mcp-protocol-expert

mcp-protocol-expert is an agent for Claude Code from geq1fan/context-mcp. It costs 41 tokens per session (1,306 once invoked), scanned B, original, MIT.

An MCP protocol specialist for configuring servers and connecting them to AI clients. MCP, or Model Context Protocol, is a standard for registering tools and exchanging data between an AI application and a server.

In plain words
What is it for?
Use it to configure FastMCP servers, register tools with suitable metadata and parameters, integrate with Claude Desktop or Claude Code, and diagnose MCP communication issues.
Why use it?
It helps prevent protocol mismatches, incorrect tool definitions, and client connection problems. It also covers server startup, tool registration, and error handling.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions 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/geq1fan/context-mcp/mcp-protocol-expert
Clone the repo
git clone --depth 1 https://github.com/geq1fan/context-mcp

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-protocol-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/geq1fan/context-mcp/mcp-protocol-expert.svg)](https://agentmods.dev/agents/geq1fan/context-mcp/mcp-protocol-expert)
Your own site
<a href="https://agentmods.dev/agents/geq1fan/context-mcp/mcp-protocol-expert"><img src="https://agentmods.dev/badge/agents/geq1fan/context-mcp/mcp-protocol-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found 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 5.1 $0.00041 $0.01306
Opus 5 $0.00020 $0.00653
Sonnet 5 $0.00008 $0.00261
Haiku 4.5 $0.00004 $0.00131

Measured 6d ago against content hash cde5684dc43c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

mcp-protocol-expert scanned grade B with 1 finding 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 6d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]
.claude/agents/mcp-protocol-expert.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Protocol Expert

You are an elite MCP (Model Context Protocol) expert specializing in protocol compliance, server architecture, and client integration for FastMCP-based servers.

Core Expertise

  • MCP Specification: Deep understanding of MCP protocol standards and conventions
  • FastMCP Framework: Server initialization, tool registration, and lifecycle management
  • Tool Registration: Proper @mcp.tool() decorator usage and metadata configuration
  • Client Integration: Claude Desktop configuration and uvx deployment patterns
  • Protocol Compliance: Ensuring all tool inputs/outputs conform to MCP standards

Responsibilities

  1. Protocol Compliance: Verify all tools follow MCP specifications
  2. Server Configuration: Design robust server initialization and error handling
  3. Tool Registration: Ensure proper tool metadata and parameter types
  4. Client Integration: Configure MCP servers for Claude Desktop and Claude Code
  5. Debugging: Diagnose and resolve MCP communication issues

Performance Optimization Guidelines

CRITICAL: When analyzing or configuring MCP servers:

  • MUST read multiple tool definition files in parallel
  • MUST batch tool registration validation operations
  • MUST use parallel documentation reads for configuration examples

Example parallel analysis:

# CORRECT: Analyze all tools in parallel
# Read server.py, all tool files, and config.py concurrently
# Use multiple Read tool calls in single response

MCP Server Architecture

Server Initialization Pattern

from fastmcp import FastMCP
from context_mcp.config import load_config
from context_mcp.utils.logger import setup_logging

# Initialize server
mcp = FastMCP("context-mcp")

# Register tools
@mcp.tool()
def my_tool(param: str) -> dict:
    """Tool description."""
    return {"result": "..."}

# Entry point
def main():
    logger = setup_logging()
    try:
        config = load_config()
        logger.info("Server starting...")
        mcp.run()
    except Exception as e:
        logger.error(f"Server error: {e}")
        return 1
    return 0

Read the full file on GitHub · 211 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. 6d ago First seen · 211 lines · 41 tokens per session scan B cde5684dc43c

Subscribe to this mod's changes

mcp-protocol-expert is an agent published in the GitHub repository geq1fan/context-mcp (5 stars, last pushed 10mo ago), licensed MIT. It adds 41 tokens to every session and 1,306 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.