Github MCP Server Java
A Java implementation of the GitHub MCP (Model Context Protocol) Server using Spring AI. This server provides MCP-compatible tools for interacting with the GitHub API.
README
GitHub MCP Server — Java / Spring AI
A production-ready MCP server that connects any MCP-compatible AI agent to the GitHub API. Manage repositories, issues, pull requests, and search — all through natural language.
Transport: HTTP/SSE on port 8080, compatible with Cursor and Claude Desktop out of the box.
Why this server?
| Capability | This server | GitHub REST API |
|---|---|---|
| Repository management | ✅ | ✅ |
| Issue & PR operations | ✅ | ✅ |
| Branch & commit control | ✅ | ✅ |
| Code & user search | ✅ | ✅ |
| Natural language interface | ✅ | ❌ |
| MCP protocol (SSE) | ✅ | ❌ |
| Java / Spring AI | ✅ | ❌ |
| GitHub Enterprise support | ✅ | ✅ |
Tools (38 total)
| Category | Count | Tools |
|---|---|---|
| Repository | 11 | create_repository, fork_repository, get_repository, list_commits, get_commit, get_file_contents, create_or_update_file, delete_file, create_branch, list_branches, merge_branch |
| Issues | 11 | create_issue, update_issue, add_issue_comment, list_issues, get_issue, close_issue, reopen_issue, assign_issue, unassign_issue, add_issue_labels, remove_issue_label |
| Pull Requests | 10 | create_pull_request, update_pull_request, list_pull_requests, get_pull_request, merge_pull_request, close_pull_request, reopen_pull_request, add_pull_request_comment, create_pull_request_review, submit_pull_request_review |
| Search | 4 | search_code, search_issues, search_repositories, search_users |
| Users | 3 | get_authenticated_user, get_user, list_user_repositories |
Quick start
# 1. Build
mvn clean package
# 2. Set credentials
export GITHUB_PERSONAL_ACCESS_TOKEN=ghp_...
# 3. Run (SSE transport — port 8080)
java -jar target/github-mcp-server-1.0.0.jar
# 4. Verify
curl http://localhost:8080/health
# 5. Inspect all tools
npx @modelcontextprotocol/inspector http://localhost:8080/sse
Get your token from GitHub Settings → Developer settings → Personal access tokens.
For GitHub Enterprise, set GITHUB_HOST to your instance URL.
Architecture
MCP Client (Cursor / Claude Desktop / other)
│ HTTP/SSE transport (/sse + /mcp/message)
▼
Tool class (@McpTool — thin delegation layer, validates required params)
▼
Service interface + impl (business logic, error mapping, pagination)
▼
GitHubRestClient (typed HTTP gateway, PAT auth, exception handling)
▼
GitHub REST API
The architecture is strictly layered:
client/— GitHub integration boundary (HTTP, Bearer-Auth, error handling)service/— domain logic (filtering, mapping, pagination)tools/— MCP-facing surface (descriptions, param validation, delegation)- Spring Boot — runtime and transport wrapper only
Every tool returns a consistent ApiResponse<T> envelope:
{ "success": true, "data": { ... } }
{ "success": false, "errorCode": "REPO_NOT_FOUND", "errorMessage": "..." }
Configuration
| Property | Env var | Required | Default | Description |
|---|---|---|---|---|
| — | GITHUB_PERSONAL_ACCESS_TOKEN |
✅ | — | GitHub Personal Access Token |
| — | GITHUB_HOST |
❌ | github.com |
GitHub hostname (for GitHub Enterprise) |
| — | GITHUB_READ_ONLY |
❌ | false |
Restrict to read-only operations |
| — | GITHUB_TOOLSETS |
❌ | all | Comma-separated list of toolsets to enable |
| — | GITHUB_TOOLS |
❌ | all | Comma-separated list of specific tools to enable |
| — | GITHUB_EXCLUDE_TOOLS |
❌ | none | Comma-separated list of tools to exclude |
Creating a GitHub Personal Access Token
- Go to GitHub Settings → Developer settings → Personal access tokens
- Click "Generate new token (classic)"
- Select the following scopes:
repo— Full control of private repositoriesworkflow— Update GitHub Action workflowsread:org— Read org and team membershipgist— Create gistsnotifications— Access notificationsread:user— Read user profile data
- Generate and copy the token
Client config
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"github": {
"url": "http://localhost:8080/sse"
}
}
}
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"github": {
"url": "http://localhost:8080/sse"
}
}
}
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
VS Code / GitHub Copilot
URL mode (if your client supports it):
{
"github.copilot.chat.mcp.servers": {
"github": {
"url": "http://localhost:8080/sse"
}
}
}
Command mode (stdio-only clients):
{
"github.copilot.chat.mcp.servers": {
"github": {
"command": "java",
"args": ["-jar", "/path/to/github-mcp-server-1.0.0.jar"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..."
}
}
}
}
Docker
# Build image
docker build -t github-mcp-server:latest .
# Run
docker run --rm -p 8080:8080 \
-e GITHUB_PERSONAL_ACCESS_TOKEN=ghp_... \
github-mcp-server:latest
If GitHub Enterprise runs in Docker on the same host, use host.docker.internal:
-e GITHUB_HOST=http://host.docker.internal:3000
Running tests
mvn test
Package structure
com.github.mcp
├── GithubMcpApplication.java @SpringBootApplication
├── config/
│ ├── GitHubProperties.java @ConfigurationProperties — token, host, readOnly, toolsets
│ └── WebConfig.java Web configuration
├── client/
│ ├── GitHubRestClient.java GET/POST/PATCH/DELETE HTTP gateway; typed exceptions
│ └── GitHubGraphqlClient.java GraphQL client
├── controller/
│ └── HealthController.java Health check endpoint (GET /health)
├── exception/
│ ├── GitHubMcpException.java Base exception
│ └── GlobalExceptionHandler.java Global error handler
├── dto/
│ ├── common/ ApiResponse · PagedResponse
│ ├── request/ *Request DTOs
│ └── response/ *Response DTOs
├── service/ Interfaces + impl — business logic, error mapping, pagination
└── tools/
├── RepositoryTools.java (11 tools)
├── IssueTools.java (11 tools)
├── PullRequestTools.java (10 tools)
├── SearchTools.java (4 tools)
└── UserTools.java (3 tools)
Troubleshooting
401 Unauthorized
Token issue. Check:
GITHUB_PERSONAL_ACCESS_TOKENis set correctly- The token has not expired
- The token has the required scopes (see Configuration)
- For GitHub Enterprise: confirm
GITHUB_HOSTis set to your instance URL
REPO_NOT_FOUND / 404 Not Found
The repository may be private and the token lacks repo scope, or the owner/name is incorrect.
Connection timeouts
The server connects to api.github.com (or your GITHUB_HOST). Ensure the JVM process has outbound network access.
Copilot / Claude can't see the server
- Confirm the server is running:
curl http://localhost:8080/health - Confirm the MCP SSE endpoint is alive:
curl http://localhost:8080/sse - Check that the URL in the client config points to
http://localhost:8080/sse
Acknowledgments
This project is a Java / Spring AI port of the official GitHub MCP Server written in Go.
License
MIT License — see LICENSE for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.