Skip to content
Back to AI Coding

Claude Code MCP Configuration

Register local and remote MCP servers with Claude Code for custom tools.

Claude CodeAdvanced

Why

Stack Overflow's 2025 Developer Survey reports 9.7% of developers use Claude Code, and JetBrains' January 2026 AI Pulse found 18% of professional developers use it at work, up 1.5x since September 2025. Claude Code can call MCP tools (query your DB, run a deploy, read a ticket) directly in the terminal session.

Wiring servers once gives the agent durable capabilities across sessions without re-explaining API calls.

When

Configure MCP when you want the agent to act on external systems (DB, tickets, deploy) or read internal docs/resources. Skip for pure code edits in the repo.

How

1. Build or pick an MCP server (stdio local or SSE remote). 2. Add it to .mcp.json (project) or ~/.claude/mcp.json (user): { "mcpServers": { "db": { "command": "node", "args": ["db-server.js"] } } } 3. For remote: { "url": "https://mcp.example.com/sse", "transport": "sse" }. 4. Restart Claude Code; /mcp lists connected servers and tools. 5. The agent now calls your tools when relevant; reference them explicitly in prompts.

Example

// .mcp.json { "mcpServers": { "postgres": { "command": "npx", "args": ["@mcp/postgres", "postgres://localhost/db"] }, "tickets": { "url": "https://mcp.internal/tickets/sse", "transport": "sse" } } } In session: "use the postgres tool to find users without a profile, then fix each"

Common Problems

  • ⚠Error: Cannot find module '@anthropic-ai/claude-code' → run `npm install -g @anthropic-ai/claude-code`; requires Node.js 18+.
  • ⚠"Error: ENOTFOUND api.anthropic.com" → check `echo $ANTHROPIC_API_KEY` is set and network/proxy allows api.anthropic.com:443.
  • ⚠Error: Rate limit: "429 Too Many Requests" → run `/cost` to check usage, `/compact` to shrink context, or wait for quota reset.

Best Practices

  • ✓Commit .mcp.json so the whole team shares tool access.
  • ✓Validate servers with the MCP Inspector before registering with Claude.
  • ✓Measure the outcome with a concrete metric (time saved, defect rate, test coverage) so the practice can be justified and improved.

FAQ

What is Claude Code MCP Configuration?

Register local and remote MCP servers with Claude Code for custom tools. It helps developers quickly grasp the core value and use cases of Claude Code MCP Configuration.

How do I get started with Claude Code MCP Configuration?

To get started with Claude Code MCP Configuration, focus on these points first: Build or pick an MCP server (stdio local or SSE remote).

What are common mistakes with Claude Code MCP Configuration?

Common mistakes when using Claude Code MCP Configuration include: Error: Cannot find module '@anthropic-ai/claude-code' → run `npm install -g @anthropic-ai/claude-code`; requires Node.js 18+.; "Error: ENOTFOUND api.anthropic.com" → check `echo $ANTHROPIC_API_KEY` is set and network/proxy allows api.anthropic.com:443.; Error: Rate limit: "429 Too Many Requests" → run `/cost` to check usage, `/compact` to shrink context, or wait for quota reset..

What are the best practices for Claude Code MCP Configuration?

Best practices for Claude Code MCP Configuration include: Commit .mcp.json so the whole team shares tool access.; Validate servers with the MCP Inspector before registering with Claude.; Measure the outcome with a concrete metric (time saved, defect rate, test coverage) so the practice can be justified and improved..

How do I learn more about Claude Code MCP Configuration?

Start with the official docs, then search real-world examples on GitHub. Validate patterns in a small scratch repo before applying them to production code.