@penqwin/mcp
The @penqwin/mcp server provides token-efficient, AST-based structural "skeletons" of a codebase to LLM agents, reducing token usage by 80–95% compared to sending raw source files.
get_repo_index: Retrieve a compact table of contents of the entire repository, listing all tracked source files and their top-level exported symbol names (~10–20 tokens per file). Always recommended as the first call.get_folder_skeleton: Fetch structural skeletons (exports, function signatures, type definitions, doc comments) for all source files under a specified folder prefix (~50 tokens per file) — ideal for exploring a module or feature area.get_file_skeleton: Retrieve the detailed AST skeleton of a single file, including all exports with signatures, imports, class members, and JSDoc comments — useful when deep detail on one file is needed.search_symbols: Search the entire repository's AST index for files that export a specific symbol (function, class, type, or interface) by name, returning the file path, language, kind, signature, and doc comment.get_repo_stats: Obtain aggregate statistics about the repository, including total file count and a breakdown by programming language, for a quick overview of the tech stack and codebase scale.
Click on "Install 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., "@@penqwin/mcpshow me the skeleton of src/main.ts"
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.
@penqwin/mcp
An AST-based Model Context Protocol (MCP) server that provides token-efficient codebase skeletons to LLM agents (like Cursor, Claude Desktop, and Antigravity).
Instead of sending full raw source code files to the LLM, this server exposes structural "skeletons" (imports, exports, signatures, and JSDoc comments) of files and directories. This reduces token context sizes by 80% to 95% during codebase exploration and navigation.
Features & Tools
The server registers 5 core tools with the MCP protocol:
Tool Name | Description |
| Returns a compact Table of Contents of the repository (all files + top-level exported names). ~10–20 tokens/file. |
| Retrieves structural skeletons for all files matching a directory/folder prefix. |
| Retrieves the detailed structural skeleton (signatures, types, methods, parameters, and JSDocs) of a single file. |
| Queries the AST index to find files that export a specific class, function, struct, or type. |
| Returns aggregate statistics of the repository, including file counts and language breakdown. |
Related MCP server: cctx-mcp
Configuration
The MCP server is configured entirely via environment variables.
Environment Variable | Description | Example |
| Machine-to-machine API key generated from the DB |
|
| The organization ID associated with the API key |
|
| The repository owner and name to target |
|
| The REST API gateway URL of the |
|
IDE Integrations
You can integrate this MCP server with your favorite IDE using either npx (highly recommended for end-users, as it doesn't require cloning/building) or by pointing to your local build.
1. Direct Integration (via npm/npx)
This is the easiest setup for users. The IDE will automatically fetch and run the latest version of the package.
Cursor
Go to Cursor Settings -> Features -> MCP, and click + Add New MCP Server:
Name:
penqwinType:
commandCommand:
npx -y @penqwin/mcpAdd the required environment variables under the env settings.
Antigravity / Gemini Code Assistant
Add this to your mcp_config.json:
{
"mcpServers": {
"penqwin": {
"command": "npx",
"args": ["-y", "@penqwin/mcp"],
"env": {
"PENQWIN_API_KEY": "your_api_key",
"PENQWIN_ORG_ID": "your_org_id",
"PENQWIN_REPO": "your_repo",
"PENQWIN_API_URL": "https://app.penqwin.com"
}
}
}
}Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"penqwin": {
"command": "npx",
"args": ["-y", "@penqwin/mcp"],
"env": {
"PENQWIN_API_KEY": "your_api_key",
"PENQWIN_ORG_ID": "your_org_id",
"PENQWIN_REPO": "your_repo",
"PENQWIN_API_URL": "https://app.penqwin.com"
}
}
}
}2. Local Source Integration
If you have cloned the repository locally and compiled it:
Cursor
Command:
node d:/Projects/EngDoc/eng-doc-mcp/dist/index.js(Use forward slashes for Windows paths)
Antigravity / Claude Desktop
Command:
nodeArgs:
["d:/Projects/EngDoc/eng-doc-mcp/dist/index.js"]
Learn more:
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Penqwin/penqwin-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server