agentmods.dev

github

github is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from metagit-ai/metagit-cli. Its token cost is not measured, scanned A, original, MIT.

A connection to GitHub, a service for hosting Git repositories and collaborating on code, configured to run in a Docker container. It requires a GitHub personal access token to connect.

In plain words
What is it for?
Use it as the configured GitHub connection for tasks that require the repository service, once a personal access token is supplied.
Why use it?
It provides a configured way for an agent to access GitHub through an external tool instead of requiring a separate local setup. The supplied details do not specify which GitHub actions are available.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 3repo yesterday A scan tokens not measured original MIT

Good fit Use it as the configured GitHub connection for tasks that require the repository service, once a personal access token is supplied.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/metagit-ai/metagit-cli/github
View source ↗ metagit-ai/metagit-cli metagit-ai.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/metagit-ai/metagit-cli

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for github

README.md
[![agentmods](https://agentmods.dev/badge/mcp/metagit-ai/metagit-cli/github/github.svg)](https://agentmods.dev/mcp/metagit-ai/metagit-cli/github)
Your own site
<a href="https://agentmods.dev/mcp/metagit-ai/metagit-cli/github"><img src="https://agentmods.dev/badge/mcp/metagit-ai/metagit-cli/github/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for github

Your own site · 80×15
<a href="https://agentmods.dev/mcp/metagit-ai/metagit-cli/github"><img src="https://agentmods.dev/badge/mcp/metagit-ai/metagit-cli/github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

github scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.vscode/mcp.json · 16 lines

What it actually says

{
  "github": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "-e",
      "GITHUB_PERSONAL_ACCESS_TOKEN",
      "ghcr.io/github/github-mcp-server"
    ],
    "env": {
      "GITHUB_PERSONAL_ACCESS_TOKEN": "${input:github_token}"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 16 lines scan A d83cad0639c7

Subscribe to this mod's changes

github is an MCP server published in the GitHub repository metagit-ai/metagit-cli (3 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Git and workflowProject ManagementPythonagent-skillsclimcp-server
Related

Other mcp servers, from other repositories

cc-audit

MCP server "cc-audit" as configured in ryo-ebata/cc-audit. Launched with ./target/release/cc-audit serve.

ryo-ebata/cc-audit · not measured

rrt

MCP server "rrt" as configured in Anselmoo/mcp-zen-of-languages. Runs locally from the repo-release-tools[mcp] Python package.

Anselmoo/mcp-zen-of-languages · not measured

analyzer

MCP server for Python, JavaScript, and TypeScript code analysis with Ruff, ty, Vulture, and Biome. Runs locally from the mcp-server-analyzer Python package.

Anselmoo/mcp-zen-of-languages · not measured

linebreak-gate

LineBreak security gate at the git/CI boundary: dependency CVE scan + AI SAST, human-approved overrides, git-native audit records. Runs locally from the linebreak-gate Python package.

Baktun-Studio/linebreak-gate · not measured

memi

Memi is the design layer for agentic AI. Runs locally from the @memi-design/cli npm package.

memi-design/memi · not measured

p4mcp-server

MCP server "p4mcp-server" as configured in perforce/p4mcp-server. Runs in Docker (ghcr.io/perforce/p4mcp-server:2026.3.2996147). Needs 4 environment variables to run.

perforce/p4mcp-server · not measured