GitHub MCP. Manage repos, issues, and code search from your agent.

Q: How do I search for code within a specific organization?

Use the 'searchgithubcode' tool and include the organization qualifier in your query, for example: 'org:vinkius my-term'.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Just plug in your AI agents and start using Vinkius.

GitHub MCP Server manages repositories, tracks issues, and searches code via AI agents. Connect your GitHub account to your preferred AI client and automate core developer workflows—listing repos, getting file contents, or creating new issues—all from a natural conversation.

Manage your entire software development lifecycle without leaving your chat window.

What your AI agents can do

Add issue comment

Supports markdown formatting.

Add a comment to an issue or PR

Create new issue

Opens a new issue in a specific repository.

Create pull request

Requires the head branch (your changes) and base branch (merge target).

Create a pull request

+ 15 more capabilities included

View repository details and lists

List all repos for a user or organization, or fetch the specific metadata for a single project.

Manage issues and pull requests

List open issues or pull requests for a repo, or programmatically create new issues from your chat.

Search and read code files

Fetch the full text contents of any file or directory, or run targeted searches across the entire codebase.

Track project growth and ownership

List all forks and contributors to a repository to gauge community interest and ownership.

Identify user context and permissions

Retrieve the authenticated user's profile details to confirm permissions and project context.

Ask AI about this MCP

Ask ChatGPT

Ask Claude

Ask Perplexity

Supported MCP Clients

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

Free for Subscribers

Waiting for input…

AI Agent

GitHub MCP Server: 12 Tools for Code Management

These tools let your AI agent read, write, and search all core components of your GitHub environment, from issues to code files.

add019e9a8e

add issue comment

Supports markdown formatting. Add a comment to an issue or PR

create019d75a5

create new issue

Opens a new issue in a specific repository.

create019e9a8e

create pull request

Requires the head branch (your changes) and base branch (merge target). Create a pull request

get019d75a5

get file contents

Reads the full text content of a specified file.

get019e9a8e

get issue details

Get a specific issue by number

get019d75a5

get my github profile

Retrieves the authenticated user's GitHub profile information.

get019d75a5

get repository details

Fetches detailed metadata and configuration for a given repository.

list019e9a8e

list branches

List repository branches

list019e9a8e

list commits

Optionally filter by branch name or SHA. List recent commits

list019d75a5

list org repositories

Lists all repositories owned by a specific organization.

list019d75a5

list pull requests

Lists all open and closed pull requests for a given repository.

list019e9a8e

list releases

List repository releases

list019d75a5

list repo issues

Lists all open issues for a specific repository.

list019e9a8e

list stargazers

Useful for popularity tracking. List repository stargazers

list019d75a5

list user repositories

Lists all repositories owned by the authenticated user.

search019d75a5

search github code

Executes a powerful search for specific code snippets across the codebase.

search019d75a5

search github repositories

Searches and lists repositories by name or description across GitHub.

verify019d75a5

verify api connection

Checks the connection status and validity of the GitHub API token.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with GitHub, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 4,700+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

What you can do with this MCP connector

GitHub MCP Server gives your AI client direct access to core GitHub functions. You'll use this server to manage repos, track issues, and search code right from your chat. You connect your GitHub account to your preferred AI client and automate core developer workflows—listing repos, getting file contents, or creating new issues—all without leaving your chat window.

It's all about getting stuff done, fast.

View Repository Details and Lists
You can list all repos owned by your user or a specific organization (list_user_repositories, list_org_repositories), or grab the specific metadata for any single project (get_repository_details). You can also see all forks associated with a project (list_repository_forks).

Manage Issues and Pull Requests
You can list all open issues for a repo (list_repo_issues) or list all pull requests, open or closed, for a repo (list_pull_requests). You can also open a new issue in a specific repository directly from your chat (create_new_issue).

Search and Read Code Files
You can run a powerful search for specific code snippets across the entire codebase using search_github_code. You can also search and list repositories by name or description across all of GitHub (search_github_repositories). Need to see what's in a file? Use get_file_contents to read the full text of any specified file.

Finally, you can confirm your identity and permissions by retrieving your profile info (get_my_github_profile) or checking the API connection status (verify_api_connection).

How GitHub MCP Works

1 Subscribe to the GitHub MCP Server via Vinkius and enter your Personal Access Token.
2 Your AI client sends a request (e.g., 'List all PRs for vinkius/vurb-core').
3 The server executes the required GitHub API calls and returns structured data directly to your AI client.

The bottom line is, your AI client talks to GitHub, and you get the answer without opening a browser.

Who Is GitHub MCP For?

This is for the developer, the tech lead, and the project manager who's tired of context switching. You're the one who wakes up needing to know the status of a pull request or audit a repository's file structure without manually clicking through dashboards. You need visibility into the codebase and the project's operational status, fast.

Software Developer

Uses the agent to run get_file_contents to understand a new module's structure, or uses search_github_code to find a specific function signature across multiple repos.

DevOps Engineer

Uses the agent to run list_org_repositories and get_repository_details to audit project metadata and ensure compliance across the fleet.

Technical Project Manager

Uses the agent to run list_repo_issues and list_pull_requests to get a real-time overview of project bottlenecks and community engagement status.

