mcpField
P
Penqwin

Penqwin

Local
github.com/sarinmsariAI & Agents3Updated 16w ago
Repository

About Penqwin

Penqwin is an AST-based MCP server for coding agents that need to explore a repository without loading entire source files. It provides compact code skeletons containing structure and documentation, along with repository and symbol search tools.

Key features

  1. 01Repository index with exported names
  2. 02Folder and file code skeletons
  3. 03AST-based symbol search
  4. 04Repository statistics and language breakdown

Use cases

  1. 01Map a repository before editing
  2. 02Inspect file signatures without full source
  3. 03Locate files exporting a symbol

MCP support

Registers five MCP tools for repository indexing, file and folder skeletons, symbol search, and repository statistics. It connects to the Penqwin backend using configured environment variables.

#context-router#reduce-llm-token#cut-llm-cost

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "penqwin": {
      "command": "npx",
      "args": [
        "-y",
        "@penqwin/mcp"
      ],
      "env": {
        "PENQWIN_API_KEY": "<PENQWIN_API_KEY>",
        "PENQWIN_ORG_ID": "<PENQWIN_ORG_ID>",
        "PENQWIN_REPO": "<PENQWIN_REPO>",
        "PENQWIN_API_URL": "<PENQWIN_API_URL>"
      }
    }
  }
}
Run commandnpx -y @penqwin/mcp
Environment variables to set
PENQWIN_API_KEYSecret
PENQWIN_ORG_ID
PENQWIN_REPO
PENQWIN_API_URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@penqwin/mcp

Tools

5

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
include_statsbooleanNoIf true, also returns language breakdown and total file count.

Details

From the project README

@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 NameDescription
get_repo_indexReturns a compact Table of Contents of the repository (all files + top-level exported names). ~10–20 tokens/file.
get_folder_skeletonRetrieves structural skeletons for all files matching a directory/folder prefix.
get_file_skeletonRetrieves the detailed structural skeleton (signatures, types, methods, parameters, and JSDocs) of a single file.
search_symbolsQueries the AST index to find files that export a specific class, function, struct, or type.
get_repo_statsReturns aggregate statistics of the repository, including file counts and language breakdown.

Configuration

The MCP server is configured entirely via environment variables.

Environment VariableDescriptionExample
PENQWIN_API_KEYMachine-to-machine API key generated from the DBed_live_0e21cf14...
PENQWIN_ORG_IDThe organization ID associated with the API key0db9f7b5-7206-...
PENQWIN_REPOThe repository owner and name to target<org_name>/<repo_name>
PENQWIN_API_URLThe REST API gateway URL of the penqwin backendhttp://app.penqwin.com

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: penqwin
  • Type: command
  • Command: npx -y @penqwin/mcp
  • Add 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: node
  • Args: ["d:/Projects/EngDoc/eng-doc-mcp/dist/index.js"]

Learn more:

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.