search_wikipedia_pagesLABSCO SUMMARY
Section-level retrieval is what makes it cheap enough to use constantly.
Listing a page's sections and then fetching only the one that matters is the difference between a fact check costing a paragraph and costing an entire article — which decides whether verification happens on every claim or only when someone remembers to ask. The migration notes are worth reading before you wire it up: this has moved to the stateless 2026-07-28 spec, the session header and WebSocket transport are gone, and the stdio entry point was deleted, so it is HTTP-only now.
What it is
An MCP server that gives a model Wikipedia access shaped for verification rather than browsing. Five tools cover the path from a vague query to a specific passage, and a built-in prompt instructs a client to check claims proactively rather than waiting to be asked.
What you get
search_wikipedia_pages— searches articles on a topic and returns the top 5 results with the information needed to pick between themget_wikipedia_page_info— comprehensive detail for a page, including content, summary, hyperlinked words and categoriesget_wikipedia_page_summary— a quick summary with a customisable sentence lengthget_wikipedia_page_sections— the list of sections on a page, which is how you avoid pulling a very long article wholeget_wikipedia_page_sections_info— the content of specific sections, addressed by title or index- Multi-language queries on every tool through a language parameter, defaulting to
en - A
fact_checking_instructionsprompt that turns proactive verification on for the conversation
Requirements
No account and no key. Python 3.13 or higher with uv: clone, uv sync, then uv run python librarian_server.py, which starts on http://0.0.0.0:8000 with the MCP endpoint at /mcp. Register it with claude mcp add librarian -t http http://localhost:8000/mcp. Production runs behind gunicorn with the uvicorn worker class. Communication is Streamable HTTP only, against the MCP 2026-07-28 spec — the earlier WebSocket and /sse endpoints have been removed, so a client configured for those will not connect. The project is librarian (version 0.1.0).
Setup effort
Build from source — git clone https://github.com/mlziade/librarian.git
USE CASES
01
Checking a claim mid-conversation
Search for the article, pull the relevant section, and correct the statement against what the source says.
02
Making verification automatic
Turn on the fact-checking prompt so claims get verified proactively instead of only when you ask.
03
Getting oriented on an unfamiliar subject
Read the page summary at the length you want, then follow its categories and linked terms outward.
04
Reading one part of a very long article
List the sections first and fetch only the one you need, rather than pulling the whole page.
05
Checking a fact in another language
Run the same lookup against a different language edition, where coverage of a local topic is often better.
5 tools
Listed in project docs. Your client may show a different list.
get_wikipedia_page_infoget_wikipedia_page_summaryget_wikipedia_page_sectionsget_wikipedia_page_sections_infoBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- uv
- Python 3.13 or later
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/mlziade/librarian.git
cd librarian
uv sync
uv run python librarian_server.pyMCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add librarian -t http http://localhost:8000/mcpAny MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"librarian": {
"url": "http://localhost:8000/mcp"
}
}
}Start the server first (last step above). For a server you deployed elsewhere, use https://<your host>/mcp instead of localhost.