What Changes When You Connect

List all repos for an organization using list_org_repositories to immediately get a full inventory count, eliminating manual browsing through GitHub web interfaces.
When you need to audit a project, get_repository_details provides immediate metadata—like last updated date and branch count—without needing to navigate the repo settings page.
Instead of reading dozens of comments to find a bug, search_github_code lets you pinpoint a specific function signature or class definition across the entire codebase.
Tracking project health is easy: list_repo_issues gives you a live count of open bugs, while list_pull_requests shows exactly which PRs are stuck waiting for review.
You can initiate action instantly. Use create_new_issue to file a bug or request a feature without ever leaving your chat window.
Audit project scope by calling list_repository_forks to see how many times the codebase has been adopted by the community.

Real-World Use Cases

The bug report is buried deep in the code.

A developer needs to find where a specific error handling function is used. They run search_github_code with the error signature. The agent returns all relevant file paths and snippets, letting them jump straight to the source code without searching through dozens of READMEs or file trees.

The team needs a full list of all services.

A DevOps engineer needs to audit every service under the 'AcmeCorp' organization. They run list_org_repositories, which returns a clean, structured list of all 50 repositories, including metadata, allowing them to build an inventory quickly.

A new feature needs to be tracked.

A PM decides a feature is needed. They use the agent to run create_new_issue with a detailed description and labels. The issue instantly appears in the target repository, and they get a link, all without opening the GitHub website.

Checking the status of a big PR.

A developer asks the agent to list_pull_requests for a key repo. The agent checks the status, noting if it's approved, if conflicts exist, and who the last reviewer was. This replaces manually checking the PR dashboard.

The Tradeoffs

Manually checking repo status

Going to the GitHub website, navigating to the repository, clicking the 'Issues' tab, then scrolling through the list until the desired issue is found.

→ Ask your agent to list_repo_issues for the specific repo. It pulls the data instantly, providing a structured list of the latest issues and their statuses.

Searching code via browser UI

Trying to use the GitHub search bar for complex code patterns. The UI search is good for keywords, but it struggles to isolate specific code blocks or file contents accurately.

→ Use the dedicated search_github_code tool. It runs a precise query across the database, returning the exact code snippets you need, not just matching filenames.

Trying to list all repos via API playground

Manually calling multiple REST endpoints (e.g., /orgs/{org}/repos, /users/{user}/repos) and stitching the results together in a spreadsheet.

→ Use the list_org_repositories or list_user_repositories tools. They handle the necessary API calls internally and give you a clean, aggregated list in one go.

When It Fits, When It Doesn't

Use this MCP Server if your primary workflow involves reading, listing, or searching structured development data. You need to automate the repetitive act of switching between GitHub tabs (Issues, PRs, Code). Don't use it if you only need to view a single, non-critical piece of information (e.g., checking a username). For those cases, the native GitHub UI is fine. If your goal is to execute multi-step workflows—like 'Find the latest bug, list the affected files, and create a new issue'—this server is mandatory.

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by GitHub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

How we secure it →

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This server provides 18 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

add_issue_comment create_new_issue create_pull_request get_file_contents get_issue_details get_my_github_profile get_repository_details list_branches list_commits list_org_repositories list_pull_requests list_releases list_repo_issues list_stargazers list_user_repositories search_github_code search_github_repositories verify_api_connection

The GitHub dashboard forces you to click through too many tabs.

Today, if you want to know the status of a project, you click the repo link. Then you might click 'Issues,' scroll past dozens of old tickets, and then click 'Pull Requests' to see if the code is merged. You're bouncing between tabs, copying issue numbers, and checking dates just to get a simple overview of project health.

With the GitHub MCP Server, you just tell your agent: 'What's the status of the core services?' It runs `list_org_repositories` and `list_repo_issues` in the background. You get the structured answer immediately, no dashboard clicks required.

GitHub MCP Server: Manage Repositories and Issues

Instead of manually fetching file contents via the web UI, or running multiple searches, you send a single prompt: 'What's the definition of the user model in the auth service?' The agent executes `get_file_contents` and returns the code block directly. It's an instant, context-aware read operation.

This isn't just a wrapper. It moves your development workflow from a click-and-copy process to a conversational command. It fundamentally changes how you interact with source control.

Common Questions About GitHub MCP

How do I get a Personal Access Token (PAT) for GitHub? +

Log in to GitHub, go to Settings > Developer settings > Personal access tokens, and you can generate a new token (classic or fine-grained) there.

Can I read private repositories? +

Yes, provided that your Personal Access Token has the necessary scopes (e.g., 'repo') to access your private content.

How do I search for code within a specific organization? +

Use the 'search_github_code' tool and include the organization qualifier in your query, for example: 'org:vinkius my-term'.

Can I comment on issues via the agent? +

The current version supports creating new issues. For commenting or advanced PR management, you can use the search and metadata tools to gather context.

How does the `get_file_contents` tool read file content? +

It fetches the raw text of the file. You just provide the full repository path and file name. The agent returns the content, which you can then analyze or summarize.

What if I need to list all user repositories using `list_user_repositories`? +

You must specify the GitHub username. The tool returns a list of repository names and their primary metadata. This lets your AI client know what's available on that user's account.

Does the GitHub MCP Server handle rate limits? +

Yes, the Vinkius platform manages rate limit adherence. When you make too many calls, the agent pauses and waits for the appropriate window reset, so your workflow doesn't fail.

Can I check the connection status using `verify_api_connection`? +

This tool confirms that your Personal Access Token (PAT) is valid and authorized. It returns a success or failure status immediately, letting you know if the connection works before you start.

View all recipes →