
MCP Servers Collection
from geoffjay
A collection of MCP servers providing structured interfaces for AI assistants to interact with various development tools and services.
โ labsco summary โ our analysis, not the vendor's
What it is โ A small collection of MCP servers by one author, currently an Overmind process-manager server and a Finnhub-backed fundamental-analysis server.
What you get โ
- Overmind server: start/stop/restart Procfile processes and check health โ
overmind_start,overmind_status,overmind_restart,overmind_run,overmind_check_procfile, and more - