MCP Servers
Extend Claude Code with Model Context Protocol servers
title: MCP Servers description: Extend Claude Code with Model Context Protocol servers
Model Context Protocol (MCP) servers extend Claude Code's capabilities by providing access to external data sources, tools, and services. This guide covers setup, configuration, and best practices.
What is MCP?
MCP (Model Context Protocol) is an open standard that allows AI assistants to securely connect to external systems. MCP servers can provide:
- Resources - Data Claude can read (files, databases, APIs)
- Tools - Actions Claude can perform (queries, writes, API calls)
- Prompts - Pre-defined prompt templates
Configuration
MCP servers are configured in your settings file:
Location: ~/.claude/settings.json (global) or .claude/settings.json (project)
Official MCP Servers
Filesystem Server
Access files and directories:
Capabilities:
- Read file contents
- List directory contents
- Search files by pattern
- Get file metadata
PostgreSQL Server
Query PostgreSQL databases:
Capabilities:
- Execute SELECT queries
- Describe tables and schemas
- List databases
SQLite Server
Work with SQLite databases:
Git Server
Enhanced git operations:
Capabilities:
- View commit history
- Show diffs
- List branches
- Search commits
GitHub Server
Access GitHub repositories and issues:
Capabilities:
- List repositories
- Read issues and PRs
- Search code
- View file contents
Slack Server
Interact with Slack workspaces:
Google Drive Server
Access Google Drive files:
Community MCP Servers
The MCP ecosystem includes many community-built servers:
| Server | Purpose | Install |
|--------|---------|---------|
| mcp-server-fetch | HTTP requests | npx -y mcp-server-fetch |
| mcp-server-puppeteer | Browser automation | npx -y mcp-server-puppeteer |
| mcp-server-brave-search | Web search | npx -y mcp-server-brave-search |
| mcp-server-memory | Persistent memory | npx -y mcp-server-memory |
Find more at github.com/anthropics/mcp-servers↗
Multiple Servers
You can configure multiple MCP servers simultaneously:
Environment Variables
Using System Environment Variables
Reference existing environment variables:
Setting Server-Specific Variables
Building Custom MCP Servers
Server Template (TypeScript)
Server Template (Python)
Debugging MCP Servers
Enable Debug Logging
Check Server Status
This shows:
- Connected servers
- Available tools
- Available resources
Common Issues
Server not starting:
Permission errors:
- Check file/directory permissions
- Verify API keys are valid
- Ensure network access for external APIs
Server crashes:
- Check server logs
- Verify all required environment variables are set
- Test with minimal configuration first
Security Best Practices
1. Limit File Access
Only expose necessary directories:
2. Use Read-Only Access When Possible
Some servers support read-only mode:
3. Separate Configs by Environment
Development (~/.claude/settings.json):
Production (project .claude/settings.json):
4. Rotate Credentials
Regularly rotate API keys and tokens used by MCP servers.
Performance Tips
1. Use Project-Level Config
Configure servers at project level when they're only needed for specific projects.
2. Limit Resource Scope
Narrow down the scope of resources servers can access.
3. Use Caching
Some servers support caching - enable it for better performance: