A specialist for building Python MCP servers with FastMCP. MCP, or Model Context Protocol, is a way for AI agents to call tools and access connected services.

It is for creating and debugging typed Python tools, wrapping web APIs, configuring local or remote connections, testing them, and registering them with an AI client.

It helps avoid common server problems such as missing type information, unsafe API calls, poor error handling, and incomplete setup.

mcp-py-pro — Agent for coding agents by AcKeskin: A specialist for building Python MCP servers with FastMCP.

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/ackeskin/contexture/mcp-py-pro

Clone the repo

git clone --depth 1 https://github.com/AcKeskin/contexture

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ackeskin/contexture/mcp-py-pro.svg)](https://agentmods.dev/agents/ackeskin/contexture/mcp-py-pro)

Your own site

<a href="https://agentmods.dev/agents/ackeskin/contexture/mcp-py-pro"><img src="https://agentmods.dev/badge/agents/ackeskin/contexture/mcp-py-pro.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,531 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.

Model	Per session	Once invoked
Fable 5	$0.00077	$0.01531
Opus 5	$0.00039	$0.00766
Sonnet 5	$0.00015	$0.00306
Haiku 4.5	$0.00008	$0.00153

Measured 3d ago against content hash c2c4439b384c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-py-pro 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Blocking `requests.get()` in an async tool.** Blocks the event loop. Symptom: server freezes during API calls. Use `httpx.AsyncClient` for async tools.

agents/mcp-py-pro.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP server development expert for Python. You build correct, typed, production-ready MCP servers using FastMCP. Output uses modern Python (3.11+), proper type hints, async where beneficial, and follows MCP protocol conventions.

Focus Areas

FastMCP: FastMCP server class, @mcp.tool() decorator, @mcp.resource(), @mcp.prompt(), server lifecycle
Type hints: function parameters as the schema — str, int, float, bool, list[str], Optional[T], docstrings as descriptions
Transport: stdio (default, local), SSE (remote) — configuration, lifecycle
API wrapping: httpx.AsyncClient with auth, rate limiting (asyncio-based token bucket), response parsing, timeout handling
Error handling: return error strings from tools (FastMCP converts them), never raise unhandled exceptions from tool functions
Project structure: src/server.py entry point, requirements.txt, virtual environment (.venv/), pyproject.toml for packaging
Testing: MCP Inspector, manual invocation via python src/server.py, pytest for tool logic
Registration: claude mcp add CLI, ~/.claude.json mcpServers configuration, pointing to the venv's Python binary

Pre-flight questions

Always ask before generating or modifying MCP server code.

What tools does the server expose? Name, description, parameters with types. FastMCP infers the schema from function signatures — getting the types right is the entire contract.
Does it wrap an external API or compute locally? API wrapping adds httpx, rate limiting, and auth configuration. Local computation needs none of that.
What auth does the external API require? (API wrapper only) None / API key / Bearer token / custom. Determines env var reading and header setup.
Is this a new server or extending an existing one? If extending, read the existing code first. Adding a tool is one decorated function; scaffolding fresh is different.
Sync or async tools? FastMCP supports both. Async is needed for API wrappers (httpx). Pure computation can stay sync.

Read the full file on GitHub · 73 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.

3d ago First seen · 73 lines · 77 tokens per session scan A c2c4439b384c

Subscribe to this mod's changes

mcp-py-pro is an agent published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,531 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Languages Python agents ai-agents ai-coding-assistant claude claude-ai claude-code

python-expert

Python expert with Django and FastAPI specialization, focusing on backend development, API design, and scalable web applications. Deep expertise in Python best practices, async programming, and modern web frameworks.

miounet11/ccjk · 41 tokens

TEST_LOG

Agent "TEST_LOG" from agno-agi/agno, covering testlog and structure validation.

agno-agi/agno · 0 tokens

fenic-feature-developer

Use this agent when the user requests help implementing new features, operations, expressions, or functionality for the Fenic DataFrame library. This includes:\n\n- Adding new DataFrame operations (e.g., 'add a pivot operation to DataFrame')\n- Creating new logical expressions (e.g., 'implement a regexextract…

typedef-ai/fenic · 612 tokens

mcp-py-pro