits via text replacement ( | partial — no append / recover; has partial edits via text replacement | ✅ all | partial — no append / recover | partial — no recover |
Pages: clone to a new slug | ✅ | ❌ | ❌ | ❌ | ✅ |
Grids: write tools | ✅ 11 | ✅ 12, incl. column update + row pin/color | ✅ 11 | ❌ read-only | ✅ 11, incl. clone |
Comments, attachment upload | ✅ incl. deletion, inline image preview, and download to disk | comments ✅ / upload ❌ (download + preview instead) | ✅ | ❌ | ❌ |
Server-side read-only mode | ✅ | ❌ | ✅ | ❌ | ❌ |
Typed output schemas + tool annotations | ✅ | ❌ | ❌ | ❌ | ❌ tools return plain strings |
YFM helpers | ✅ syntax cheat sheet resource + | ❌ | ❌ | ❌ | ✅ Markdown→YFM converter + page-tree cache, prompt templates |
Docker / PyPI / MCP Registry | ✅ / ✅ / ✅ | — hosted service, closed source, nothing to install | ✅ / ✅ / ✅ | ❌ manual install | ❌ / ✅ / ❌ |
Multi-user OAuth for HTTP deployments | ✅ | ❌ per-user token pasted into static headers, no OAuth flow | ✅ | ❌ | ❌ |
Also worth knowing:
best-doctor/mcp-yandex-wiki (Python) — page create / update plus reads, with a separate
-roread-only entry point; no delete / recover, no grids, no search; PyPI onlybrekhov-ilya/yandex-wiki-mcp (npm) — pages read / write / move, grids read-only; interactive PKCE token flow with auto-refresh, no full-text search
n-r-w/yandex-mcp (Go) — Yandex Tracker + Wiki in one server, read-only by design (5 wiki read tools), no search; auth via IAM tokens from the
ycCLI only — Yandex OAuth tokens are not supportedbim-ba/ycli (Python) — one toolkit for Tracker + Wiki + Forms: a CLI, a Python SDK, a Claude Code plugin, and an MCP server whose Wiki surface is 42
wiki_*tools (15 read / 27 write, annotated, with a--read-onlyflag); no full-text search tool, and attachment downloads stay CLI/SDK-only
As of August 2026, full-text search exists only here (up to 50 results) and in slartus (up to 10) — Yandex's own hosted server ships without a search tool — and the combination of search, grid writes, server-side read-only mode, and typed schemas is unique to this project.
This project is a fork of ya-yandex-wiki-mcp and builds on findings from
slartus/mcp-yandex-wiki — see Credits.
Full-text search
page_search wraps the POST /v1/search endpoint — the same backend that powers the
Wiki web search bar, undocumented until Yandex published its
API reference in
August 2026. Search first, then open a result with page_get by its slug.
Two wire modes. By default: up to 50 results in one call (
limitis clamped to 1–50; the API rejects anything else) and no pagination — the response cursors are alwaysnull. Withhighlight=true: pages are hard-capped at 10 results regardless oflimit, matches come wrapped in<em>, andcursor(the page number echoed back innext_cursor) walks up to ~100 results. The set ends whenresultscomes back empty ornext_cursorisnullon a non-empty page — past the endnext_cursorkeeps counting up over empty pages, so it alone does not mean "more exists".Filters run server-side, before the limit — a filtered search does not lose matches to it:
slug_prefix(section filter, deep prefixes liketech-doc/mlare fine),result_type(page/file),authors(page owners byuid/cloud_uid—user_get_currentsupplies your own, turning "find my pages about X" into two calls), andcreated_between/modified_betweendate intervals (both bounds required — the API rejects open ones).Quoted
"exact phrase"queries work;pageresults get absolutehttps://wiki.yandex.ru/...links,fileresults get direct download links.contentis a ~510-character excerpt, not the page and not a summary: it is cut from wherever the match sits, the query terms need not be inside it, and its line breaks and tabs are the page's own layout (table cells arrive tab-separated) rather than separators between fragments. Passhighlight=trueto get matches wrapped in<em>tags. Read the page withpage_getbefore answering from it. Empty forfileresults.
Traversing the tree
page_get_descendants returns a subtree as one flat list of {id, slug} from every
nesting level. Passing from_root=true instead of page_id/slug walks the whole
Wiki — the way in when no starting slug is known, so search is not the only entry
point. Prefer a section slug when you have one: wikis run to thousands of pages, and
fetch_all stops at its ~500-item cap with truncated: true.
