MCPInstall

awesome-mcp-servers-discovery

Discover, explore, and learn about MCP (Model Context Protocol) servers from a curated list of 6000+ implementations across 30+ categories

Installs
233
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/mcp-skills --skill awesome-mcp-servers-discovery
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads awesome-mcp-servers-discovery automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Awesome MCP Servers Discovery

Skill by ara.so — MCP Skills collection.

This skill enables discovery and exploration of the Awesome MCP Servers repository, a curated list of Model Context Protocol (MCP) servers, tools, frameworks, clients, and utilities. The repository catalogs 6000+ MCP server implementations across 30+ categories including file systems, databases, cloud platforms, AI services, and more.

What is This Repository

Awesome MCP Servers is a community-driven collection that helps developers:

  • Discover MCP servers by category (databases, file systems, cloud storage, etc.)
  • Find official vs. community implementations
  • Access reference servers and tutorials
  • Learn security best practices for MCP
  • Discover tools to install and manage MCP servers

The repository includes:

  • Reference Servers: Example implementations from the official MCP protocol
  • Official Servers: Vendor-maintained implementations (marked with ⭐)
  • Community Servers: 6000+ community-built implementations
  • Tools & Utilities: CLI tools, managers, and frameworks for MCP
  • Multi-language documentation: English, 简体中文, 繁體中文, 日本語, 한국어

Installation & Access

Accessing the Repository

# Clone the repository
git clone https://github.com/YuzeHao2023/Awesome-MCP-Servers.git
cd Awesome-MCP-Servers

# View the full Excel list of 6000+ servers
# Open Full-List-of-MCP-Servers.xlsx

Installing MCP Server Management Tools

# Install mcp-get (CLI tool for installing MCP servers)
npm install -g @michaellatman/mcp-get

# Install mcp-cli (inspector for MCP servers)
npm install -g @wong2/mcp-cli

# Install yamcp (workspace manager)
npm install -g yamcp

Key Categories

📂 File Systems

Servers providing file system access with configurable permissions.

Official Reference:

# Filesystem server from modelcontextprotocol
npx @modelcontextprotocol/server-filesystem <allowed-directory>

Community Examples:

  • mcp-everything-search - Everything Search integration
  • fast-filesystem-mcp - Fast filesystem implementation
  • llm-context - Context-aware file access

🗄️ Databases

Database access with schema inspection and query capabilities.

PostgreSQL Example:

# Official PostgreSQL MCP server
npx @modelcontextprotocol/server-postgres postgresql://user:password@localhost/dbname

Other Database Servers:

  • SQLite: @modelcontextprotocol/server-sqlite
  • MongoDB: @kiliczsh/mcp-mongo-server
  • Redis: Official from redis/mcp-redis
  • BigQuery: @LucasHild/mcp-server-bigquery
  • Neon (⭐): @neondatabase/mcp-server-neon

🔄 Version Control

Git and version control integration.

GitHub Official Server:

# Install GitHub MCP server
npm install @github/github-mcp-server

# Configure in Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@github/github-mcp-server"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  }
}

☁️ Cloud Storage

Access to cloud storage platforms.

Google Drive:

npx @modelcontextprotocol/server-gdrive

Box (Official ⭐):

📦 Sandbox & Virtualization

Secure sandbox environments for code execution.

E2B (Official ⭐):

npm install @e2b/mcp-server

# Configure
{
  "mcpServers": {
    "e2b": {
      "command": "npx",
      "args": ["-y", "@e2b/mcp-server"],
      "env": {
        "E2B_API_KEY": "${E2B_API_KEY}"
      }
    }
  }
}

Microsandbox (Official ⭐):

⚡ Cloud Platforms

Integration with cloud providers.

Cloudflare (Official ⭐):

npm install @cloudflare/mcp-server-cloudflare

# Configure
{
  "mcpServers": {
    "cloudflare": {
      "command": "npx",
      "args": ["-y", "@cloudflare/mcp-server-cloudflare"],
      "env": {
        "CLOUDFLARE_API_TOKEN": "${CLOUDFLARE_API_TOKEN}"
      }
    }
  }
}

🤖 AI Services

AI and LLM service integrations.

Notable Servers:

  • Anthropic: Official Claude API integration
  • OpenAI: OpenAI API integration
  • Hugging Face: Model inference and datasets
  • AgentQL: Web scraping for AI agents

💻 Development Tools

Development and coding assistance.

