1. Conduid
  2. Developer Tools
  3. Fake Py MCP
MCP server · Developer Tools

Fake Py MCP

fake.py meets MCP

Unclaimed MIT last commit 8 months ago fake-pydevtoolsmcp
56Fair

Scored just now · breakdown

About Fake Py MCP

Fake Py MCP is an MCP server published by barseghyanartur in the Developer Tools category: fake.py meets MCP. It has been installed 0 times through Conduid.

Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.

Install

Install
npx fake-py-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Fake Py MCP

Powered by Claude · Grounded in docs

I know everything about Fake Py MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

0.30.3
0.2.40.2.4
0.2.30.2.3
0.2.20.2.2
0.2.10.2.1

README

=========== fake-py-mcp

.. External references

.. _fake.py: https://github.com/barseghyanartur/fake.py .. _MCP Inspector: https://github.com/modelcontextprotocol/inspector .. _mcpo: https://github.com/open-webui/mcpo

.. Internal references

.. _Read the Docs: http://fake-py-mcp.readthedocs.io/ .. _Contributor guidelines: https://fakepy.readthedocs.io/en/latest/contributor_guidelines.html .. _llms.txt: https://fake-py-mcp.readthedocs.io/en/latest/llms.txt

This project exposes all Faker class methods from fake.py_ as MCP tools using FastMCP 2.0.

.. image:: https://img.shields.io/pypi/v/fake-py-mcp.svg :target: https://pypi.python.org/pypi/fake-py-mcp :alt: PyPI Version

.. image:: https://img.shields.io/pypi/pyversions/fake-py-mcp.svg :target: https://pypi.python.org/pypi/fake-py-mcp/ :alt: Supported Python versions

.. image:: https://github.com/barseghyanartur/fake-py-mcp/actions/workflows/test.yml/badge.svg?branch=main :target: https://github.com/barseghyanartur/fake-py-mcp/actions :alt: Build Status

.. image:: https://readthedocs.org/projects/fake-py-mcp/badge/?version=latest :target: http://fake-py-mcp.readthedocs.io :alt: Documentation Status

.. image:: https://img.shields.io/badge/docs-llms.txt-blue :target: https://fake-py-mcp.readthedocs.io/en/latest/llms.txt :alt: llms.txt - documentation for LLMs

.. image:: https://img.shields.io/badge/license-MIT-blue.svg :target: https://github.com/barseghyanartur/fake-py-mcp/#License :alt: MIT

.. image:: https://coveralls.io/repos/github/barseghyanartur/fake-py-mcp/badge.svg?branch=main&service=github :target: https://coveralls.io/github/barseghyanartur/fake-py-mcp?branch=main :alt: Coverage

Purpose

It's easy for a model to look smart "on paper", but real-world work requires following strict technical rules.

This MCP server provides a wide range of complex, "fake" tools to test how well a model actually follows instructions. By asking a model to generate data for these tools, you can see if it:

#. Uses the exact parameters required (no more, no less). #. Provides the correct data types and formats. #. Understands complex technical requirements without making mistakes.

If a model can accurately handle these fake tools, you can trust it to handle your real production tools. It's a simple way to find out which models are actually ready for work.

Features

  • 80+ fake.py_ fake data methods (names, text, internet, files, primitives, dates, geo, books, banking, file content), dynamically registered (no manual boilerplate), categorised and documented.
  • Binary outputs (e.g., images, PDFs) are returned as base64-encoded strings.
  • server_info tool for introspection.

Prerequisites

Python 3.10+

Installation

.. code-block:: sh

  uv tool install fake-py-mcp

Usage

Run the server

STDIO


   .. code-block:: sh

      fake-py-mcp

HTTP
~~~~

   .. code-block:: sh

      fake-py-mcp http

SSE
~~~

   .. code-block:: sh

      fake-py-mcp sse

Connect with any MCP client to access all fake.py tools
-------------------------------------------------------
Developers need good tools. Unfortunately, FastMCP does not come with a
GUI (like OpenAPI/Swagger), but there are good tools available.

Option 1: MCP Inspector

Installation

.. code-block:: sh

brew install mcp-inspector

Usage

Run MCP Inspector_ on port 8006:

.. code-block:: sh

CLIENT_PORT=8006 mcp-inspector fake-py-mcp

Or if you prefer no-auth option:

.. code-block:: sh

DANGEROUSLY_OMIT_AUTH=true CLIENT_PORT=8006 mcp-inspector fake-py-mcp

Open http://127.0.0.1:8006 and enjoy the MCP Inspector_ interface.

Option 2: mcpo

**Installation**

.. code-block:: sh

   uv tool install mcpo

**Usage**

Run `mcpo`_ on port 8006:

.. code-block:: sh

   mcpo --port 8006 -- fake-py-mcp

Open http://127.0.0.1:8006/docs and enjoy OpenAPI Swagger comfort.

Documentation
=============
- Documentation is available on `Read the Docs`_.

Tests
=====

Run the tests:

.. code-block:: sh

    pytest

Writing documentation
=====================

Keep the following hierarchy.

.. code-block:: text

    =====
    title
    =====

    header
    ======

    sub-header
    ----------

    sub-sub-header
    ~~~~~~~~~~~~~~

    sub-sub-sub-header
    ^^^^^^^^^^^^^^^^^^

    sub-sub-sub-sub-header
    ++++++++++++++++++++++

    sub-sub-sub-sub-sub-header
    **************************

License
=======

MIT

Support
=======
For security issues contact me at the e-mail given in the `Author`_ section.

For overall issues, go to `GitHub <https://github.com/barseghyanartur/fake-py-mcp/issues>`_.

Author
======

Artur Barseghyan <artur.barseghyan@gmail.com>

README mirrored from the source repository just now. The original is authoritative.

Questions

About Fake Py MCP

How do I install Fake Py MCP?

Run npx fake-py-mcp, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Fake Py MCP safe to use with an AI agent?

Its trust score is 56 out of 100 (fair). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Fake Py MCP still maintained?

The last commit was 8 months ago, with 0 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.