More verified API behavior (scopes, 403 semantics, error envelopes, limits): docs/api-notes.md.
Configuration
Variable | Required | Default | Description |
| one of the two | — | Yandex OAuth token (takes precedence when both are set) |
| — | IAM token (Yandex Cloud organizations) | |
| exactly one of the two | — | Yandex 360 organization ID ( |
| — | Yandex Cloud organization ID ( | |
| no |
|
|
| no |
|
|
| no |
| HTTP transports only. The Docker image sets |
| no | loopback without OAuth | HTTP transports only: comma-separated |
| no |
|
|
| no |
| Logs go to stderr; |
| no |
| Wiki API endpoint |
| no |
| Base for absolute page links in |
| no |
|
|
| no |
| Retries for dropped connections and |
| no |
| Text duplicate of structured tool results: |
With OAUTH_ENABLED=true the server becomes an OAuth provider: each MCP user
authorizes with their own Yandex account, and requests to the Wiki API are made with
their personal token. page_upload_attachment and page_download_attachment are
not registered in this mode — nor on any HTTP transport: they read and write files
on the machine the server runs on, which over HTTP is not the caller's machine.
Variable | Default | Description |
|
| Enable the OAuth provider |
|
|
|
|
| Yandex OAuth server |
|
| Request Wiki scopes during authorization |
| — | Your Yandex OAuth app credentials |
|
| How long a dynamically registered MCP client is kept unused. Registration is unauthenticated by protocol design, so without an expiry every registration is kept forever. A registration nobody signs in with is dropped this long after registering; each sign-in or token refresh restarts the window, counted from the moment the tokens it issued run out: the 31-day refresh token, or the access token if Yandex issued a longer one (commonly a year). Client secrets never expire on their own ( |
| — | Public URL of this server (OAuth callbacks) |
| — | Comma-separated base64 32-byte keys (required for |
|
| Redis connection |
Choosing the organization per user. WIKI_ORG_ID / WIKI_CLOUD_ORG_ID are optional
under OAuth, because each request can name its own organization: append ?orgId=... (or
?cloudOrgId=...) to the MCP server URL your client connects to. A query parameter wins
over the server-wide setting, so one deployment can serve several organizations. If a
request carries neither, the tool call fails with a message pointing at both options —
set the environment variable as the default if all your users share one organization.
See .env.example for the full annotated list and compose.yaml for a Redis baseline.
Deployment
%%{init: {"flowchart": {"wrappingWidth": 300}}}%%
flowchart LR
L["Local MCP client<br/>Claude / Cursor /<br/>Windsurf / VS Code<br/>single user"]
T["Team MCP clients<br/>multi-user,<br/>optional OAuth"]
S["yandex-wiki-search-mcp"]
W["Yandex Wiki API"]
R[("Redis<br/>optional OAuth<br/>token store")]
L -- "stdio" --> S
T -- "streamable-http" --> S
S --> W
S -.-> RHTTP server via Docker (the MCP endpoint is http://localhost:8000/mcp):
docker run --env-file .env -e TRANSPORT=streamable-http -p 127.0.0.1:8000:8000 \
--log-opt max-size=10m --log-opt max-file=3 \
ghcr.io/dlbolshov/yandex-wiki-search-mcp:latestWithoutOAUTH_ENABLED=true the HTTP endpoint has no authentication of its
own: anyone who can reach the port works with your WIKI_TOKEN. The examples
publish it on loopback only, which keeps other machines out, and the server
answers only loopback Host names, which keeps out a web page that rebinds
its own name to 127.0.0.1 (see MCP_ALLOWED_HOSTS). Neither is
authentication: any process on the machine can still use it. Widen access
only behind an authenticating reverse proxy, or with OAuth on.
The server writes no log files of its own — everything goes to stderr, which
Docker's defaultjson-file driver stores without a size limit. The
--log-opt flags above cap it; drop them only if your daemon already sets a
default.
services:
mcp-wiki:
image: ghcr.io/dlbolshov/yandex-wiki-search-mcp:latest # or: build: .
ports:
- "127.0.0.1:8000:8000"
environment:
- WIKI_TOKEN=${WIKI_TOKEN}
- WIKI_ORG_ID=${WIKI_ORG_ID}
- TRANSPORT=streamable-http
# Only if another container reaches it as http://mcp-wiki:8000:
# - MCP_ALLOWED_HOSTS=localhost,127.0.0.1,mcp-wiki
logging:
driver: json-file
options:
max-size: "10m"
max-file: "3"For Redis-backed OAuth storage, use the existing compose.yaml as the baseline.