Memory Server (Reference):

# Persistent memory across conversations
npx @modelcontextprotocol/server-memory

Sequential Thinking (Reference):

# Extended reasoning capabilities
npx @modelcontextprotocol/server-sequentialthinking

Using Server Management Tools

mcp-get: Install and Manage Servers

# Search for servers
mcp-get search database

# Install a server
mcp-get install @modelcontextprotocol/server-postgres

# List installed servers
mcp-get list

# Remove a server
mcp-get remove @modelcontextprotocol/server-postgres

mcp-cli: Inspect Servers

# Inspect a running MCP server
mcp-cli inspect http://localhost:3000

# List available tools from a server
mcp-cli tools @modelcontextprotocol/server-filesystem /path/to/dir

# Test a server
mcp-cli test @modelcontextprotocol/server-sqlite database.db

yamcp: Workspace Manager

# Initialize a workspace
yamcp init

# Add a server to workspace
yamcp add filesystem --path /allowed/directory

# Start all workspace servers
yamcp start

# Stop all servers
yamcp stop

Configuration Patterns

Claude Desktop Configuration

Located at:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Multi-Server Configuration:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"]
    },
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres"],
      "env": {
        "DATABASE_URL": "${DATABASE_URL}"
      }
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@github/github-mcp-server"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  }
}

Environment Variables Pattern

# .env file (never commit this)
DATABASE_URL=postgresql://user:pass@localhost/db
GITHUB_TOKEN=ghp_xxxxxxxxxxxxx
OPENAI_API_KEY=sk-xxxxxxxxxxxxx
CLOUDFLARE_API_TOKEN=xxxxxxxxxxxxx

# Load in shell
export $(cat .env | xargs)

Security Best Practices

⚠️ Critical Security Warnings:

  1. Arbitrary Code Execution: MCP servers can execute code with your user permissions
  2. System Access: Full access to files, network, and system resources
  3. Prompt Injection: Malicious prompts could trigger unintended actions
  4. Data Exposure: Sensitive data may be accessed or leaked

Best Practices:

# 1. Use official implementations when available (⭐ marked)
# 2. Review code before installation
git clone <mcp-server-repo>
# Review the code thoroughly

# 3. Run in isolated containers (Docker example)
docker run --rm -it \
  -v /allowed/path:/data:ro \
  --network=none \
  mcp-server-image

# 4. Limit permissions
chmod 500 /path/to/mcp-server  # Read + execute only
chown root:mcp /path/to/mcp-server

# 5. Monitor activity
# Enable logging in server config
{
  "mcpServers": {
    "myserver": {
      "command": "npx",
      "args": ["-y", "mcp-server", "--log-level", "debug"],
      "logFile": "/var/log/mcp/myserver.log"
    }
  }
}

Finding Servers by Use Case

Database Query & Analysis

# Search the Excel file or README for "database"
# Official options:
- PostgreSQL: @modelcontextprotocol/server-postgres
- SQLite: @modelcontextprotocol/server-sqlite
- MongoDB: @kiliczsh/mcp-mongo-server
- Redis: redis/mcp-redis (⭐)
- BigQuery: @LucasHild/mcp-server-bigquery

File Operations

# Reference implementation
npx @modelcontextprotocol/server-filesystem /path/to/allowed/directory

# Fast implementation
npm install fast-filesystem-mcp

# With search capabilities
npm install mcp-everything-search

Cloud Platform Management

# AWS
# Check awslabs repositories under modelcontextprotocol

# Cloudflare (⭐)
npm install @cloudflare/mcp-server-cloudflare

# Azure
# Check Azure repositories for official MCP servers

Web Scraping & Search

# Brave Search (⭐)
npm install @modelcontextprotocol/server-brave-search

# AgentQL
npm install @tinyfish-io/agentql-mcp

# Fetch (reference)
npx @modelcontextprotocol/server-fetch

Common Patterns

Pattern: Adding a New Server to Your Setup

# 1. Find the server in the repository
# Browse categories in README or search Full-List-of-MCP-Servers.xlsx

# 2. Review the server (security check)
git clone <server-repo-url>
cd <server-repo>
cat README.md  # Check documentation
cat package.json  # Check dependencies

# 3. Install via mcp-get or npm
mcp-get install <server-package>
# OR
npm install <server-package>

# 4. Configure in Claude Desktop
# Edit claude_desktop_config.json
{
  "mcpServers": {
    "newserver": {
      "command": "npx",
      "args": ["-y", "<server-package>", "<args>"],
      "env": {
        "API_KEY": "${API_KEY}"
      }
    }
  }
}

# 5. Restart Claude Desktop
# Server should now be available

Pattern: Testing a Server Before Deployment

# Use mcp-cli to test
mcp-cli test <server-package> <args>

# Example: Test filesystem server
mcp-cli test @modelcontextprotocol/server-filesystem /tmp

# Check available tools
mcp-cli tools <server-package> <args>

# Inspect server metadata
mcp-cli inspect <server-package>

Pattern: Creating a Multi-Environment Setup

# Development config (dev_claude_config.json)
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/dev"]
    },
    "postgres": {
      "env": {
        "DATABASE_URL": "postgresql://localhost/dev_db"
      }
    }
  }
}

# Production config (prod_claude_config.json)
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/var/www"]
    },
    "postgres": {
      "env": {
        "DATABASE_URL": "${PROD_DATABASE_URL}"
      }
    }
  }
}

