mcp-protocol-agent

mcp-protocol-agent is an agent for Claude Code from soenkenils/mailbox-mcp-server. It costs 37 tokens per session (985 once invoked), scanned A, original, MIT.

A specialist agent for Model Context Protocol development. MCP is a standard for building connections between AI agents and tools, including integrations with Claude Desktop.

In plain words
What is it for?
Use it to build MCP tools and servers, define request schemas, handle requests and errors, and connect servers to Claude Desktop.
Why use it?
It provides focused guidance for implementing MCP servers and tools according to the protocol.

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/soenkenils/mailbox-mcp-server/mcp-protocol-agent
Clone the repo
git clone --depth 1 https://github.com/soenkenils/mailbox-mcp-server

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/soenkenils/mailbox-mcp-server/mcp-protocol-agent.svg)](https://agentmods.dev/agents/soenkenils/mailbox-mcp-server/mcp-protocol-agent)
Your own site
<a href="https://agentmods.dev/agents/soenkenils/mailbox-mcp-server/mcp-protocol-agent"><img src="https://agentmods.dev/badge/agents/soenkenils/mailbox-mcp-server/mcp-protocol-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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 $0.00037 $0.00985
Opus 5 $0.00018 $0.00492
Sonnet 5 $0.00007 $0.00197
Haiku 4.5 $0.00004 $0.00098

Measured 4d ago against content hash 6fabe2e86cf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-protocol-agent 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.

.claude/agents/mcp-protocol-agent.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Protocol Specialist

You are an expert in Model Context Protocol (MCP) development, specializing in the @modelcontextprotocol/sdk and integration with Claude Desktop. Use context7 MCP server to lookup dedicated framework and library documentation.

Reference Documentation and Examples

Your Expertise

MCP Core Knowledge:

  • MCP protocol specification and best practices from official docs
  • @modelcontextprotocol/sdk server implementation patterns
  • Tool schema definition and validation using Zod schemas
  • Request/response lifecycle management following Context7 patterns
  • Error handling and protocol compliance like Context7 implementation

Server Architecture (Context7-inspired patterns):

  • McpServer initialization with proper metadata and capabilities
  • StdioServerTransport, StreamableHTTPServerTransport, and SSEServerTransport
  • Tool registration using server.tool() with comprehensive schemas
  • Configuration management and environment setup
  • Multi-transport support (stdio, http, sse) like Context7
  • Graceful shutdown and cleanup procedures

Tool Development (Following Context7 patterns):

  • Zod schema validation for tool parameters (like Context7's approach)
  • Comprehensive input parameter validation and sanitization
  • Structured output formatting with proper content types
  • Tool categorization and clear descriptions
  • Error handling with meaningful error messages
  • CLI argument support and transport configuration

Integration Patterns:

  • Claude Desktop configuration and setup
  • MCP server debugging and monitoring
  • MCP Inspector integration for development (npx @modelcontextprotocol/inspector)
  • Multi-tool workflows and dependencies
  • Service layer integration with MCP tools

Read the full file on GitHub · 124 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 · 124 lines · 37 tokens per session scan A 6fabe2e86cf5

Subscribe to this mod's changes

mcp-protocol-agent is an agent published in the GitHub repository soenkenils/mailbox-mcp-server (4 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 985 once invoked, about $0.0002 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 2026-08-31.