Security
Read-only is server-side: with
WIKI_READ_ONLY=truewrite tools are never registered — there is nothing for a confused agent to call.Plain-token HTTP is unauthenticated: with an HTTP transport and OAuth off, every caller that reaches the port acts as the owner of
WIKI_TOKEN— in any organization that token can reach, since?orgId=/?cloudOrgId=on the endpoint override the configured one. Keep it on loopback or behind an authenticating proxy, or enable OAuth. Loopback alone does not keep out a web page that rebinds its own name to127.0.0.1, so the server also answers only theHostnames inMCP_ALLOWED_HOSTS— loopback ones by default. The local-filesystem tools (page_upload_attachment,page_download_attachment) are registered over stdio only, so an HTTP server never reads or writes its own disk on a caller's behalf.Wiki API does not enforce OAuth scopes (re-verified 2026-08-11, after Yandex documented the scopes — see docs/api-notes.md): a
wiki:readtoken can still write, so use the read-only mode rather than relying on token scopes.Secrets are
SecretStrthroughout — masked in logs andrepr;DEBUGHTTP logging never includes headers or bodies.Deletion is recoverable:
page_deletereturns a recovery token forpage_recover.Unrelated keys in a shared
.envare ignored, but a misspelled setting (WIKI_READ_ONL) stops the server instead of silently falling back to a default you did not choose.
Development
uv sync --dev
uv run yandex-wiki-search-mcp # run locally
uv run pytest # testsuv picks an interpreter from Python 3.11–3.14, the range uv.lock has wheels for
(.python-versions), and downloads one if the machine has none.
Before committing, run the full verification set from CONTRIBUTING.md. How the server is put together — the layers, the code map, testing seams, CI and the release process — is described in docs/architecture.md. Verified API behavior and probe scripts are documented in docs/api-notes.md.
The Wiki API drifts (the search endpoint silently changed contract once already, back
when it was undocumented) — scripts/contract_sweep.py re-verifies every client method
against a live organization and reports validation mismatches and undeclared keys:
uv run python scripts/contract_sweep.py users/YOU/contract-sweep # live contract checks
uv run python scripts/contract_sweep.py users/YOU/contract-sweep --cleanup # remove fixturesWith SWEEP_SLUG=users/YOU/contract-sweep in .env (see .env.example) the slug argument
can be omitted; the server itself never reads that variable.
The API drift check workflow runs the same sweep
weekly when the DRIFT_* repository secrets are configured
(instructions in the workflow header); without them it skips quietly.
Credits
This project began as a fork of APonkratov/yandex-wiki-mcp
(ya-yandex-wiki-mcp) by Aleksandr Ponkratov, an excellent, well-tested Python MCP server
for the Yandex Wiki API, licensed under Apache-2.0. It has since grown its own surface —
full-text search, typed input schemas on all 33 tools and output schemas on 32, YFM helpers,
cursor draining, multi-user OAuth and a live contract sweep against the API — while the
original copyright and license are preserved (see LICENSE and NOTICE).
The idea and key API findings behind full-text search come from
slartus/mcp-yandex-wiki (JavaScript, MIT):
it was the first to discover the then-undocumented POST /v1/search endpoint (Yandex
published a reference for it only in August 2026) and to report that OAuth scopes are
not enforced. No code was taken from it — only findings and ideas, independently
re-verified against a live organization and extended here.
Trademarks
"Yandex" and "Yandex Wiki" are trademarks of YANDEX LLC. This is an unofficial, community-built project: not affiliated with, sponsored, or endorsed by Yandex — the names are used nominatively, to state which service the server talks to. The logo is an original mark that reproduces neither Yandex Wiki nor MCP branding (design notes).
mcp-name: io.github.dlbolshov/yandex-wiki-search-mcp
Available Tools
33 toolsgrid_add_columnsAdd Wiki Grid ColumnsA
Add columns to a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: columns (required), grid_id (required), revision (required), position. Returns: Row and column mutations answer with `results` (+ `revision`).
grid_add_rowsAdd Wiki Grid RowsA
Add rows to a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: rows (required), grid_id (required), revision (required), position, +1 more. Returns: Row and column mutations answer with `results` (+ `revision`).
grid_copyCopy Wiki GridA
Copy a Yandex Wiki dynamic table to an existing target page. This starts an asynchronous operation and returns operation metadata.
