MCP Servers

MCP (Model Context Protocol) lets Claude connect to external tools. Think of MCPs as plugins that give Claude new abilities.

What Are MCP Servers?

MCP servers are bridges between Claude and external systems:

• Context7 - Access up-to-date documentation
• Playwright - Browser automation and testing
• Chrome DevTools - Inspect live browsers
• GitHub - Interact with repos and PRs

Context Warning

Each MCP server adds context. Too many active MCPs can slow Claude down and fill your context window. Choose 2-3 that match your workflow.

Recommended MCPs

For Python development:

MCP Server	Purpose	Priority
Context7	Latest library documentation	High
Playwright	Browser testing & automation	High
Chrome DevTools	Browser debugging	Medium
GitHub	Repos, PRs, issues	Medium

Installing MCP Servers

1. Add an MCP server

   claude mcp add context7 -- npx -y @upstash/context7-mcp

2. Verify installation

   claude mcp list

3. Use in conversation

   > use context7 to look up the latest FastAPI documentation for dependency injection

Detailed Setup

Context7 - Documentation Access

Context7 injects up-to-date, version-specific documentation into Claude’s context.

claude mcp add context7 -- npx -y @upstash/context7-mcp

Usage:

> use context7 to find the latest Vue 3 composition API docs

> use context7: how do I use Pydantic v2 model validators?

Tip

Add “use context7” to prompts when you need current documentation. Claude’s training data may be outdated for fast-moving libraries.

Playwright - Browser Automation

Playwright lets Claude interact with web pages for testing and automation.

claude mcp add playwright -- npx -y @playwright/mcp@latest

Usage:

> use playwright to test the login flow on localhost:3000

> write an E2E test that adds an item to cart and checks out

What Claude can do:

• Navigate to URLs
• Click buttons, fill forms
• Take screenshots
• Extract page content
• Run tests

Chrome DevTools - Browser Debugging

Inspect and debug live browser sessions.

claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest

Usage:

> inspect the network requests when I click the submit button

> check for console errors on the current page

> what's causing the layout shift on mobile?

Managing MCP Servers

List Active Servers

claude mcp list

Remove a Server

claude mcp remove context7

Disable Temporarily

> /mcp disable postgres

Check Status

> /mcp status

MCP Tool Search

For projects with many MCP tools, Claude Code uses lazy loading: loads only tool metadata upfront (~100 tokens/tool), fetches full definitions on-demand. Automatically activates when tools would consume >10% of context.

Check status with /mcp list - tools using lazy loading are marked [lazy].

Environment Variables

MCP_TIMEOUT - Server startup timeout in ms (default: 5000). Increase for slow-starting servers:

MCP_TIMEOUT=10000 claude

MAX_MCP_OUTPUT_TOKENS - MCP response limit (default: 25,000). Increase if responses get truncated:

MAX_MCP_OUTPUT_TOKENS=50000 claude

Windows Configuration

On native Windows (not WSL), prefix npx commands with cmd /c:

claude mcp add --transport stdio my-server -- cmd /c npx -y @some/package

Note

Not needed in WSL.

MCP Configuration File

For persistent configuration, edit ~/.claude/mcp.json:

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    },
    "playwright": {
      "command": "npx",
      "args": ["-y", "@playwright/mcp@latest"]
    },
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"]
    }
  }
}

Project-Level MCP Configuration

Create .mcp.json in your project root for team-shared MCP servers. Use ${VAR_NAME} for environment variables:

{
  "mcpServers": {
    "database": {
      "command": "npx",
      "args": ["-y", "@company/db-mcp-server"],
      "env": {
        "DB_HOST": "localhost"
      }
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  }
}

Variables are read from your environment at runtime. Don’t commit secrets!

Remote MCP Servers (HTTP/SSE)

Connect to remote MCP servers over HTTP using Server-Sent Events:

# CLI
claude mcp add --transport sse remote-api https://api.example.com/mcp/sse

# JSON config
{
  "mcpServers": {
    "remote-api": {
      "type": "sse",
      "url": "https://api.example.com/mcp/sse",
      "headers": { "Authorization": "Bearer ${API_TOKEN}" }
    }
  }
}

Useful for company-hosted servers or cloud-based tool providers.

Best Practices

Limit Active MCPs - Choose 2-3 that match your current work. Too many MCPs consume context unnecessarily.

Use MCPs Explicitly - Tell Claude when to use an MCP:

> use context7 to check the SQLAlchemy 2.0 async syntax

Disable When Not Needed - MCPs consume context even when idle:

> /mcp disable postgres

Verify Critical Information - Context7 provides latest docs, but double-check for important decisions.

Troubleshooting

MCP Not Responding

claude mcp status context7    # Check status
claude mcp restart context7    # Restart server

Connection Errors - Verify network connectivity or connection strings.

Slow Responses - Reduce active MCPs, disable unused servers, or check for excessive data output.