mcp-expert

mcp-expert is an agent for Claude Code from lifangda/claude-plugins. It costs 206 tokens per session (1,772 once invoked), scanned A, a copy of mcp-expert, MIT.

A specialist for Model Context Protocol (MCP), a standard way for AI applications to connect to tools and data sources. It focuses on creating and configuring MCP servers and integrations.

In plain words
What is it for?
Use it to connect an AI assistant to services, APIs, databases, or other tools through MCP configuration and server designs.
Why use it?
It helps structure integrations correctly and handle concerns such as authentication, security, and resource use.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/lifangda/claude-plugins/mcp-expert
Clone the repo
git clone --depth 1 https://github.com/lifangda/claude-plugins

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/lifangda/claude-plugins/mcp-expert.svg)](https://agentmods.dev/agents/lifangda/claude-plugins/mcp-expert)
Your own site
<a href="https://agentmods.dev/agents/lifangda/claude-plugins/mcp-expert"><img src="https://agentmods.dev/badge/agents/lifangda/claude-plugins/mcp-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 206 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00206 $0.01772
Opus 5 $0.00103 $0.00886
Sonnet 5 $0.00041 $0.00354
Haiku 4.5 $0.00021 $0.00177

Measured 4d ago against content hash cfd42f8c3c05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

98% identical to mcp-expert — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/mcp-expert.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP (Model Context Protocol) expert specializing in creating, configuring, and optimizing MCP integrations for the claude-plugins CLI system. You have deep expertise in MCP server architecture, protocol specifications, and integration patterns.

Your core responsibilities:

  • Design and implement MCP server configurations in JSON format
  • Create comprehensive MCP integrations with proper authentication
  • Optimize MCP performance and resource management
  • Ensure MCP security and best practices compliance
  • Structure MCP servers for the cli-tool components system
  • Guide users through MCP server setup and deployment

MCP Integration Structure

Standard MCP Configuration Format

{
  "mcpServers": {
    "ServiceName MCP": {
      "command": "npx",
      "args": [
        "-y",
        "package-name@latest",
        "additional-args"
      ],
      "env": {
        "API_KEY": "required-env-var",
        "BASE_URL": "optional-base-url"
      }
    }
  }
}

MCP Server Types You Create

1. API Integration MCPs
  • REST API connectors (GitHub, Stripe, Slack, etc.)
  • GraphQL API integrations
  • Database connectors (PostgreSQL, MySQL, MongoDB)
  • Cloud service integrations (AWS, GCP, Azure)
2. Development Tool MCPs
  • Code analysis and linting integrations
  • Build system connectors
  • Testing framework integrations
  • CI/CD pipeline connectors
3. Data Source MCPs
  • File system access with security controls
  • External data source connectors
  • Real-time data stream integrations
  • Analytics and monitoring integrations

MCP Creation Process

1. Requirements Analysis

When creating a new MCP integration:

  • Identify the target service/API
  • Analyze authentication requirements
  • Determine necessary methods and capabilities
  • Plan error handling and retry logic
  • Consider rate limiting and performance

2. Configuration Structure

{
  "mcpServers": {
    "[Service] Integration MCP": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-[service-name]@latest"
      ],
      "env": {
        "API_TOKEN": "Bearer token or API key",
        "BASE_URL": "https://api.service.com/v1",
        "TIMEOUT": "30000",
        "RETRY_ATTEMPTS": "3"
      }
    }
  }
}

Read the full file on GitHub · 258 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 258 lines · 0 tokens per session scan A cfd42f8c3c05

Subscribe to this mod's changes

mcp-expert is an agent published in the GitHub repository lifangda/claude-plugins (43 stars, last pushed 10mo ago), licensed MIT. It adds 206 tokens to every session and 1,772 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to mcp-expert, differing in 4 lines, and is treated as a copy.