Skip to main content

Simple MCP Server Collection, Packaged

Project description

mcp_servers

A collection of MCP servers

Disclaimer

This project is created for personal use and does not guarantee stable behavior. It is made public solely as a reference for other programmers. The project is highly unstable, premature, and may produce undesired outcomes, so use it at your own risk.

Development Setup

git clone git@github.com:assagman/mcp_servers.git

cd mcp_servers

uv venv --python 3.12 && source .venv/bin/activate

uv sync --extra dev

Examples

All LLM models are used from openrouter.ai, so on OPENROUTER_API_KEY env var is mandatory for this project to interact with a LLM model.

cp ./examples/.env.example ./examples/.env then set your OPENROUTER_API_KEY in ./examples/.env. In these examples google/gemini-2.5-flash-preview is picked as the LLM model since it's the best fit model for this workflow I experienced. You need to buy credits on https://openrouter.ai/settings/credits to experiment. Even some free alternatives can work sometimes, but either they do not produce consistent outputs or there are some problems with thi hosting server like rate limits or unavailability. Make sure you select models with tools usage. Generally Google and OpenAI models, even with smaller/cheaper ones, works well.

Example usage: as a package in client code

python examples/run_filesystem_agent.py

without making any changes, this command should be executed successfully as is, and it'll operate on a temporary directory.

Example usage: as a separate, dedicated MCP server

mcpserver start --server filesystem --port 8765 --allowed-dir $(pwd) --detach

Above command should start MCP server for filesystem in the background process. ps aux | rg mcpserver is expected to show this related process.

python examples/run_filesystem_agent_2.py

after some experimentation, please run:

mcpserver stop --server filesystem

This specific example uses CLI app utility to start/stop MCP seperately from the client code (different from the first example).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_servers-0.1.0.tar.gz (20.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_servers-0.1.0-py3-none-any.whl (33.6 kB view details)

Uploaded Python 3

File details

Details for the file mcp_servers-0.1.0.tar.gz.

File metadata

  • Download URL: mcp_servers-0.1.0.tar.gz
  • Upload date:
  • Size: 20.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.10

File hashes

Hashes for mcp_servers-0.1.0.tar.gz
Algorithm Hash digest
SHA256 42c4be8d84883660ec3f16afe62f7b8c7a7528b086de638ca9a9028bd9bf693b
MD5 69442c91b393b06463c9871aaf3f665a
BLAKE2b-256 24f779b937217efe90eba4ba3287764023e2c91bc0ecae9c34437dc7b4b3fd05

See more details on using hashes here.

File details

Details for the file mcp_servers-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: mcp_servers-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 33.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.10

File hashes

Hashes for mcp_servers-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 251b31355a543b8ee076cce84e4d596fa7cd777038621fc6a44ce2399513a07d
MD5 0a59d55b52469f79cdfde26fc3978e9e
BLAKE2b-256 d6a6036c5723d4895e7bc0bcfc293c4b40af43f3ab9c8c0026bcdfc9b33f25d6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page