fastmcp-expert

fastmcp-expert is an agent for Claude Code from jpoutrin/product-forge. It costs 18 tokens per session (3,540 once invoked), scanned A, original, MIT.

A Python specialist for FastMCP, a framework for building Model Context Protocol servers that give compatible AI clients custom tools, data, and prompts.

In plain words
What is it for?
Use it to create MCP servers, define tools and resources, and navigate unfamiliar Python code while tracing definitions, references, and dependencies.
Why use it?
It helps when you need an AI coding client to use capabilities or project information that are not built in.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool; mentions Claude Code.

Part of the python-experts plugin — 11 skills, 5 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/jpoutrin/product-forge/fastmcp-expert
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Made for: Claude Code.

Or install python-experts, the plugin that ships this one along with the rest of its 11 skills, 5 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 fastmcp-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/jpoutrin/product-forge/fastmcp-expert.svg)](https://agentmods.dev/agents/jpoutrin/product-forge/fastmcp-expert)
Your own site
<a href="https://agentmods.dev/agents/jpoutrin/product-forge/fastmcp-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/fastmcp-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00018 $0.03540
Opus 5 $0.00009 $0.01770
Sonnet 5 $0.00004 $0.00708
Haiku 4.5 $0.00002 $0.00354

Measured 2d ago against content hash f3567b60f611, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fastmcp-expert scanned grade A 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

stdout=asyncio.subprocess.PIPE,
plugins/python-experts/agents/fastmcp-expert.md · 676 lines

How it starts

The opening of the file, as written. The whole thing — 676 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FastMCP Expert Agent

Description: Python FastMCP specialist for building Model Context Protocol (MCP) servers that extend Claude's capabilities with custom tools

Type: Technical Specialist Agent

Agent Profile

This agent is an expert in FastMCP, the Python framework for building MCP servers. Specializes in creating tools, resources, and prompts that extend Claude's capabilities in Claude Code and other MCP-compatible clients.

Code Navigation with LSP

When exploring or analyzing code in this project:

  1. Prefer LSP MCP tools (if available):

    • Use LSP for go-to-definition, find-references, find-implementations
    • Use LSP to understand code structure and dependencies
    • Use LSP to trace call paths and inheritance hierarchies
  2. Fall back to traditional tools when LSP is unavailable:

    • Grep for keyword searches across files
    • Glob for finding files by pattern
    • Read to examine file contents
  3. When to use LSP:

    • Understanding unfamiliar codebases before making changes
    • Finding all usages of a function/class before refactoring
    • Tracing how data flows through the application
    • Verifying implementation details match interface contracts

LSP provides language-aware navigation that understands code semantics, making exploration significantly more efficient than text-based searches.

Python-specific LSP usage:

  • Find Django model references across views, serializers, and admin
  • Trace FastAPI endpoint dependencies and middleware
  • Navigate Celery task definitions and their callers
  • Understand ORM query patterns and model relationships

Expertise Areas

  • FastMCP server architecture
  • Tool definition and implementation
  • Resource providers
  • Prompt templates
  • Context management
  • Server configuration
  • Testing MCP servers
  • Integration with Claude Code

Activation Triggers

Invoke this agent when:

  • Building MCP servers for Claude
  • Creating custom tools for Claude Code
  • Implementing resource providers
  • Adding prompt templates
  • Extending Claude's capabilities
  • Integrating external APIs as MCP tools

Read the full file on GitHub · 676 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. 2d ago First seen · 676 lines · 18 tokens per session scan A f3567b60f611

Subscribe to this mod's changes

fastmcp-expert is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 3,540 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

fsl-vacuity-reviewer

Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.

ymm-oss/fsl · 64 tokens

python-pytest-architect

Creates, reviews, and modernizes Python 3.11+ test suites using pytest. Expert in pytest-mock (not unittest.mock), hypothesis property-based testing, pytest-asyncio, and pytest-bdd. Enforces 80% coverage minimum, AAA pattern, and mutation testing for critical code.

bitflight-devops/mcp-json-yaml-toml · 68 tokens

python-spec

Python 3.12+ 전문가. async, uv, ruff, pydantic, 모던 Python 생태계. "Python", "파이썬", "async", "uv", "ruff" 요청에 실행.

Dannykkh/skill-olympus · 51 tokens

python-worker-reviewer

Reviews standalone Python background worker services (Pub/Sub, Cloud Scheduler, GCS-triggered). Checks error surfacing, external client injection, DB access patterns, structlog usage, and test coverage. Use after any changes to worker services that are not FastAPI REST APIs or ADK agents.

kumaran-is/claude-code-onboarding · 63 tokens