Wikisource Mcp

io.github.mrfentmenPublished by GitHub account mrfentmenv1.0.0Updated Oct 24, 2026

Use this MCP server to searching and reading public-domain texts on Wikisource. Tools include...

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Lets an assistant search and read public-domain texts hosted on Wikisource through a local MCP server.

What you can do
The server exposes tools for searching Wikisource and reading public-domain texts from it, so an assistant can look up works and pull their content into a conversation. The registry description names searching and reading as its purpose; no individual tool names or parameters are listed in the available material.
When to use it
Worth adding when a task involves public-domain literature, historical documents, or other Wikisource-hosted texts and the assistant needs to find and read them directly rather than through manual browsing.
Requirements
Runs as a local process over stdio, installed from the npm package wikisource-mcp, so a Node.js runtime and npm are needed on the machine. It is desktop-only and not offered as a web executable. No authentication, environment variables, or headers are declared, but network access is implied by fetching Wikisource content.
Before you install
The description is very short and no README is available, so the exact tool set and behavior are not documented here. It reads public content from Wikisource, a third-party site, so queries and retrieved text leave the local machine. No credentials, payments, or write actions are declared.

Installation

In SourceWeft

  1. Open Wikisource Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

wikisource-mcp

Search and read bounded extracts from Wikisource, a useful source for public-domain texts, historical documents, speeches, translations, and primary-source research.

Tools

  • search_texts: search titles and snippets.
  • read_text: read a bounded plain-text extract from a named page.

Wikisource pages can have different rights and edition notes. A page being available on Wikisource does not automatically make every scan, translation, or transcription reusable everywhere. Check the page's rights information before publishing or redistributing text. The server is read-only, keyless, and does not crawl arbitrary websites.

Run

bash
npm installnpm run buildnode dist/index.js

Source: README.md at commit e405bbf

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 22, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.