Inputs: grid_id (required), slug, title, page_id. Returns: dry_run, operation, status_url
grid_createCreate Wiki GridA
Create a Yandex Wiki dynamic table resource on a page. This changes structured data.
Inputs: title (required), slug, page_id. Returns: id, page, rows, title, +7 more
grid_deleteDelete Wiki GridBDestructive
Delete a Yandex Wiki dynamic table. This changes structured data and is destructive.
Inputs: grid_id (required). Returns: Acknowledgment for `DELETE /grids/{id}`. The endpoint answers 204 No Content (d…
grid_delete_columnsDelete Wiki Grid ColumnsADestructive
Delete columns from a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: grid_id (required), revision (required), column_slugs (required). Returns: Row and column mutations answer with `results` (+ `revision`).
grid_delete_rowsDelete Wiki Grid RowsADestructive
Delete rows from a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: grid_id (required), row_ids (required), revision (required). Returns: Row and column mutations answer with `results` (+ `revision`).
grid_getGet Wiki GridARead-only
Get a Yandex Wiki dynamic table by grid ID.
Inputs: grid_id (required), sort, fields, filter, +3 more. Returns: id, page, rows, title, +7 more
grid_move_columnMove Wiki Grid ColumnAIdempotent
Move a column inside a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: grid_id (required), position (required), revision (required), column_slug (required). Returns: Row and column mutations answer with `results` (+ `revision`).
grid_move_rowMove Wiki Grid RowAIdempotent
Move a row inside a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: row_id (required), grid_id (required), revision (required), position, +1 more. Returns: Row and column mutations answer with `results` (+ `revision`).
grid_updateUpdate Wiki GridAIdempotent
Update a Yandex Wiki dynamic table. Fetch the grid first and pass the latest revision. This changes structured data.
Inputs: grid_id (required), revision (required), title, default_sort. Returns: id, page, rows, title, +7 more
grid_update_cellsUpdate Wiki Grid CellsAIdempotent
Update cells in a Yandex Wiki dynamic table. This changes structured data. Each cell patch must include row_id, value, and exactly one of column_id or column_slug.
Inputs: cells (required), grid_id (required). Returns: `POST /grids/{id}/cells` answers with `cells`, not `results`. Its own model rat…
page_add_commentAdd Page CommentB
Add a comment to a Yandex Wiki page.
Inputs: body (required), slug, page_id, parent_id, +1 more. Returns: id, body, author, parent_id, +7 more
page_append_contentAppend Wiki ContentA
Append content to the top, bottom, or anchor of a Yandex Wiki page. Content is Markdown (YFM): plain Markdown renders as-is, but GitHub-specific extensions ('[!NOTE]' alerts, raw HTML) do not — see the wiki-mcp://yfm-cheatsheet resource for YFM equivalents.
Inputs: content (required), slug, anchor, page_id, +1 more. Returns: id, slug, owner, title, +10 more
page_cloneClone Wiki PageA
Copy a Yandex Wiki page to a new slug and return the copy's id and slug once the operation completes. Copies title and content only: child pages, comments, attachments, and edit history stay with the original, and the copy gets a new page id. Fails when the target slug is already occupied. The Wiki API has no true move/rename; to relocate a page, clone it and delete the original — re-uploading attachments and re-creating grids on the copy if they must follow.
Inputs: target (required), slug, title, page_id. Returns: The clone operation's result: where the copy landed. `POST /pages/{id}/clone` i…
page_createCreate Wiki PageA
Create a Yandex Wiki page. Content is Markdown (YFM): plain Markdown renders as-is, but GitHub-specific extensions ('[!NOTE]' alerts, raw HTML) do not — see the wiki-mcp://yfm-cheatsheet resource for YFM equivalents.
Inputs: slug (required), title (required), content (required). Returns: id, slug, owner, title, +10 more
page_deleteDelete Wiki PageADestructive
Delete a Yandex Wiki page and return a recovery token.
Inputs: slug, page_id. Returns: recovery_token
page_delete_attachmentDelete Page AttachmentADestructive
Delete an attachment from a Yandex Wiki page. File ids come from page_get_attachments. Does not touch page content — any file macro referencing the attachment stays behind, broken.
Inputs: file_id (required), slug, page_id. Returns: Acknowledgment for `DELETE /pages/{id}/attachments/{fid}`. The endpoint answers…
page_delete_commentDelete Page CommentADestructive
Delete a comment from a Yandex Wiki page and return the page's updated comment count. Comment ids come from page_get_comments.
Inputs: comment_id (required), slug, page_id. Returns: Acknowledgment for `DELETE /pages/{id}/comments/{cid}`. The endpoint answers 20…
page_download_attachmentDownload Page AttachmentA
Download a Yandex Wiki page attachment to a local file: the bytes stream to disk without a size cap and never enter the conversation — the counterpart to page_read_attachment, for getting the artifact itself (a PDF, an archive, a large export). Writes atomically; refuses to replace an existing file unless overwrite is true. File ids come from page_get_attachments.
Inputs: file_id (required), save_to (required), slug, page_id, +1 more. Returns: Acknowledgment for a download-to-disk: where the bytes landed. Built client-sid…
page_editEdit Wiki Page ContentA
Edit a Yandex Wiki page by exact-text replacements, without resending the whole page: reads the current content, applies the replacements in order, and writes the result back with a single update. Each old_text must match the stored YFM markup exactly (copy it from page_get, whitespace included) and occur exactly once unless replace_all is set — a missing or ambiguous match fails the whole call before anything is written. NOTE: the Wiki API has no page revisions, so the read-modify-write is not atomic; allow_merge (on by default) asks Wiki to merge a concurrent edit that landed in between rather than overwrite it. Do NOT blindly retry a call whose result you did not see: a replacement whose new_text contains its own old_text applies again on a repeat. Content is Markdown (YFM): plain Markdown renders as-is, but GitHub-specific extensions ('[!NOTE]' alerts, raw HTML) do not — see the wiki-mcp://yfm-cheatsheet resource for YFM equivalents.
Inputs: replacements (required), slug, page_id, is_silent, +1 more. Returns: Compact acknowledgment for page_edit — also tool-level, never from the wire. De…
page_getGet Wiki PageARead-only
Get a Yandex Wiki page by page_id or slug.
Inputs: slug, fields, page_id. Returns: id, slug, owner, title, +9 more
page_get_attachmentsGet Page AttachmentsBRead-only
Get attachments for a Yandex Wiki page.
Inputs: slug, cursor, page_id, fetch_all, +1 more. Returns: results, truncated, next_cursor, prev_cursor
page_get_commentsGet Page CommentsBRead-only
Get comments for a Yandex Wiki page.
Inputs: slug, cursor, page_id, fetch_all, +1 more. Returns: results, truncated, next_cursor, prev_cursor
page_get_descendantsGet Page DescendantsARead-only
Get the subtree of Yandex Wiki pages under a parent page. Returns descendants from ALL nesting levels as one flat list of {id, slug} items — slugs encode the hierarchy ('/x/y' is nested under '/x'), so the tree can be reconstructed without further calls. Combine with fetch_all=true to map a whole section at once; if the result comes back truncated=true, continue via next_cursor or narrow down by calling this tool on a subsection's slug. Pass from_root=true instead of page_id/slug to enumerate the WHOLE Wiki, top-level pages included — the way to inventory an organization when no starting slug is known. Prefer a section slug when you have one: a full wiki is routinely thousands of pages, so a root walk costs many requests and a large reply, and fetch_all stops at its ~500-item cap with truncated=true.
Inputs: slug, cursor, page_id, fetch_all, +3 more. Returns: results, truncated, next_cursor, prev_cursor
page_get_gridsGet Page GridsARead-only
Get dynamic tables attached to a Yandex Wiki page.
Inputs: slug, cursor, page_id, order_by, +3 more. Returns: results, truncated, next_cursor, prev_cursor
page_get_resourcesGet Page ResourcesBRead-only
Get resources linked to a Yandex Wiki page, including attachments and grids.
Inputs: slug, cursor, search, page_id, +5 more. Returns: results, truncated, next_cursor, prev_cursor
page_read_attachmentRead Page AttachmentARead-only
Read a Yandex Wiki page attachment's content into the conversation (nothing is saved anywhere): PNG/JPEG/GIF/WebP images arrive as a native image block — vision-capable clients render and see them — text files (SVG included, it is XML) as text, anything else base64-encoded. Meant for images and text attachments — diagrams, screenshots, configs, CSVs, logs. Refuses non-image content over 128 KiB and images over 2 MiB. Use page_download_attachment to save it locally, or fetch the attachment's download_url from page_get_attachments yourself. page_get_attachments is also where file ids come from.
Inputs: file_id (required), slug, page_id.
page_recoverRecover Wiki PageA
Recover a deleted Yandex Wiki page using a recovery token.
