What it does
The server lets an MCP-compatible client search Wikisource and read short, bounded extracts from public-domain texts. Results are limited to excerpts rather than full documents, which keeps responses compact when an assistant is working with source material.
It suits workflows where an AI assistant needs to look up a public-domain passage, quote or historical text and pull in only the relevant portion. Because Wikisource hosts texts that are out of copyright, it is a fit for research, citation checking and reading older literature.
The source does not describe the setup steps, runtime requirements or supported clients, so these are not covered here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.mrfentmen/wikisource-mcp
Search and read bounded extracts from public-domain texts on Wikisource.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it