Helps find beginner-friendly open source issues on GitHub, filtering out those already being worked on by checking linked PRs via GraphQL.
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., "@mcp-oss-onramp Find beginner-friendly open source issues for Python"
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.
AI Scout for truly available, beginner-friendly OSS issues.
Run directly via npx:
npx mcp-oss-onrampYou can also run the server with a token directly in your terminal:
MCP_OSS_ONRAMP_GITHUB_TOKEN="your_token_here" npx mcp-oss-onrampRelated MCP server: gitea-mcp
Add this to your AI agent's configuration:
{
"mcpServers": {
"oss-onramp": {
"command": "npx",
"args": ["-y", "mcp-oss-onramp"]
}
}
}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.
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).
MIT
Scout a GitHub repository to discover truly available, beginner-friendly issues. This tool uses GitHub GraphQL for high-precision PR cross-referencing.
IMPORTANT FOR AI AGENTS: To avoid rate limits and enable high-precision scouting, ensure the MCP_OSS_ONRAMP_GITHUB_TOKEN environment variable is set with a GitHub Personal Access Token. If unauthenticated, the tool fallbacks to a lower-precision REST mode.
| Name | Required | Description | Default |
|---|---|---|---|
| repository | Yes | Full repository name (e.g., 'owner/repo') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses fallback mode when unauthenticated and mentions high-precision mode, but does not detail rate limits, output format, or error handling. No annotations exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact paragraphs: purpose and method, then critical usage note. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, method, and authentication. Lacks detail on how 'truly available' issues are determined, which is minor given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter, repository, with a clear schema description. Description does not add semantics beyond the schema, so baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool scouts a GitHub repository for beginner-friendly issues, using GraphQL for PR cross-referencing. Verb and resource are specific and distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance on setting an environment variable for authentication and notes the fallback behavior without a token. No siblings to differentiate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is distinct and well-defined.
The single tool name 'scout_issues' follows a clear verb_noun pattern. Consistency is inherently maintained with one tool.
Having only one tool is too few for the apparent scope of an OSS onboarding server. It feels thin and limits functionality.
The server covers only scouting for issues, missing other essential operations like fetching issue details or interacting with issues. This leaves significant gaps for a comprehensive tool set.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
An MCP server that gives your AI access to the source code and docs of all public github repos
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ryotaro-tanaka/mcp-oss-onramp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
