---

name: mcp-management description: > Manages MCP (Model Context Protocol) servers for Claude Code and Claude Desktop. Activates for: finding MCP servers, MCP registries, MCP server setup, MCP configuration, MCP troubleshooting, MCP security, building MCP servers, MCP transport selection, claude mcp commands, mcp.json files, mcpServers configuration, tool poisoning prevention, MCP debugging, Smithery, Glama, GitHub MCP registry, which MCP server should I use. NOT for: general Claude Code settings (use claude-code-mastery), OAuth/authentication unrelated to MCP, generic API integrations without MCP.

MCP Management

Comprehensive guide for finding, configuring, securing, and building MCP servers for Claude Code and Claude Desktop.

Quick Navigation

• Find Servers: See Discovering MCP Servers
• Configure Servers: See references/server-configs.md
• Build Custom Servers: See references/building-servers.md
• Security: See references/security-essentials.md
• Troubleshooting: See references/troubleshooting.md
• Enterprise: See references/enterprise-config.md

Platform Differences

Discovering MCP Servers

Primary Registries

Specialized Directories

Evaluation Criteria

When selecting an MCP server:

1. Maintenance: Recent commits? Active issues?
2. Security: Reviewed code? Known vulnerabilities?
3. Token cost: How many tokens does it consume?
4. Transport: HTTP (remote) vs stdio (local)?
5. Trust: Official vs community vs unknown author?

Pre-Installation Workflow

CRITICAL: Before installing ANY MCP server, follow this workflow:

1. Fetch and Read the README

Always retrieve the server's README.md from GitHub or the registry:

Copy# View README directly
gh repo view owner/repo-name

# Or fetch raw README
curl -s https://raw.githubusercontent.com/owner/repo/main/README.md

Look for:

• Required environment variables
• Prerequisites (Node 18+, Python 3.10+, API keys)
• Configuration options and defaults
• Usage examples and limitations
• Security considerations

2. Check for Deprecations

3. Verify Prerequisites

Copy# Check Node version (18+ typically required)
node --version

# Check Python version (3.10+ for MCP SDK)
python3 --version

# Check if package exists
npm view @package/server-name

4. Review Security Implications

Before proceeding, confirm:

• What filesystem paths can it access?
• What network requests can it make?
• What environment variables does it read?
• Is the source code available and reviewed?

5. Install Following README Instructions

Only after completing steps 1-4, install using the README's recommended method.

Transport Types

Quick Setup Examples

Claude Code (CLI)

Copy# Add remote server
claude mcp add --transport http github https://api.githubcopilot.com/mcp/

# Add local server
claude mcp add --transport stdio postgres -- npx -y @modelcontextprotocol/server-postgres

# List servers
claude mcp list

# Remove server
claude mcp remove github

Claude Desktop (JSON)

Copy{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_xxx"
      }
    }
  }
}

MCP vs CLI Decision

Token budget matters: GitHub MCP ~40k tokens. Context7 ~500 tokens. Enable sparingly.

Security Essentials

Critical risks (2025 research: 43% of servers have command injection flaws):

1. Prompt injection: Malicious content in fetched data manipulates Claude
2. Tool poisoning: Malicious tool descriptions trick model into unsafe actions
3. Credential exposure: API keys in version control or logs

Mitigations:

• Only install from trusted registries
• Review server code before installing unknown servers
• Use scoped tokens with minimal permissions
• Never commit credentials to version control
• Enable project-scope servers only after review

See references/security-essentials.md for detailed patterns.

Building MCP Servers

Language Selection

Python Quick Start (FastMCP)

Copyfrom mcp.server.fastmcp import FastMCP

mcp = FastMCP("my-server")

@mcp.tool()
async def my_tool(param: str) -> str:
    """Tool description for Claude."""
    return f"Result: {param}"

if __name__ == "__main__":
    mcp.run(transport="stdio")

TypeScript Quick Start

Copyimport { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new McpServer({ name: "my-server", version: "1.0.0" });

server.registerTool("my_tool", {
  description: "Tool description for Claude",
  inputSchema: { param: z.string() }
}, async ({ param }) => ({
  content: [{ type: "text", text: `Result: ${param}` }]
}));

const transport = new StdioServerTransport();
await server.connect(transport);

Critical: For stdio transport, NEVER write to stdout (corrupts JSON-RPC). Use stderr or logging libraries.

See references/building-servers.md for complete patterns.