GitHub Stars MCP Server

Created By
ccbikaia year ago
A Cloudflare-powered MCP (Model Context Protocol) Server that allows you to search and query your GitHub starred repositories using natural language.
Overview

what is GitHub Stars MCP Server?

GitHub Stars MCP Server is a Cloudflare-powered Model Context Protocol (MCP) server that enables users to search and query their GitHub starred repositories using natural language.

how to use GitHub Stars MCP Server?

To use the GitHub Stars MCP Server, deploy it to Cloudflare Workers and interact with it using any MCP-compatible client by sending natural language queries to the provided API endpoint.

key features of GitHub Stars MCP Server?

  • Automatically fetches and processes GitHub starred repositories.
  • Scheduled weekly updates via GitHub Actions.
  • Stores repository metadata and README content.
  • Provides semantic search capabilities through Cloudflare AutoRAG.
  • Exposes a MCP-compatible API for integration with AI agents.

use cases of GitHub Stars MCP Server?

  1. Quickly finding specific starred repositories based on natural language queries.
  2. Integrating with AI agents for enhanced repository management.
  3. Keeping track of updates to starred repositories automatically.

FAQ from GitHub Stars MCP Server?

  • What is required to set up the GitHub Stars MCP Server?

You need Node.js, PNPM, a GitHub Personal Access Token, and a Cloudflare account.

  • How does the server update starred repositories?

The server uses GitHub Actions to automatically fetch and process starred repositories on a weekly basis.

  • Can I use this server for repositories that I don't own?

No, the server only processes repositories that you have starred on GitHub.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
ccbikai
Star
62
Language
JavaScript
License
-

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

2 days ago
Fomox402

3 days ago