LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Toolofficial publisher

Outils du GitHub MCP

Tool : A precise action the AI can call · requires mcp:github

Issues, pull requests, code and security alerts, in read and write mode.

The best free option for acting on a repository; limit the token scope.

Docs
Overall score
7.3 /10
Security: one caveat, see the card
Utility
8.0
Reliability
6.0
Security
One caveat
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Managing a GitHub repository from an AI assistant usually means juggling multiple interfaces: the web UI, the command line, and automation scripts. GitHub's official MCP server solves this by exposing platform features directly to your AI tool via the MCP protocol.

In practice, the tool connects to the GitHub API using a personal access token (PAT) or OAuth, then makes a set of actions available to the AI agent: reading and writing issues, managing pull requests, browsing code, monitoring GitHub Actions workflows, checking Dependabot alerts, and reviewing security analysis results. All of this can be controlled in natural language from your MCP host of choice.

It is aimed at developers who want to automate repetitive repository tasks, triage bugs, track CI/CD pipelines, or analyze code security without leaving their usual working environment (VS Code, Cursor, Claude Desktop, JetBrains, etc.).

It is not suited for people without a GitHub account or repository to manage, nor for those looking for a tool with no technical setup: installation requires Docker or Go, and managing an access token.

What it offers

  • ·Issue read and write: create, edit, comment on, and close issues in natural language.
  • ·Pull request management: open, review, merge, and track PR status directly from the AI agent.
  • ·Code navigation: browse files, analyze commits, and understand repository structure.
  • ·GitHub Actions workflow monitoring: view runs, analyze build failures, and track CI/CD pipelines.
  • ·Security alerts: access Dependabot results and code security analysis findings.
  • ·Notifications and discussions management: access team discussions and manage GitHub notifications.
  • ·GitHub Enterprise support: compatible with GitHub Enterprise Cloud (ghe.com) and GitHub Enterprise Server via host configuration.
  • ·Insiders mode: early access to new experimental features via a dedicated URL or header.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
mcp
Host
mcp:github
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Capabilities
readswritesexecutesnetwork
Your data
Data with third parties
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 April 2025

How to install Outils du GitHub MCP

1. Install Docker on your machine and make sure it is running. 2. Create a GitHub personal access token (PAT) with only the permissions you actually need. 3. Store the token in an environment variable: export GITHUB_PERSONAL_ACCESS_TOKEN=your_token 4. Add the MCP server configuration to your host's config file (VS Code, Cursor, Claude Desktop, etc.), referencing the environment variable rather than pasting the token directly. 5. If your host supports remote MCP servers, you can use the URL https://api.githubcopilot.com/mcp/ directly with OAuth, with no Docker or manual token management required. 6. Make sure the config file is not tracked by version control (add it to .gitignore if needed) to prevent token leaks.
docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server

Official documentation ↗

In the same category

Whole category Code →