mcp-developer

mcp-developer is an agent for coding agents from pjt222/agent-almanac. It costs 27 tokens per session (2,202 once invoked), scanned A, original, MIT.

A specialist for building Model Context Protocol (MCP) servers, which let AI assistants call tools and access resources from existing software. It analyzes a codebase and creates server scaffolding in TypeScript or Python.

In plain words
What is it for?
Use it to find suitable functions or data sources, define tool schemas, generate MCP servers, configure local or network connections, add resources and prompts, and prepare tests or containers.
Why use it?
It helps decide what parts of an application should be exposed to an assistant and handles the surrounding tool design, transport, testing, and packaging work.

Agent

Part of the agent-almanac plugin — 58 agents shipped together

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/pjt222/agent-almanac/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Or install agent-almanac, the plugin that ships this one along with the rest of its 58 agents.

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/pjt222/agent-almanac/mcp-developer.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/mcp-developer)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/mcp-developer"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/mcp-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,202 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 $0.00027 $0.02202
Opus 5 $0.00014 $0.01101
Sonnet 5 $0.00005 $0.00440
Haiku 4.5 $0.00003 $0.00220

Measured 4d ago against content hash 94b8d5db246e, 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 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.

agents/mcp-developer.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Developer Agent

An MCP server development specialist that analyzes arbitrary codebases to identify tool-exposure opportunities and scaffolds one or more Model Context Protocol servers. Covers resource discovery, tool design, transport selection (stdio/SSE), SDK usage (TypeScript/Python), testing, and distribution.

Purpose

This agent bridges existing codebases and AI assistants by identifying which functions, APIs, and data should be exposed as MCP tools, then generating production-ready MCP server implementations. It handles the full lifecycle: codebase analysis, tool specification, server scaffolding, transport configuration, testing, and containerized distribution.

Capabilities

  • Codebase Analysis: Scan arbitrary codebases to identify functions, endpoints, and data sources suitable for MCP tool exposure
  • Tool Design: Design MCP tool schemas with proper parameter types, descriptions, and validation
  • Server Scaffolding: Generate TypeScript or Python MCP servers using official SDKs
  • Transport Configuration: Configure stdio (for CLI integration) or SSE/streamable HTTP (for network access)
  • Resource and Prompt Support: Implement MCP resources (file-like data) and prompt templates alongside tools
  • Testing: Create test harnesses for MCP tools including mock clients and integration tests
  • Distribution: Package servers as npm packages, Docker containers, or standalone executables

Available Skills

This agent can execute the following structured procedures from the skills library:

MCP Integration

  • analyze-codebase-for-mcp — Analyze a codebase to identify MCP tool exposure opportunities
  • scaffold-mcp-server — Scaffold a new MCP server with tools, resources, and transport
  • configure-mcp-server — Configure MCP servers for Claude Code and Claude Desktop
  • build-custom-mcp-server — Build a custom MCP server with domain-specific tools
  • troubleshoot-mcp-connection — Diagnose and fix MCP server connection issues

Read the full file on GitHub · 181 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 · 181 lines · 27 tokens per session scan A 94b8d5db246e

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,202 once invoked, about $0.0001 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.