# Swap configs as needed
ln -sf ~/dev_claude_config.json ~/Library/Application\ Support/Claude/claude_desktop_config.json

Troubleshooting

Server Not Appearing in Claude

# 1. Check config syntax
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json | jq .

# 2. Verify server installation
npx <server-package> --help

# 3. Check server logs
# Add logging to config:
{
  "mcpServers": {
    "myserver": {
      "command": "npx",
      "args": ["-y", "server", "--verbose"]
    }
  }
}

# 4. Restart Claude Desktop completely
killall "Claude"
open -a "Claude"

Server Crashes or Errors

# 1. Test server standalone
npx <server-package> <args>

# 2. Check permissions
ls -la $(which <server-binary>)

# 3. Verify environment variables are set
echo $GITHUB_TOKEN  # Should show token

# 4. Check for conflicting servers
# Remove other servers temporarily from config

# 5. Update server to latest version
npm update <server-package>

Finding a Server for Specific Use Case

# 1. Search README by category
# Browse https://github.com/YuzeHao2023/Awesome-MCP-Servers

# 2. Search Excel file
# Open Full-List-of-MCP-Servers.xlsx
# Use Excel search/filter features

# 3. Use GitHub search
# Search within repository for keywords

# 4. Check official implementations first
# Look for ⭐ markers in README

# 5. Review community discussions
# Check Issues and Discussions tabs on GitHub

Performance Issues

# 1. Limit server scope
# Example: Restrict filesystem access
{
  "filesystem": {
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/specific/path"]
  }
}

# 2. Use caching where available
# Check server documentation for cache options

# 3. Monitor resource usage
top -p $(pgrep -f mcp-server)

# 4. Consider lighter alternatives
# Check category for alternative implementations

Reference: Key Server Categories

CategoryCountNotable Servers
📂 File Systems~50filesystem (⭐), everything-search, fast-filesystem-mcp
🗄️ Databases~100postgres (⭐), sqlite (⭐), mongodb, redis (⭐), bigquery
🔄 Version Control~30github (⭐), gitlab, git (⭐)
☁️ Cloud Storage~40gdrive (⭐), box (⭐), ms-365
⚡ Cloud Platforms~60cloudflare (⭐), aws, azure, google
🤖 AI Services~80anthropic, openai, huggingface
💻 Dev Tools~200memory (⭐), sequential-thinking (⭐), docker
🔍 Search & Web~150brave-search (⭐), fetch (⭐), agentql
💬 Communication~40slack, linear, atlassian
📈 Monitoring~30sentry (⭐), metoro, signoz

Additional Resources

Contributing to the List

If you want to add a server to Awesome MCP Servers:

# 1. Fork the repository
gh repo fork YuzeHao2023/Awesome-MCP-Servers

# 2. Add your server to appropriate category in README.md
# Format: - Name — URL

# 3. Create pull request
git checkout -b add-my-server
git add README.md
git commit -m "Add my-server to Category"
git push origin add-my-server
gh pr create

FAQ

What does the awesome-mcp-servers-discovery skill do?

Discover, explore, and learn about MCP (Model Context Protocol) servers from a curated list of 6000+ implementations across 30+ categories

How do I install awesome-mcp-servers-discovery?

Run npx skills add https://github.com/reason-machines/mcp-skills --skill awesome-mcp-servers-discovery in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/awesome-mcp-servers-discovery/ (personal) or .claude/skills/awesome-mcp-servers-discovery/ (project).

Which AI agents can use awesome-mcp-servers-discovery?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is awesome-mcp-servers-discovery safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains awesome-mcp-servers-discovery?

It is published by reason-machines in reason-machines/mcp-skills. It has 233 recorded installs.

More from reason-machines/mcp-skills

View all →

codebase-memory-mcp-intelligence

reason-machines/mcp-skills

High-performance code intelligence MCP server that indexes codebases into knowledge graphs for structural queries, call traces, and architecture analysis

AI & Agents505 installs

playwright-mcp-server

reason-machines/mcp-skills

Browser automation MCP server using Playwright's accessibility tree for LLM-friendly web interaction

AI & Agents285 installs

tradingview-mcp-assistant

reason-machines/mcp-skills

AI-assisted TradingView chart analysis and automation via Chrome DevTools Protocol for Claude Code

AI & Agents262 installs

lanhu-mcp-collaboration

reason-machines/mcp-skills

AI-powered design collaboration server connecting Lanhu design platform with AI coding assistants for requirements analysis, UI design extraction, and team knowledge sharing

AI & Agents256 installs

chrome-devtools-mcp-automation

reason-machines/mcp-skills

Expert guidance for Chrome DevTools MCP server - browser automation, debugging, and performance analysis for AI agents

AI & Agents239 installs

github-mcp-server

reason-machines/mcp-skills

Open the skill to read its SKILL.md instructions.

AI & Agents237 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs