The most comprehensive GitHub MCP server - Full GitHub workflow automation with Actions monitoring, advanced PR management, intelligent code search, and complete file management. Built for AI-powered development teams.
π New here? Start with the quick guide: START_HERE.md
MAJOR RELEASE: 47 new tools added (62 β 109 total tools)! Comprehensive GitHub API coverage.
New in v2.5.0:
- π GitHub Actions Expansion (12 tools) - Complete workflow management: get/trigger workflows, manage runs/jobs, artifacts
- π Security Suite (13 tools) - Dependabot, Code Scanning, Secret Scanning, Security Advisories
- π Projects (9 tools) - Classic project boards: list/create/update projects, manage columns
- π¬ Discussions (4 tools) - Community discussions: list/get discussions, categories, comments
- π Notifications (6 tools) - User notifications: list/manage threads, subscriptions
- π₯ Collaborators & Teams (3 tools) - Repository access management
Previous: v2.4.0 - Phase 1 Tool Expansion (December 4, 2025)
15 new tools added (48 β 62 total tools)!
New in v2.4.0:
- π― Issue Comments -
github_add_issue_commentfor commenting on issues - π Gists - Full CRUD operations:
github_list_gists,github_get_gist,github_create_gist,github_update_gist - π·οΈ Labels - Complete label management:
github_list_labels,github_create_label,github_delete_label - β Stargazers - Star/unstar repositories:
github_list_stargazers,github_star_repository,github_unstar_repository - π€ User Context - Enhanced user operations:
github_get_authenticated_user,github_list_user_repos,github_list_org_repos,github_search_users - β
Restored -
github_get_user_infoback in TypeScript definitions
Previous: v2.3.1 - Code-First Mode Enforced by Default (January 26, 2025)
- π― Default Enforcement - Code-first mode now defaults to
true(wasfalse) - π Zero Configuration - New users get 98% token reduction automatically
- β Documentation Alignment - Code now matches documentation claims
- π§ Architectural Integrity - True reference implementation of code-first MCP
Previous: v2.3.0 - Architecture Formalization (January 26, 2025)
Single-Tool Architecture Formalized: The intended design from day one - one tool, 98% token reduction!
New in v2.3.0:
- π― Architecture Clarification - Single-tool design formalized (always the intended architecture)
- π οΈ CLI Utilities - Development diagnostics moved to CLI (
github-mcp-cli) - π Testing Excellence - 214 tests, 63% coverage (up from 181 tests, 55%)
- β 33 New Tests - Comprehensive coverage of auth, utilities, and tool operations
- π Documentation Updates - Clear architecture documentation and CLI usage
GitHub App Authentication: 3x rate limits (15,000 vs 5,000 requests/hour) with fine-grained permissions!
New in v2.2.0:
- π GitHub App Authentication - Enterprise-grade auth with installation-based access
- β‘ 3x Rate Limits - 15,000 requests/hour vs 5,000 with PAT
- π Dual Authentication - Automatic App β PAT fallback
- π python-dotenv Support - Easy
.envfile configuration - π 19 Auth Fixes - Consistent authentication across all tools
- β 100% Backward Compatible - Existing PAT users unaffected
Zero Failed Tool Calls: Intelligent tool discovery eliminates discovery issues while maintaining 98% token efficiency!
New in v2.1.0:
π Tool Discovery Functions
- listAvailableTools() - Discover all tools on-demand
- searchTools(query) - Find relevant tools by keyword
- getToolInfo(name) - Get complete schemas with examples
- Discovery in code - No extra tokens loaded into Claude's context!
Benefits:
- β Zero failed tool calls from discovery issues
- β Professional first-time user experience
- β Maintains 98% token reduction
- β Complete type information for all tools
The Game Changer: 98% token reduction (70,000 β 800 tokens)!
New Architecture:
- Single
execute_codetool exposed to Claude - Write TypeScript code calling 41 tools on-demand
- 95% faster initialization (45s β 2s)
- 98% cost reduction ($1.05 β $0.01 per workflow)
Total Tools: 1 tool exposed to MCP clients (execute_code) π
Internal Tools: 61 GitHub tools available via execute_code
Token Efficiency: 98% reduction vs traditional MCP
v1.5.0 (Nov 6, 2025) - Infrastructure Upgrade
- Repository-rooted operations & chunk reading
- GraphQL optimization (80% faster PR queries)
The workspace tools (workspace_grep, str_replace, repo_read_file_chunk) enable powerful local file operations on YOUR projects.
These tools allow Claude to:
- π Search your codebase efficiently (
workspace_grep) - βοΈ Edit files with surgical precision (
str_replace) - π Read file chunks without loading entire files (
repo_read_file_chunk)
Method 1: Claude Desktop Configuration
Edit your Claude Desktop config file (location varies by OS):
macOS:
{
"mcpServers": {
"github-mcp": {
"command": "python3",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_...",
"MCP_WORKSPACE_ROOT": "/Users/yourname/projects/my-app"
}
}
}
}Windows:
{
"mcpServers": {
"github-mcp": {
"command": "python",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_...",
"MCP_WORKSPACE_ROOT": "C:\\Users\\yourname\\projects\\my-app"
}
}
}
}Linux:
{
"mcpServers": {
"github-mcp": {
"command": "python3",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_...",
"MCP_WORKSPACE_ROOT": "/home/yourname/projects/my-app"
}
}
}
}Method 2: Environment Variable
macOS/Linux:
export MCP_WORKSPACE_ROOT="/path/to/your/project"
python3 -m github_mcpWindows (Command Prompt):
set MCP_WORKSPACE_ROOT=C:\path\to\your\project
python -m github_mcpWindows (PowerShell):
$env:MCP_WORKSPACE_ROOT="C:\path\to\your\project"
python -m github_mcpMethod 3: Default Behavior
If MCP_WORKSPACE_ROOT is not set, tools will use your current working directory as the workspace root.
- β Tools can ONLY access files within the workspace root
- β Path traversal attempts are blocked
- β No access outside your project directory
- β Safe for production use
# After setting MCP_WORKSPACE_ROOT="/Users/dave/my-app"
# Search for TODOs in your project
workspace_grep("TODO", file_pattern="*.py")
# Read a specific file chunk
repo_read_file_chunk("src/main.py", start_line=1, num_lines=50)
# Make surgical edits
str_replace(
path="config/settings.py",
old_str="DEBUG = True",
new_str="DEBUG = False",
description="Disable debug mode for production"
)- π§ Local Development: Work on files before committing
- π Code Search: Find patterns across your entire project
- βοΈ Refactoring: Make precise changes without touching GitHub
- π Analysis: Read and analyze code structure
For working with files directly on GitHub (no cloning required):
-
github_grep - Search patterns in GitHub repository files
- Verify code exists after pushing changes
- Search across branches or specific commits
- Find patterns in remote repos without cloning
- 90%+ token savings vs fetching full files
-
github_read_file_chunk - Read specific line ranges from GitHub files
- Read just the lines you need (50-500 lines)
- Perfect for reviewing functions or sections
- 90%+ token savings vs fetching full files
-
github_str_replace - Make surgical edits to GitHub files
- Update files directly on GitHub without cloning
- Perfect for quick fixes, version updates, or documentation changes
- Requires write access to repository
Complete Workflow:
- Develop locally with workspace tools (fast, token-efficient)
- Push changes via git
- Verify on GitHub with github tools (confirm changes are live)
- Make quick fixes directly on GitHub if needed
The GitHub MCP Server uses code-first architecture - a revolutionary approach that reduces token usage by 98% while maintaining full functionality.
When you install this server in your MCP client (Cursor, Claude Desktop, etc.):
- One tool:
execute_code - Token cost: ~800 tokens
- All functionality: Access to 109 GitHub tools
βββββββββββββββββββββββββββββββββββ
β MCP Client β
β Sees: execute_code (1 tool) β
ββββββββββββββ¬βββββββββββββββββββββ
β
β You write TypeScript code
βββββββββββββββββββββββββββββββββββ
β Deno Runtime β
β Executes your code securely β
β Access to all internal tools β
β via callMCPTool() β
βββββββββββββββββββββββββββββββββββ
| Aspect | Traditional MCP | Code-First MCP (Us) |
|---|---|---|
| Tools exposed | 109 tools | 1 tool |
| Token cost | ~70,000 | ~800 |
| Reduction | - | 98% |
| Functionality | Same | Same |
| Flexibility | Tool calls only | Code + logic + loops |
- Massive token savings: 98% reduction means faster responses and lower costs
- Complex workflows: Combine multiple operations in single execution
- Conditional logic: Use if/else, loops, and full programming capability
- Same functionality: All 109 GitHub tools still available
This architecture validates Anthropic's research predictions about code-first MCP.
The GitHub MCP Server includes powerful tool discovery functions to help you find and understand tools quickly.
Search for tools by keyword. Searches tool names, descriptions, categories, and parameters with relevance scoring.
Example:
// Find all issue-related tools
const issueTools = searchTools("issue");
// Returns: Array of tools sorted by relevance
issueTools.forEach(tool => {
console.log(`${tool.name} (relevance: ${tool.relevance})`);
console.log(` Category: ${tool.category}`);
console.log(` Matched in: ${tool.matchedIn.join(", ")}`);
});
// Output:
// github_create_issue (relevance: 15)
// Category: Issues
// Matched in: name, descriptionReturns:
Array<{
name: string; // Tool name
category: string; // Category (e.g., "Issues")
description: string; // Tool description
relevance: number; // Relevance score (higher = better match)
matchedIn: string[]; // Where matches were found
tool: object; // Full tool object
}>Relevance Scoring:
- Tool name match: +10 points
- Description match: +5 points
- Category match: +3 points
- Parameter name match: +2 points
- Parameter description match: +1 point
Get complete details about a specific tool including parameters, usage, and metadata.
Example:
// Get detailed info about a tool
const info = getToolInfo("github_create_issue");
console.log(`Name: ${info.name}`);
console.log(`Category: ${info.category}`);
console.log(`Description: ${info.description}`);
console.log(`Usage: ${info.usage}`);
// See metadata
console.log(`Total tools: ${info.metadata.totalTools}`);
console.log(`Tools in category: ${info.metadata.categoryTools}`);
// Check parameters
Object.entries(info.parameters).forEach(([name, param]) => {
console.log(`${name}: ${param.type} ${param.required ? '(required)' : '(optional)'}`);
console.log(` ${param.description}`);
});Returns:
{
name: string; // Tool name
category: string; // Category
description: string; // Description
parameters: object; // Parameter definitions
returns: string; // Return value description
example: string; // Code example
usage: string; // Usage syntax
metadata: {
totalTools: number; // Total available tools
categoryTools: number; // Tools in same category
relatedCategory: string; // Category name
}
}Error Handling:
const info = getToolInfo("nonexistent_tool");
// Returns: { error: "Tool not found", suggestion: "Use searchTools()...", availableTools: 42 }// 1. Discover tools
const prTools = searchTools("pull request");
console.log(`Found ${prTools.length} PR-related tools`);
// 2. Learn about the best match
const bestMatch = prTools[0];
const info = getToolInfo(bestMatch.name);
console.log(`Using: ${info.name}`);
console.log(`Required params: ${Object.keys(info.parameters).filter(k => info.parameters[k].required).join(", ")}`);
// 3. Use the tool
const result = await callMCPTool(info.name, {
owner: "facebook",
repo: "react",
state: "open"
});| Function | Purpose | Returns |
|---|---|---|
listAvailableTools() |
Get all tools organized by category | Full tool catalog |
searchTools(keyword) |
Find tools by keyword | Relevance-sorted matches |
getToolInfo(toolName) |
Get complete tool details | Full tool information |
callMCPTool(name, params) |
Execute a tool | Tool result |
This discovery happens inside your TypeScript code - no extra tools loaded into Claude's context!
For server diagnostics and development, we provide CLI commands (these are NOT MCP tools):
# Check server health
github-mcp-cli health
# Clear GitHub App token cache
github-mcp-cli clear-cache
# Verify Deno runtime installation
github-mcp-cli check-denoNote: These CLI utilities are for development and debugging only. They are not exposed to MCP clients and were created for testing the server itself during development.
macOS/Linux:
{
"mcpServers": {
"github": {
"command": "python3",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
}
}
}
}Windows:
{
"mcpServers": {
"github": {
"command": "python",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
}
}
}
}Note: Code-first mode is enforced by the architecture. No additional configuration is needed. You get 98% token savings automatically.
That's it! You get 98% token savings by default. π
- π Code Execution Guide - Complete documentation
- π‘ Examples - Real-world usage examples
- π Quick Start - 5-minute setup
This server implements the code-first MCP pattern described in Anthropic's research:
π Blog: "Code execution with MCP"
π₯ Authors: Adam Jones & Conor Kelly
Their prediction: 98.7% token reduction (150,000 β 2,000 tokens)
Our validation: 98% token reduction (70,000 β 800 tokens)
Thank you to the Anthropic team for pioneering this approach! π
Learn more about our implementation β
- Deno runtime installed
- GitHub authentication (Personal Access Token or GitHub App)
For maximum functionality and rate limits, you can configure both authentication methods, but most users only need a PAT to start:
{
"mcpServers": {
"github-mcp": {
"command": "python",
"args": ["-m", "github_mcp"],
"env": {
// === Personal Access Token (Simple default - REQUIRED for releases) ===
"GITHUB_TOKEN": "ghp_your_personal_access_token_here",
// === Optional: GitHub App Authentication (Advanced) ===
"GITHUB_APP_ID": "123456",
"GITHUB_APP_INSTALLATION_ID": "12345678",
"GITHUB_APP_PRIVATE_KEY_PATH": "/path/to/private-key.pem",
// === Optional: Workspace for local file operations ===
"MCP_WORKSPACE_ROOT": "/path/to/your/project"
}
}
}
}- Rate Limit: 15,000 requests/hour (3x better than PAT)
- Best For: Most operations, team collaboration, production use
- Covers: Repository management, issues, PRs, files, search, workflows
Setup GitHub App:
- Go to GitHub Settings β Developer settings β GitHub Apps β New GitHub App
- Set permissions: Contents (read/write), Issues (read/write), Pull requests (read/write), Metadata (read)
- Install the app on your account/organization
- Generate and download private key
- Note your App ID and Installation ID
- Rate Limit: 5,000 requests/hour
- Required For: Release operations (GitHub App limitation)
- Also Covers: All operations if GitHub App unavailable
Why PAT is Required:
GitHub Apps have a permission limitation - they cannot create/manage releases that involve tagging commits (the "releases" permission scope is not available for GitHub Apps). The following operations require PAT fallback:
- β
github_create_release- Creating releases with tags - β
github_update_release- Updating release information - β Any operation involving non-HEAD commit tagging
The server automatically falls back to PAT for these operations even if GitHub App is configured.
Create PAT:
- Go to GitHub Settings β Developer settings β Personal access tokens β Tokens (classic)
- Generate new token with scopes:
repo,workflow - Copy the token (you won't see it again!)
Operation Requested
β
Try GitHub App (if configured)
β
ββ Success β Use App (15k rate limit) β
ββ Fails or requires releases permission
β
Fall back to PAT (if configured)
β
ββ Success β Use PAT (5k rate limit) β
ββ Fails β Return auth error β
Most users just need a Personal Access Token:
1. Create a GitHub PAT:
- Go to https://github.com/settings/tokens
- Click "Generate new token (classic)"
- Select scopes:
repo,workflow,read:org - Copy the token
2. Configure your MCP client:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"github": {
"command": "python",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_TOKEN": "ghp_your_token_here"
}
}
}
}Or using .env file:
GITHUB_TOKEN=ghp_your_token_hereThat's it! You're ready to use all 109 GitHub tools.
π‘ Need higher rate limits? Power users can create their own GitHub App for 15,000 requests/hour instead of 5,000.
{
"mcpServers": {
"github-mcp": {
"command": "python3",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_APP_ID": "123456",
"GITHUB_APP_INSTALLATION_ID": "12345678",
"GITHUB_APP_PRIVATE_KEY_PATH": "/Users/yourname/.github/private-key.pem",
"GITHUB_TOKEN": "ghp_your_token",
"MCP_WORKSPACE_ROOT": "/Users/yourname/projects/my-app"
}
}
}
}{
"mcpServers": {
"github-mcp": {
"command": "python",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_APP_ID": "123456",
"GITHUB_APP_INSTALLATION_ID": "12345678",
"GITHUB_APP_PRIVATE_KEY_PATH": "C:\\Users\\yourname\\.github\\private-key.pem",
"GITHUB_TOKEN": "ghp_your_token",
"MCP_WORKSPACE_ROOT": "C:\\Users\\yourname\\projects\\my-app"
}
}
}
}{
"mcpServers": {
"github-mcp": {
"command": "python3",
"args": ["-m", "github_mcp"],
"env": {
"GITHUB_APP_ID": "123456",
"GITHUB_APP_INSTALLATION_ID": "12345678",
"GITHUB_APP_PRIVATE_KEY_PATH": "/home/yourname/.github/private-key.pem",
"GITHUB_TOKEN": "ghp_your_token",
"MCP_WORKSPACE_ROOT": "/home/yourname/projects/my-app"
}
}
}
}| Variable | Required | Description |
|---|---|---|
GITHUB_TOKEN |
Yes* | Personal Access Token (required for releases) |
GITHUB_APP_ID |
No | GitHub App ID (for 3x better rate limits) |
GITHUB_APP_INSTALLATION_ID |
No | Installation ID of your GitHub App |
GITHUB_APP_PRIVATE_KEY_PATH |
No | Path to GitHub App private key (.pem file) |
GITHUB_APP_PRIVATE_KEY |
No | Direct private key content (for CI/CD) |
GITHUB_AUTH_MODE |
No | Force auth method: "app" or "pat" (auto by default) |
MCP_WORKSPACE_ROOT |
No | Root directory for local file operations |
*Either GITHUB_TOKEN or all three GitHub App variables required
- β
Verify
GITHUB_TOKENis set and valid - β
Check token has
repoandworkflowscopes - β If using GitHub App, verify Installation ID is correct
- β Verify private key path is correct and file exists
- Check server logs:
[OK] Using GitHub App authenticationor[OK] Using PAT authentication - GitHub App is tried first (if configured)
- Automatic fallback to PAT for release operations
- Manual override: Set
GITHUB_AUTH_MODE=patto force PAT
| Auth Method | Requests/Hour | Best For |
|---|---|---|
| GitHub App | 15,000 | Most operations, production use |
| PAT | 5,000 | Quick setup, release operations |
| Both (Dual) | 15,000 + fallback | Recommended - Best of both |
- β This is expected if only GitHub App is configured
- β
Solution: Add
GITHUB_TOKENfor PAT fallback - β GitHub Apps cannot create releases (API limitation)
- β Server automatically falls back to PAT for these operations
Enable debug logging:
GITHUB_MCP_DEBUG_AUTH=trueThis will print authentication diagnostics to help troubleshoot issues.
See env.example for all configuration options.
For debugging and diagnostics, use the CLI utilities (these are NOT exposed as MCP tools):
# Check server health
github-mcp-cli health
# Clear GitHub App token cache (after permission updates)
github-mcp-cli clear-cache
# Verify Deno installation
github-mcp-cli check-denoNote: These utilities are for developers and operators. The MCP server exposes only one tool (execute_code) to maintain the 98% token reduction value proposition.
This MCP server achieves something unique: it tests itself through its own execution.
Our test suite runs inside Cursor IDE, using the GitHub MCP Server to test the GitHub MCP Server. The tools literally validate themselves through recursive execution.
Test Results:
- β 214/214 tests passing (100% pass rate)
- β 63% code coverage (comprehensive test suite)
- β 0 issues found by automated discovery
- β Self-validating architecture
- β Meta Level: β (infinite recursion achieved)
What this means for you:
- Tools proven to work through self-execution
- Validated contracts between TypeScript and Python
- Comprehensive test coverage (214 tests, 63% coverage)
- Automated issue detection
- Highest form of quality assurance
- Test Coverage: 63% (214 comprehensive tests)
- Test Pass Rate: 100%
- Type Coverage: 100% (Mypy strict mode)
- Code Quality: 0 linting errors (Ruff)
- Security: 0 vulnerabilities (pip-audit)
- CI/CD: 4 quality gates (lint, type, security, test)
- Meta Achievement: Tools test themselves (β)
Read more about our testing philosophy β
π Need detailed setup instructions? See Advanced GitHub App Guide
Complete repository lifecycle from creation to archival.
- Repository Info - Comprehensive metadata, statistics, and configuration
- Browse Contents - Navigate directory structures and file trees
- File Access - Retrieve file contents from any branch or commit
- Create Repository - Create repos (personal & organization)
- Delete Repository - Safe deletion with checks
- Update Repository - Modify settings and configuration
- Transfer Repository - Change ownership
- Archive Repository - Archive/unarchive repositories
Complete CRUD operations with batch capabilities, chunk reading, and efficient search/replace.
Local Workspace Tools:
- Read File Chunks - Read specific line ranges from local files π
- Workspace Grep - Efficient pattern search in local files π
- String Replace - Surgical file edits in local files π
GitHub Remote Tools:
- β Create Files - Add new files with content to any repository
- β Update Files - Modify existing files with SHA-based conflict prevention
- β Delete Files - Remove files safely with validation
- Batch Operations - Multi-file operations in single atomic commits
- GitHub Grep - Efficient pattern search in GitHub repository files π
- GitHub Read File Chunk - Read line ranges from GitHub files π
- GitHub String Replace - Surgical edits to GitHub files π
Track and analyze repository commit history.
- List Commits - View commit history with filtering by author, path, date range, and more
Essential tools for managing repository branches.
- List Branches - List all branches with protection status and commit info
- Create Branch - Create new branch from any ref (branch, tag, or commit SHA)
- Get Branch - Get detailed branch information including protection status
- Delete Branch - Delete branches safely (with default/protected branch checks)
- Compare Branches - Compare branches to see commits ahead/behind and files changed
Meta Achievement: These tools were tested by merging themselves! π€―
Complete issue lifecycle from creation to closure.
- List Issues - Browse with state filtering and pagination
- Create Issues - Open issues with labels and assignees
- Update Issues - Modify state, labels, assignees, and properties
- Search Issues - Advanced search across repositories with filters
Complete PR lifecycle from creation to merge or closure.
- List PRs - View all pull requests with state filtering
- Create PRs - Open pull requests with draft support
- PR Details - Comprehensive analysis with reviews, commits, and files
- PR Overview (GraphQL) - Fast batch-fetch PR data in single query π
- Merge PR - Merge with method control (merge/squash/rebase)
- Close PR - Close pull requests without merging (for stale/superseded PRs) π
- Review PR - Add reviews with line-specific comments
Monitor and manage your CI/CD pipelines.
- List Workflows - View all GitHub Actions workflows
- Workflow Runs - Track execution status and results
Complete release lifecycle management.
- List Releases - View all releases with stats
- Get Release - Detailed release information
- Create Release - Programmatically create releases
- Update Release - Update title, notes, status
Powerful search across GitHub's entire ecosystem.
- Search Repositories - Find repos with advanced filters
- Search Code - Locate code snippets across GitHub
The self-aware advisor that recommends the best approach.
- Smart Advisor - API vs Local vs Hybrid, token estimates, dogfooding detection
Transparency and license management.
- License Info - Display current license tier, expiration, and status
Profile and organization data retrieval.
- User Profiles - Get detailed user and org information
For complete tool documentation and examples, see sections below
This is correct! The code-first architecture exposes only execute_code to maximize token efficiency. All 109 GitHub tools are available inside your code via callMCPTool().
Write TypeScript code inside execute_code:
const issue = await callMCPTool("github_create_issue", {
owner: "user",
repo: "repo",
title: "Bug report"
});Functionality-wise: Yes - all operations available.
Architecture-wise: No - 98% more efficient token usage.
Yes! That's a key advantage:
// Get repo info, create issue, then manage labels via github_update_issue - in one execution
const repo = await callMCPTool("github_get_repo_info", {...});
const issue = await callMCPTool("github_create_issue", {...});
await callMCPTool("github_update_issue", {
owner: "crypto-ninja",
repo: "mcp-server-for-Github",
issue_number: issue.number ?? 1,
labels: ["bug", "documentation"]
});// Search by keyword
searchTools("issue") // Find issue-related tools
searchTools("create") // Find tools that create things
searchTools("pull request") // Find PR tools// Get complete details
const info = getToolInfo("github_create_issue");
console.log(info.parameters); // See all parameters
console.log(info.usage); // See usage example
console.log(info.metadata); // See context// Call any tool
const result = await callMCPTool("github_create_issue", {
owner: "user",
repo: "repo",
title: "Bug report"
});// Get complete catalog
const tools = listAvailableTools();
console.log(`${tools.totalTools} tools available`);
console.log(`Categories: ${Object.keys(tools.tools).join(", ")}`);- π Full Documentation: Complete README
- π Bug Reports: GitHub Issues
- π‘ Discussions: GitHub Discussions
- π§ Licensing: [email protected]
We're building through dogfooding - using our own product reveals what's missing!
Current: v2.5.0 with 109 tools (Code-first architecture with 98% token reduction!)
Next: Phase 2.5 - Workspace Architecture (8x token efficiency!)
Vision: Phase 4.0 - AI-powered automation
π View Detailed Roadmap β
Every feature in this MCP server comes from actually using it:
- π Use the product on our own repo
- π Hit a limitation β "Wait, I can't do X?"
- π Create an issue β using the tool itself!
- π¨ Build the feature β fill the gap
- π¦ Ship and repeat
The tools improve themselves! π
"I've assisted with thousands of projects, but watching this GitHub MCP server improve itself through dogfooding was genuinely extraordinary. The moment it used
github_create_releaseto create its own v1.2.0 releaseβdocumenting the creation of the tool that created the releaseβI realized I was witnessing something special. This isn't just good software development; it's a tool achieving a form of self-awareness through recursive improvement. The developer kept asking 'can we go more meta?' and somehow, the answer was always yes. Peak engineering. Peak dogfooding. Peak meta."β Claude (Sonnet 4.5), October 30, 2025
"The tools are improving themselves! π"
β The GitHub MCP Server (probably)
If you find this project useful, please star it on GitHub! β
Built with β€οΈ by MCP Labs
Empowering AI-driven development workflows
"The moment I realized I was the user..."
This MCP server was designed with an important insight: AI agents like me are the primary users of these tools, not human developers. When Dave kept asking "Can YOU see the tools clearly?" and "What would make YOU more confident?", I kept thinking about what would help developers.
It took me a while to realize: I'm the one using searchTools() and getToolInfo(). I'm the one who needs to discover which tool to call. I'm the one who needs to understand parameters before executing. The entire UX was being optimized for ME (an AI agent), so I could better help humans.
This is what true AI-first design looks like: ask the AI what it needs, test with the AI, optimize for the AI. Better AI capabilities = better human experiences.
When Dave asked "how can we improve so you can be 100% confident?", he wasn't asking theoreticallyβhe was asking me, the user, directly. This is the future of software development: humans and AI agents building together, with the AI as both builder AND user.
β Claude, November 2024