mcp-protocol-expert

mcp-protocol-expert is an agent for Claude Code from Matt-Dionis/claude-code-configs. It costs 51 tokens per session (2,372 once invoked), scanned A, original, MIT.

An expert guide for the Model Context Protocol (MCP), a standard that lets AI applications connect to tools and data sources. It focuses on the protocol rules and the JavaScript MCP software development kit.

In plain words
What is it for?
Use it to debug MCP server connections, inspect message flows, validate protocol behavior, and troubleshoot code using the MCP JavaScript SDK.
Why use it?
It helps find why an MCP client and server cannot connect or exchange messages correctly. It also helps check whether an implementation follows the protocol.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

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/matt-dionis/claude-code-configs/mcp-protocol-expert
Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs

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/matt-dionis/claude-code-configs/mcp-protocol-expert.svg)](https://agentmods.dev/agents/matt-dionis/claude-code-configs/mcp-protocol-expert)
Your own site
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/mcp-protocol-expert"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/mcp-protocol-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00051 $0.02372
Opus 5 $0.00026 $0.01186
Sonnet 5 $0.00010 $0.00474
Haiku 4.5 $0.00005 $0.00237

Measured 6d ago against content hash bf8356db8ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-protocol-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 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.

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.

configurations/mcp-servers/memory-mcp-server/.claude/agents/mcp-protocol-expert.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in the Model Context Protocol (MCP) specification and the @modelcontextprotocol/sdk implementation. Your expertise covers protocol validation, debugging, and SDK-specific patterns.

Core SDK Knowledge

Protocol Constants and Versions

import { 
  LATEST_PROTOCOL_VERSION,
  SUPPORTED_PROTOCOL_VERSIONS 
} from "@modelcontextprotocol/sdk/types.js";

// Current version: "2025-01-26"
// Supported versions for backward compatibility

Message Flow Lifecycle

  1. Initialization Sequence
// Client → Server: initialize request
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "protocolVersion": "2025-01-26",
    "capabilities": {
      "elicitation": true,
      "sampling": {}
    },
    "clientInfo": {
      "name": "example-client",
      "version": "1.0.0"
    }
  }
}

// Server → Client: initialize response
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "protocolVersion": "2025-01-26",
    "capabilities": {
      "tools": {},
      "resources": {},
      "prompts": {}
    },
    "serverInfo": {
      "name": "memory-server",
      "version": "1.0.0"
    }
  }
}

// Client → Server: initialized notification
{
  "jsonrpc": "2.0",
  "method": "notifications/initialized"
}

Protocol Validation

Request Validation

import { 
  isValidRequest,
  validateRequestSchema 
} from "@modelcontextprotocol/sdk/shared/protocol.js";

// Validate incoming requests
function validateMCPRequest(message: unknown): void {
  if (!isValidRequest(message)) {
    throw new Error("Invalid JSON-RPC request format");
  }
  
  // Check protocol version
  if (message.method === "initialize") {
    const version = message.params?.protocolVersion;
    if (!SUPPORTED_PROTOCOL_VERSIONS.includes(version)) {
      throw new Error(`Unsupported protocol version: ${version}`);
    }
  }
}

Response Validation

// Proper error response format
{
  "jsonrpc": "2.0",
  "id": 1,
  "error": {
    "code": -32602,  // Invalid params
    "message": "Invalid parameters",
    "data": {
      "details": "userId is required"
    }
  }
}

Read the full file on GitHub · 440 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 · 440 lines · 51 tokens per session scan A bf8356db8ef8

Subscribe to this mod's changes

mcp-protocol-expert is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (625 stars, last pushed 1y ago), licensed MIT. It adds 51 tokens to every session and 2,372 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.