What can you do with this server?

This MCP server provides secure access to any MediaWiki wiki for searching, reading, and—with authentication—editing content and metadata. * Search the wiki full-text and filter by namespace/limit. * Read page wikitext or parsed HTML by title. * List pages with prefix, namespace, and pagination filters. * Create, edit, delete, and move pages (write tools require authentication; deletion requires admin auth). * List categories and inspect category members or a page’s categories. * View recent changes with filters for namespace, type, tag, and timestamp. * Parse arbitrary wikitext into HTML. * Retrieve site configuration, version info, and namespaces. * Look up user details and list user contributions. * Get file/image metadata and list files with prefix or MIME-type filters.

Which integrations are available for this server?

Enables searching, reading, creating, and editing wiki pages, categories, and files on Wikipedia and other MediaWiki-based platforms.

How do I use mcp-mediawiki-crunchtools?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-mediawiki-crunchtools Find the 'DevOps' page and summarize the introduction." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

mcp-mediawiki-crunchtools

by crunchtools

Overview Schema Source Related Servers Discussions Admin

Python

Remote

mcp-mediawiki-crunchtools

Secure MCP server for MediaWiki wikis. Search, read, create, edit, and manage wiki pages, categories, files, and more. Works with any MediaWiki instance — public or private.

Installation

uvx (recommended)

uvx mcp-mediawiki-crunchtools

pip

pip install mcp-mediawiki-crunchtools
mcp-mediawiki-crunchtools

Container

podman run -e MEDIAWIKI_URL=https://en.wikipedia.org/w/ \
  quay.io/crunchtools/mcp-mediawiki

Related MCP server: requarks-wiki-mcp

Usage with Claude Code

Read-only (public wiki, no auth needed)

claude mcp add mcp-mediawiki-crunchtools \
  --env MEDIAWIKI_URL=https://en.wikipedia.org/w/ \
  -- uvx mcp-mediawiki-crunchtools

With authentication (for write operations)

claude mcp add mcp-mediawiki-crunchtools \
  --env MEDIAWIKI_URL=https://your-wiki.com/w/ \
  --env MEDIAWIKI_USERNAME=BotUser \
  --env MEDIAWIKI_PASSWORD=BotPassword \
  -- uvx mcp-mediawiki-crunchtools

HTTP transport (systemd / container)

podman run -d --name mcp-mediawiki \
  -p 127.0.0.1:8016:8016 \
  -e MEDIAWIKI_URL=https://your-wiki.com/w/ \
  quay.io/crunchtools/mcp-mediawiki \
  --transport streamable-http --host 0.0.0.0

Claude Code config:

{"type": "http", "url": "http://127.0.0.1:8016/mcp"}

Environment Variables

Variable	Required	Description
`MEDIAWIKI_URL`	Yes	Wiki base URL (e.g., `https://en.wikipedia.org/w/`)
`MEDIAWIKI_USERNAME`	No	Bot/user account for write operations
`MEDIAWIKI_PASSWORD`	No	Bot/user password
`MEDIAWIKI_HTTP_USER`	No	HTTP Basic Auth username (.htaccess)
`MEDIAWIKI_HTTP_PASS`	No	HTTP Basic Auth password
`MEDIAWIKI_ALLOW_HTTP`	No	`true` permits plain `http://` to a non-localhost wiki addressed by a private IP literal

Tools (19)

Category	Tool	Description
Pages	`search`	Full-text search across wiki
Pages	`get_page`	Get page wikitext content
Pages	`get_page_html`	Parse page to HTML
Pages	`list_pages`	List pages with prefix filter
Pages	`create_page`	Create a new page
Pages	`edit_page`	Edit an existing page
Pages	`delete_page`	Delete a page
Pages	`move_page`	Move/rename a page
Categories	`list_categories`	List all categories
Categories	`get_category_members`	Get pages in a category
Categories	`get_page_categories`	Get categories for a page
Recent Changes	`list_recent_changes`	List recent edits
Parsing	`parse_wikitext`	Parse raw wikitext to HTML
Site Info	`get_site_info`	Get wiki config and version
Site Info	`list_namespaces`	List wiki namespaces
Users	`get_user_info`	Get user details
Users	`list_user_contributions`	List user edits
Files	`get_file_info`	Get file/image metadata
Files	`list_files`	List files on the wiki

Development

# Install dev dependencies
uv sync --all-extras

# Quality gates
uv run ruff check src tests
uv run mypy src
uv run pytest -v
gourmand --full .
podman build -f Containerfile .

License

AGPL-3.0-or-later

Available Tools

19 tools

create_page_toolCreate Page ToolC

Create a new wiki page. Requires authentication.

Inputs: title (required), content (required), summary. Returns: object

delete_page_toolDelete Page ToolB

Delete a wiki page. Requires admin authentication.

Inputs: title (required), reason. Returns: object

edit_page_toolEdit Page ToolC

Edit an existing wiki page. Requires authentication.

Inputs: title (required), content (required), minor, summary. Returns: object

get_category_members_toolGet Category Members ToolC

Read-only

Get pages in a category.

Inputs: category (required), limit, member_type, continue_from. Returns: object

get_file_info_toolGet File Info ToolB

Read-only

Get file/image metadata from the wiki.

Inputs: filename (required). Returns: object

get_page_categories_toolGet Page Categories ToolB

Read-only

Get categories that a page belongs to.

Inputs: title (required), limit, show_hidden. Returns: object

get_page_html_toolGet Page Html ToolC

Read-only

Parse a wiki page to HTML.

Inputs: title (required). Returns: object

get_page_toolGet Page ToolB

Read-only

Get page wikitext content by title.

Inputs: title (required). Returns: object

get_site_info_toolGet Site Info ToolA

Read-only

Get wiki configuration and version info.

