Dev Research Assistant
Provides tools for interacting with the public GitHub API, including fetching and summarizing a repository's README, counting and listing recent open issues, and retrieving repository metadata such as stars, forks, main language, license, and description.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Dev Research Assistant (MCP Server)
A small, self-hosted MCP server that gives an AI assistant quick developer research tools: summarize a GitHub repo and its README, check what issues are open, and summarize pasted text. Built for the Amazon Developer Hackathon 2026, Alexa+ track, as a self-hosted MCP server an Alexa+ Agent Skill can connect to.
What it does
The server speaks the Model Context Protocol (spec 2025-11-25) over Streamable HTTP and exposes four tools:
Tool | What it returns |
| Fetches a public GitHub repo README and returns an extractive summary of it |
| Counts open issues of a repo (PRs excluded) and lists the most recent ones |
| Stars, forks, main language, license, description of a repo |
| Extractive summary of any text you pass in |
Example questions an agent can answer with these tools:
"What is the modelcontextprotocol/python-sdk repo about?"
"How many open issues does facebook/react have right now, and what are the newest ones?"
"Summarize this changelog for me."
Related MCP server: github-mcp-server
How it maps to the Alexa+ track
Alexa+ Agent Skills can call MCP servers to reach tools and live data. This
project is that server side: a standards-compliant MCP server, self-hosted,
running over Streamable HTTP. Any MCP client (an Alexa+ Agent Skill, or a
local client like the MCP Inspector) can connect to the /mcp endpoint,
list the tools, and call them. The tools hit the public GitHub API at
runtime, so answers are live data, not canned text.
Run it
Needs Python 3.10 or newer.
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
.venv/bin/python server.pyThe server binds 127.0.0.1:8000 and serves the MCP endpoint at
http://127.0.0.1:8000/mcp. Set HOST and PORT env vars to change the
bind address or port. Set GITHUB_TOKEN if you want a higher GitHub API
rate limit; it works without one for light use.
Quick test
With the server running, in another terminal:
curl -s -X POST http://127.0.0.1:8000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl-test","version":"1.0"}}}'Then tools/list and tools/call with the same headers. See VERIFY.md for
a recorded run with real output.
Layout
server.py- the whole server (official Python MCP SDK)requirements.txt- dependencies (mcp,httpx)VERIFY.md- recorded local verification runSUBMISSION.md- Devpost submission draft
License
MIT, see LICENSE. Copyright Benjamin Kincses.
This server cannot be deployed
Maintenance
Related MCP Connectors
GitHub Copilot MCP: code, repo, PR, workflow tools for AI assistants.
GitHub repo search, stats, language breakdown and comparison as agent tools.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to analyze GitHub repositories, including fetching repository details, searching, and retrieving README content.456 npm2ISC
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with GitHub issues, pull requests, and Actions workflows through MCP tools.-
- FlicenseCqualityDmaintenanceExposes GitHub repository data via MCP tools, a resource, and a prompt, enabling repo summaries, issue/PR listing, keyword search, and repo health review.4-
- FlicenseNot gradedqualityCmaintenanceEnables natural-language analysis of GitHub repositories by exposing repository metadata, source code retrieval, search, and file reading as MCP tools, with answers grounded in the actual repository content.-