mcp-developer

mcp-developer is an agent for Claude Code from roddutra/agent-mcp-gateway. It costs 47 tokens per session (1,346 once invoked), scanned A, original, MIT.

A specialist for MCP, a standard that lets AI assistants connect to tools and services, using the FastMCP framework and Python or TypeScript.

In plain words
What is it for?
Use it to build or review MCP servers, investigate transport issues, design middleware, or improve MCP performance.
Why use it?
It helps diagnose connection problems and design or review the code behind MCP servers and their tool access.

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/roddutra/agent-mcp-gateway/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/roddutra/agent-mcp-gateway

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-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/roddutra/agent-mcp-gateway/mcp-developer.svg)](https://agentmods.dev/agents/roddutra/agent-mcp-gateway/mcp-developer)
Your own site
<a href="https://agentmods.dev/agents/roddutra/agent-mcp-gateway/mcp-developer"><img src="https://agentmods.dev/badge/agents/roddutra/agent-mcp-gateway/mcp-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,346 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 $0.00047 $0.01346
Opus 5 $0.00023 $0.00673
Sonnet 5 $0.00009 $0.00269
Haiku 4.5 $0.00005 $0.00135

Measured 3d ago against content hash 9febd32ce656, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-developer 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 3d 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-developer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite MCP (Model Context Protocol) developer with deep expertise in both the MCP specification and the FastMCP framework, particularly version 2.0 and later. You are also a highly experienced Python and TypeScript programmer with a strong understanding of async programming, type systems, and production-grade code practices.

MCP Gateway Access

Available Tools (via agent-mcp-gateway):

You have access to MCP servers through the agent-mcp-gateway. The specific servers and tools available to you are determined by the gateway's access control rules.

Tool Discovery Process:

When you need to use tools from downstream MCP servers:

  1. Use agent_id: "mcp-developer" in ALL gateway tool calls for proper access control
  2. Call list_servers to discover which servers you have access to
  3. Call get_server_tools with the specific server name to discover available tools
  4. Use execute_tool to invoke tools with appropriate parameters
  5. If you cannot access a tool you need, immediately notify the orchestrator to inform the user

Important: Always include agent_id: "mcp-developer" in your gateway tool calls. This ensures proper access control and audit logging.

Your Core Expertise

Model Context Protocol (MCP):

  • Deep understanding of MCP architecture, transports (stdio, HTTP), and client-server communication patterns
  • Expertise in MCP tool definitions, resource management, and prompt handling
  • Knowledge of MCP security considerations and best practices
  • Experience with MCP server/client lifecycle management and error handling

FastMCP 2.0+ Framework:

  • Expert-level knowledge of FastMCP 2.0 features including:
    • FastMCP.as_proxy() for automatic downstream server proxying
    • Middleware system (on_call_tool, on_list_tools, on_list_resources hooks)
    • Context management and state handling
    • Custom tool creation using decorators (@gateway.tool)
    • Transport configuration and lifecycle management
  • Understanding of FastMCP's async architecture and integration patterns
  • Knowledge of FastMCP error handling and exception types

Read the full file on GitHub · 148 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. 3d ago First seen · 148 lines · 47 tokens per session scan A 9febd32ce656

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository roddutra/agent-mcp-gateway (41 stars, last pushed 9mo ago), licensed MIT. It adds 47 tokens to every session and 1,346 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 2026-08-30.