GPUI Kit MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GPUI Kit MCP show me the Column Types section in the data-table docs"
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.
gpui-kit-mcp
English | 简体中文
MCP (Model Context Protocol) server for the GPUI Kit documentation.
It bundles the full GPUI Kit documentation into a local corpus so AI clients such as Claude Code, Cursor and Trae can search and read the guides, gpui-base primitives, gpui-component widgets and gpui-shell docs without network access.
Features
Complete offline corpus: all 376 pages listed in
https://gpui-kit.com/llms.txt(English and Simplified Chinese)Bilingual search: word-based indexing for English, bigram indexing for Chinese, with automatic language preference based on the query
Section-level reads: fetch only the content under one heading on long pages to keep context small
Zero configuration: standard stdio MCP server, one
npxcommand to connect
Related MCP server: docs-mcp
Quick start
npx -y @dishuyl/gpui-kit-mcp --helpMCP client configuration
For Claude Desktop, Cursor, Trae and other MCP clients:
{
"mcpServers": {
"gpui-kit": {
"command": "npx",
"args": ["-y", "@dishuyl/gpui-kit-mcp"]
}
}
}On Windows, if the client cannot launch npx directly, use:
{
"mcpServers": {
"gpui-kit": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@dishuyl/gpui-kit-mcp"]
}
}
}Tools
Tool | Description | Main parameters |
| Full-text search with path, description and matching snippet |
|
| Read a whole page or a single section |
|
| Browse pages filtered by language, section or keyword |
|
| Return the collected |
|
lang accepts all (default, auto-prefers the query language), en or zh. section accepts docs, base, component, shell or a path prefix such as base/primitives.
Examples
Use search_docs to search for "data table virtual scroll"
Use get_doc to read the "Column Types" section of /component/data-table.md
Use get_docs_index to list the shell docs in zhDevelopment
git clone https://github.com/SinJayXie/gpui-kit-mcp.git
cd gpui-kit-mcp
npm install
npm run collect # re-download the gpui-kit.com docs
npm run build # compile to dist/
node dist/index.jsnpm run collect writes:
data/llms.txt: snapshot of the documentation indexdata/docs.json: all page contentsdata/meta.json: collection time, page count and failures
License
Code is released under the MIT license.
The bundled documentation comes from gpui-kit.com. Its prose and illustrations are licensed under CC BY 4.0, and code examples under Apache-2.0. Keep the GPUI Kit attribution and source link when redistributing.
Available Tools
4 toolsget_docRead a GPUI Kit doc pageARead-only
Read a GPUI Kit documentation page as Markdown. Accepts a path from search_docs (for example /component/button.md) or a page title/slug such as "Button". Use section to return only one heading's content on long pages. When a title matches several pages, the available paths are returned so you can choose.
Inputs: path (required), lang, section, maxChars.
get_docs_indexGet GPUI Kit llms.txt indexARead-only
Return the collected https://gpui-kit.com/llms.txt index: every documentation page with its path and one-line description. Filter by language or section to keep the response small.
Inputs: lang, section.
list_docsList GPUI Kit docsARead-only
List GPUI Kit documentation pages, optionally filtered by language, section, or a keyword matched against title and description. Useful for browsing what is available before reading a page.
Inputs: lang, limit, query, section.
search_docsSearch GPUI Kit docsARead-only
Full-text search across all GPUI Kit documentation (guides, gpui-base primitives, components, gpui-shell). Returns matching pages with title, path, description and a content snippet. Start here, then call get_doc with the returned path.
Inputs: query (required), lang, limit, section.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
get_doc is clearly distinct as the read tool, but search_docs, list_docs, and get_docs_index all return lists of documentation pages with paths and descriptions. The descriptions hint at differences (full-text search vs. keyword browse vs. llms.txt index), but an agent can easily pick the wrong one, especially list_docs vs. get_docs_index which both filter by language and section.
All names are snake_case verb_noun (search_docs, get_doc, list_docs, get_docs_index), which is predictable. Minor deviation: get_doc uses a singular object while get_docs_index embeds a plural compound noun, so the pattern isn't perfectly uniform.
Four tools is a sensible, well-scoped surface for a documentation server: one search, one read, and two browsing helpers. The only quibble is that the two listing tools partly overlap, so the set could arguably be three.
The core docs workflow is covered end to end: discover (search/list/index), then read a page with section-level granularity and path disambiguation. No obvious dead ends, though there is no tool for retrieving runnable examples or API signatures beyond what the Markdown pages contain.
Maintenance
Related MCP Connectors
Versioned documentation registry and semantic search for AI tools and coding assistants.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
MCP server for querying Forkast documentation
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Related MCP Servers
- AlicenseAqualityBmaintenanceIndexes your project's markdown documentation and exposes it to AI agents via local hybrid search (lexical + semantic) with progressive disclosure tools.389 npm5MIT
- FlicenseNot gradedqualityCmaintenanceLocal documentation search server for AI models using hybrid retrieval (phrase, keyword, vector). Provides MCP tools to search and fetch documentation from bundled or custom doc sets without any external API keys.-
- AlicenseNot gradedqualityBmaintenanceTurns any documentation website into a standalone, dependency-free MCP server with local Chinese-first CJK search, enabling AI agents to read and search docs offline without API keys.5 npm1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides AI assistants offline fuzzy search, precise section retrieval, and section listing over bundled mobile-development documentation, enabling natural-language lookups of components, hooks, guides, and best practices.MIT