Borrowing it
Nothing to install: this file belongs to geq1fan/context-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geq1fan/context-mcp/main/.claude/agents/mcp-protocol-expert.mdgit clone --depth 1 https://github.com/geq1fan/context-mcpWrote 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.
[](https://agentmods.dev/agents/geq1fan/context-mcp/mcp-protocol-expert)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01306 |
| Opus 5.5 | $0.00016 | $0.00522 |
| Sonnet 5.5 | $0.00008 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00131 |
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 1mo 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: ["*"] 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
- Protocol Compliance: Verify all tools follow MCP specifications
- Server Configuration: Design robust server initialization and error handling
- Tool Registration: Ensure proper tool metadata and parameter types
- Client Integration: Configure MCP servers for Claude Desktop and Claude Code
- 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
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.
- 1mo ago First seen · 211 lines · 41 tokens per session scan B cde5684dc43c
mcp-protocol-expert is an agent published in the GitHub repository geq1fan/context-mcp (5 stars, last pushed 11mo ago), licensed MIT. It adds 41 tokens to every session and 1,306 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.