mcpField
M
mcp-oss-onramp

mcp-oss-onramp

Local
github.com/ryotaro-tanakaVersion Control0Updated 23w ago
Repository

About mcp-oss-onramp

mcp-oss-onramp is an MCP server that helps contributors find available, beginner-friendly open-source issues. It uses GitHub GraphQL to check linked pull requests and summarizes issue descriptions for LLMs.

Key features

  1. 01Finds beginner-friendly issues without relying on labels
  2. 02Checks linked pull requests for active work
  3. 03Summarizes issue descriptions for LLMs

Use cases

  1. 01Finding an open-source issue for a first contribution
  2. 02Filtering out issues with linked pull requests
  3. 03Reviewing issue details in a concise form

MCP support

Exposes issue discovery capabilities to MCP clients. It can be launched with npx and configured with a GitHub token or authenticated GitHub CLI for higher precision.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "ryotaro-tanaka-mcp-oss-onramp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-oss-onramp"
      ]
    }
  }
}
Run commandnpx -y mcp-oss-onramp

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
npmmcp-oss-onramp0.1.3

Tools

1

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
repositorystringYesFull repository name (e.g., 'owner/repo')

Details

From the project README

mcp-oss-onramp

AI Scout for truly available, beginner-friendly OSS issues.

日本語版はこちら | Full Documentation

Quick Start

Run directly via npx:

npx mcp-oss-onramp
Direct Execution (CLI)

You can also run the server with a token directly in your terminal:

MCP_OSS_ONRAMP_GITHUB_TOKEN="your_token_here" npx mcp-oss-onramp

MCP Configuration

Add this to your AI agent's configuration:

{
  "mcpServers": {
    "oss-onramp": {
      "command": "npx",
      "args": ["-y", "mcp-oss-onramp"]
    }
  }
}

Features

  • True Availability: Checks linked PRs via GraphQL to filter out issues already being worked on.
  • AI-Optimized: Summarizes issue bodies for efficient LLM consumption.
  • High Precision: Targets beginner-friendly tasks even without explicit labels.

Prerequisites

  • GitHub Authentication (Recommended):
    • Set MCP_OSS_ONRAMP_GITHUB_TOKEN environment variable, OR
    • Install GitHub CLI (gh) and authenticate via gh auth login.
  • Node.js: Version 18 or higher.

Note: The server works without authentication but will be rate-limited and provide lower precision (no PR cross-referencing).

License

MIT

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.