About Github Projects Mcp Server
The GitHub Projects V2 MCP server provides tools for managing GitHub Projects V2 boards through the GraphQL API. It is intended for users who want to view and update project tickets from Claude or other MCP clients. It requires a GitHub personal access token with repo, project and read:org permissions.
Key features
- 01List Projects V2 for users and organizations
- 02View project fields and items
- 03Create issues and add them to projects
- 04Create draft issues in a project
- 05Update field values on project items
- 06Delete items from a project
Use cases
- 01Checking ticket status on a project board from a chat
- 02Creating issues and adding them to a specific project
- 03Filtering project items by state or single-select field
MCP support
This project is an MCP server that exposes eight tools for Projects V2 to MCP clients such as Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
8Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| owner | string | Yes |
Details
From the project READMEGitHub Projects V2 MCP Server
A Model Context Protocol (MCP) server that provides tools for managing GitHub Projects V2 through Claude and other MCP clients. This server uses the GitHub GraphQL API for interacting with GitHub Projects V2.
Features
- List and view GitHub Projects V2 for users and organizations
- Get project fields and items (issues, PRs, draft issues)
- Create issues and add them to projects
- Create draft issues directly in projects
- Update project item field values
- Delete items from projects
Usage
This server can be used with any MCP client, such as Claude Desktop. Add it to
your MCP client configuration (e.g., claude_desktop_config.json).
Option 1: Using Published Package
Here's an example configuration using uvx as the command runner:
{
"mcpServers": {
"github-projects": {
"command": "uvx",
"args": [
"mcp-github-projects"
],
"env": {
"GITHUB_TOKEN": "your_pat_here"
}
}
}
}
Make sure to replace your_pat_here with your actual GitHub Personal Access
Token.
Option 2: From Source Code
To run the project directly from source code, follow these steps:
Setup
-
Clone the repository:
git clone [email protected]:Arclio/github-projects-mcp.git cd github-projects-mcp -
Create and activate a virtual environment:
uv venv source venv/bin/activate -
Install dependencies:
uv pip install -e . -
Set your GitHub token as an environment variable:
Create a GitHub Personal Access Token and give it the necessary permissions. The required permissions are:
repo,project, andread:org.Add the token to your
.envfile after running this command:cp .env.example .envThen add the following to your
.envfile:export GITHUB_TOKEN=your_personal_access_token
Usage from source code
When using from source code, configure your MCP client as follows:
{
"mcpServers": {
"github-projects": {
"command": "uv",
"args": [
"--directory",
"/path/to/github-projects-mcp",
"run",
"mcp-github-projects"
],
"env": {
"GITHUB_TOKEN": "your_pat_here"
}
}
}
}
Make sure to replace /path/to/github-projects-mcp and your_pat_here with
your actual repository path and GitHub Personal Access Token.
Available Tools
list_projects: List GitHub Projects V2 for a given organization or userget_project_fields: Get fields available in a GitHub Project V2get_project_items: Get items in a GitHub Project V2 (supports filtering by state or custom single-select fields)create_issue: Create a new GitHub issueadd_issue_to_project: Add an existing GitHub issue to a Project V2update_project_item_field: Update a field value for a project itemcreate_draft_issue: Create a draft issue directly in a GitHub Project V2delete_project_item: Delete an item from a GitHub Project V2
See tool documentation in the server code for detailed usage information.
Development
The project is structured as follows:
src/github_projects_mcp/: Main package directoryserver.py: MCP server implementation with tool definitionsgithub_client.py: GraphQL client for GitHub API interactions
To contribute, make sure to:
- Add proper error handling for all GraphQL operations
- Add type annotations for all functions and parameters
- Update documentation when adding new tools or features
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.