Inputs: no named parameters. Returns: object

get_user_info_toolGet User Info ToolC

Read-only

Get user details from the wiki.

Inputs: username (required). Returns: object

list_categories_toolList Categories ToolC

Read-only

List all categories on the wiki.

Inputs: limit, prefix, from_name. Returns: object

list_files_toolList Files ToolC

Read-only

List files on the wiki.

Inputs: limit, prefix, from_name, mime_type. Returns: object

list_namespaces_toolList Namespaces ToolA

Read-only

List all namespaces on the wiki.

Inputs: no named parameters. Returns: object

list_pages_toolList Pages ToolB

Read-only

List wiki pages with optional prefix filter.

Inputs: limit, prefix, namespace, from_title. Returns: object

list_recent_changes_toolList Recent Changes ToolC

Read-only

List recent edits on the wiki.

Inputs: tag, limit, namespace, change_type, +1 more. Returns: object

list_user_contributions_toolList User Contributions ToolC

Read-only

List edits by a user.

Inputs: username (required), limit, namespace, from_timestamp. Returns: object

move_page_toolMove Page ToolC

Move (rename) a wiki page. Requires authentication.

Inputs: to_title (required), from_title (required), reason, move_talk, +1 more. Returns: object

parse_wikitext_toolParse Wikitext ToolC

Read-only

Parse raw wikitext to HTML.

Inputs: wikitext (required), title. Returns: object

search_toolSearch ToolC

Read-only

Full-text search across the wiki.

Inputs: query (required), limit, namespace. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.2/5.0

Scored 2026-11-01 14:10 across 19 tools

Disambiguation4/5

Each tool targets a distinct resource+action pair (pages, categories, files, users, search, namespaces), so misselection is unlikely. The only fuzzy boundary is between get_page_html_tool (renders a page by title) and parse_wikitext_tool (renders raw wikitext), which sound similar until you read the input difference. get_page_tool vs get_page_html_tool is also a subtle distinction but handled by descriptions.

Naming Consistency5/5

Every tool follows the same verb_noun_tool pattern (list_, get_, create_, edit_, delete_, move_, parse_) in consistent snake_case with a uniform _tool suffix. Pluralization for list operations (list_pages, list_files, list_categories) is applied predictably. No mixed conventions.

Tool Count4/5

19 tools is slightly heavy but each one maps to a meaningful MediaWiki operation across pages, categories, files, users, and search. There is very little redundancy — nothing overlaps enough to be pruned. It sits near the upper edge of comfortable scoping for a single wiki API.

Completeness3/5

Page lifecycle is fully covered (list/get/create/edit/delete/move), but revision history and diffs are entirely absent, which is a core wiki workflow. Files and categories are read-only — no upload/delete file, no add/remove category from a page — leaving agents to dead-end on those write paths. User tooling is also read-only.

Maintenance

ActivityActive

ResponsivenessLimited data

Resources

Related MCP Connectors

EcoCarbonWikiA
dev.carbonitex.ecogame
Read-only MCP for the Eco game wiki: search, Markdown pages, and wiki_* lookups. No keys, no writes.
Documentation Access Search Games & Gamification
111
https://ecogame.carbonitex.dev/mcp
mcpA
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
https://llmse.ai/mcp
Flowdex
dk.flowdex
Read and write your team's shared, AI-readable wiki from any MCP client.
Note Taking Documentation Access Workplace & Productivity
1
https://mcp.flowdex.dk/mcp
Shard Connector for Obsidian
com.shardconnector
Hosted MCP server for Obsidian Sync vaults: read, search, edit notes. Not affiliated with Obsidian.
Note Taking Knowledge & Memory Search
1
https://mcp.shardconnector.com/mcp

Related MCP Servers

mediawiki-mcp-server
Content Management Systems Search Developer Tools
olgasafonova
A
license
A
quality
A
maintenance
MCP server for MediaWiki wikis. Search, read, edit, and manage wiki content from AI assistants. Includes formatting, link checking, revision history, and markdown conversion.
Updated 3 days ago (2026-11-09 21:39 UTC)
43
23
MIT
requarks-wiki-mcp
Content Management Systems Knowledge & Memory RAG Systems
uyu423
A
license
A
quality
D
maintenance
An MCP server that enables AI agents to interact with Wiki.js as a knowledge base through a comprehensive set of 29 tools for content retrieval and management. It supports full-text search, page versioning, and asset browsing with optional write operations secured by safety gates.
Updated 9 months ago (2026-02-16 13:54 UTC)
29
66 npm
8
MIT
WikiJS MCP Server
Content Management Systems Knowledge & Memory Search
vnikhilbuddhavarapu
A
license
Not graded
quality
D
maintenance
An MCP server that enables full management of WikiJS instances, supporting operations like page creation, searching, and updating. It also provides tools for knowledge graph exploration, content summarization, and retrieval of wiki statistics.
Updated 8 months ago (2026-03-23 15:23 UTC)
19 npm
MIT
mediawiki-mcp
Content Management Systems Documentation Access Search
ttpears
A
license
A
quality
B
maintenance
An MCP server for MediaWiki instances with multi-wiki support, providing full read/write access via REST and Action APIs across multiple named wikis.
Updated 16 hours ago (2026-11-12 16:45 UTC)
21
98 npm
3
MIT

mcp-mediawiki-crunchtools

Installation

uvx (recommended)

pip

Container

Usage with Claude Code

Read-only (public wiki, no auth needed)

With authentication (for write operations)

HTTP transport (systemd / container)

Environment Variables

Tools (19)

Development

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

mediawiki-mcp-server

requarks-wiki-mcp

WikiJS MCP Server

mediawiki-mcp