What it does
encyport reads English Wikipedia through its public APIs. Given a phrase, it finds matching articles with a text snippet, word count and last-revision timestamp. Given a title, it returns the full plain-text article, only the lead summary, the section outline, the pages the article links to, or the recorded coordinates. Titles follow redirects, so a common name or an old title resolves to the current article.
It suits agents or scripts that need Wikipedia content without scraping pages. The six MCP tools are search_wikipedia, get_article, get_summary, get_sections, get_links and get_coordinates. No sign-up or API key is needed.
The container image starts the MCP server by default, and passing arguments runs it as a CLI that prints JSON. The mcp subcommand starts a stdio MCP server, which must be added to an MCP client's configuration. CLI exit codes are 0 on success, 1 when a lookup fails, and 2 for usage errors. Tests use hand-written payloads and do not touch the network.
Limitations and requirements
Queries en.wikipedia.org only. A title that does not resolve to a page is reported as an error rather than empty content, and a failed lookup returns exit code 1 in CLI mode. Running the MCP server requires configuring it in an MCP client.
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.CloudCorpRecords/encyport
Search Wikipedia and read articles, summaries, sections, links, and coordinates.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it