fastmcp

fastmcp is a skill for Claude Code, Codex from metaspartan/cybara. It costs 20 tokens per session (540 once invoked), scanned A, original, MIT.

A skill for building, testing, inspecting, and deploying Python MCP servers with FastMCP. FastMCP is a Python framework for exposing typed tools and data to AI agents.

In plain words
What is it for?
Use it to wrap an API, database, or command-line program as MCP tools, inspect a server, list its tools, call them, or smoke-test an HTTP endpoint.
Why use it?
It provides a defined way to create small, testable server tools and check that local or HTTP-based MCP connections work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to wrap an API, database, or command-line program as MCP tools, inspect a server, list its tools, call them, or smoke-test an HTTP endpoint.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metaspartan/cybara/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.

Any agent
npx skills add metaspartan/cybara --skill fastmcp
Clone the repo
git clone --depth 1 https://github.com/metaspartan/cybara

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaspartan/cybara/fastmcp.svg)](https://agentmods.dev/skills/metaspartan/cybara/fastmcp)
Your own site
<a href="https://agentmods.dev/skills/metaspartan/cybara/fastmcp"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/fastmcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 42
    uvx/uv tool run commands without ==version create a rug-pull risk.
    Fix: Pin the version: uvx package-name==1.2.3
  • medium MCP Rug Pull · line 43
    uvx/uv tool run commands without ==version create a rug-pull risk.
    Fix: Pin the version: uvx package-name==1.2.3
  • medium MCP Rug Pull · line 44
    uvx/uv tool run commands without ==version create a rug-pull risk.
    Fix: Pin the version: uvx package-name==1.2.3
  • medium MCP Rug Pull · line 45
    uvx/uv tool run commands without ==version create a rug-pull risk.
    Fix: Pin the version: uvx package-name==1.2.3
  • medium MCP Rug Pull · line 53
    uvx/uv tool run commands without ==version create a rug-pull risk.
    Fix: Pin the version: uvx package-name==1.2.3
How audits are shown
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 $0.00020 $0.00540
Opus 5 $0.00010 $0.00270
Sonnet 5 $0.00004 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 8d ago against content hash a5330d24c4ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fastmcp 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 8d 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.

skills/fastmcp/SKILL.md · 72 lines

What it actually says

FastMCP

Use this when the user wants to create or test a Python MCP server, wrap an API/database/CLI as MCP tools, expose resources/prompts, or prepare an HTTP MCP endpoint.

Server Shape

Start narrow:

  • 1-3 concrete tools first.
  • Read-only by default.
  • Explicit typed parameters.
  • JSON-safe return values.
  • Clear docstrings; the docstring is the user-facing tool description.

Good tool names: get_customer, search_tickets, describe_table, summarize_file. Weak names: run, process, do_thing.

Minimal Template

from fastmcp import FastMCP

mcp = FastMCP("Example")

@mcp.tool
def echo(text: str) -> dict:
    """Echo text back for smoke testing."""
    return {"text": text}

Local Validation

Prefer isolated runs:

uvx fastmcp version
uvx fastmcp inspect server.py:mcp
uvx fastmcp list server.py --json
uvx fastmcp call server.py echo text=hello --json

If uv is unavailable, use a project virtualenv and install fastmcp there. Do not install global Python packages unless the user asks.

HTTP Transport Smoke

uvx fastmcp run server.py:mcp --transport http --host 127.0.0.1 --port 8000
uvx fastmcp list http://127.0.0.1:8000/mcp --json
uvx fastmcp call http://127.0.0.1:8000/mcp echo text=hello --json

Cybara Integration

Once the server contract is stable:

  1. Add it through Cybara MCP configuration or the MCP UI.
  2. Confirm tools/list returns the expected tool names.
  3. Call at least one real tool through Cybara before declaring integration complete.

Safety

  • Validate paths and URLs before using them.
  • Keep database examples read-only until explicitly approved.
  • Never expose raw shell execution as a general MCP tool.
  • Do not pass secrets as plain parameters unless the MCP client/server contract requires it; prefer env/config.
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. 8d ago First seen · 72 lines · 20 tokens per session scan A a5330d24c4ab

Subscribe to this mod's changes

fastmcp is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 540 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.

Related

Other skills, from other repositories

ecc-api-patterns

Skill "ecc-api-patterns" from KornLabs/truss, covering fastapi patterns, project structure, app factory and lifespan, app/main.py and configuration with pydantic-settings.

KornLabs/truss · 0 tokens

adk-agent-builder

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a…

google/adk-python · 177 tokens

adk-style

Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…

google/adk-python · 187 tokens

adk-verify-snippets

Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…

google/adk-python · 149 tokens

adk-setup

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…

google/adk-python · 146 tokens

python-lib-analyzer

Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.

shibing624/agentica · 23 tokens