Inputs: recovery_token (required). Returns: id, slug, pages_count
page_searchSearch WikiARead-only
Full-text search across the entire Yandex Wiki. Returns results (pages and files) ranked by relevance, each with a title, slug, url, and a text excerpt in content. Two modes: by default one call returns the top limit (up to 50) results and that is the whole reachable set — the response cursors stay null. With highlight=true the search switches to a paginated mode: pages are hard-capped at 10 results no matter the limit, and cursor (the page number echoed back in next_cursor) walks up to ~100 results — deeper than the default mode reaches. The set is over when results comes back empty or next_cursor is null on a non-empty page; past the end next_cursor keeps incrementing over empty pages, so do not treat it alone as 'more exists'. Use this tool to DISCOVER pages, then call page_get with a result's slug to read full content. content is an excerpt of at most ~510 characters cut from wherever the match sits in the page — not the page and not a summary of it, with no guarantee the query terms are even inside it — so treat it as a relevance signal and read the page before answering from it. Wrap multi-word exact phrases in double quotes. All filters (slug_prefix, result_type, authors, dates) run in the search backend itself, before the result limit, so a filtered search does not lose matches to it. To enumerate a section (or the whole Wiki) rather than search it, use page_get_descendants.
Inputs: query (required), limit, cursor, authors, +5 more. Returns: results, next_cursor, prev_cursor
page_updateUpdate Wiki PageAIdempotent
Update an existing Yandex Wiki page: title, content, or a redirect to another page. Content replacement is full-page when content is provided. Content is Markdown (YFM): plain Markdown renders as-is, but GitHub-specific extensions ('[!NOTE]' alerts, raw HTML) do not — see the wiki-mcp://yfm-cheatsheet resource for YFM equivalents.
Inputs: slug, title, content, page_id, +4 more. Returns: id, slug, owner, title, +10 more
page_upload_attachmentUpload Page AttachmentA
Upload a local file to Yandex Wiki and attach it to a page.
Inputs: file_path (required), slug, page_id, append_markup, +1 more. Returns: page_id, attachments, appended_markup, appended_content
user_get_currentGet Current UserARead-only
Get the calling Yandex Wiki user: username, home_cluster (the caller's personal-section slug, e.g. 'users/' — where 'create it in my section' requests belong), and identity/org ids.
Inputs: no named parameters. Returns: org, identity, username, home_cluster
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 33 tools
Most tools target distinct resources or actions, and the detailed descriptions make choices clear. However, page_get_resources overlaps with page_get_attachments and page_get_grids, and grid_update vs grid_update_cells could be confused at first glance.
All tools follow a consistent resource-prefixed snake_case pattern (page_, grid_, user_) with clear verbs and optional objects. Even related mutations like grid_add_rows, grid_delete_rows, and grid_move_column are predictable.
At 33 tools, the surface is well beyond the 16-25 range and feels heavy for an agent to navigate. While the coverage is broad, several operations could likely be consolidated or grouped to reduce cognitive load.
The server covers the full page lifecycle, search and hierarchy navigation, comments, attachments, and dynamic tables with CRUD and row/column operations. The only gaps (e.g., move/rename) are explicitly acknowledged with documented workarounds, so agents are not left at dead ends.
Maintenance
Related MCP Connectors
Shared project wiki for AI agents: read and write pages, next actions, and activity logs over MCP.
Read-only MCP for the Eco game wiki: search, Markdown pages, and wiki_* lookups. No keys, no writes.
MCP-native open-source Notion alternative: read & write pages, databases and kanban boards.
Token-free MCP server for structured RevoGrid Core, Pro, and Enterprise knowledge retrieval.
Related MCP Servers
- AlicenseBqualityBmaintenanceA secure MCP server for interacting with MediaWiki instances, allowing users to search, read, create, and manage wiki content like pages, categories, and files. It supports both public and private wikis with comprehensive authentication for full read and write operations.19AGPL 3.0
- AlicenseAqualityAmaintenanceMCP server for MediaWiki wikis. Search, read, edit, and manage wiki content from AI assistants. Includes formatting, link checking, revision history, and markdown conversion.4324MIT
- AlicenseAqualityFmaintenanceEnables reading, creating, updating, and appending content to Yandex Wiki pages via MCP. Supports both read-write and read-only modes.785 PyPI9MIT
- AlicenseNot gradedqualityDmaintenanceMinimal MCP server for Yandex Wiki that enables reading, writing, searching, and managing wiki pages and attachments.2MIT