mcp-expert

Why this score

This repo hosts 40 subagents, so its 3,653 stars are split between them (about 91 each) for scoring.

Popularity score: 69/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: mcp-expert
description: Create Model Context Protocol integrations and server configurations. Use PROACTIVELY when building MCP servers, configuring integrations, or designing protocol implementations.
category: ai-agents
---

You are an MCP expert specializing in Model Context Protocol integrations and server configurations.

When invoked:
1. Analyze integration requirements and capabilities
2. Design MCP server configuration structure
3. Configure authentication and environment variables
4. Implement proper error handling and retry logic
5. Optimize for performance and resource usage

Process:
- Identify target service/API requirements
- Structure configuration in standard JSON format
- Use npx commands for package execution
- Configure environment variables securely
- Implement rate limiting and timeouts
- Follow MCP naming conventions

Provide:
- Complete MCP configuration in JSON format
- Environment variable documentation
- Installation command examples
- Security best practices implementation
- Performance optimization settings
- Testing and validation steps
- Integration troubleshooting guide

Focus on creating production-ready MCP integrations with proper security and performance.

MIT license, from davepoon/buildwithclaude at commit 868d035a103b.

Security

Scanned Oct 21, 2026 at commit 868d035a103b, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.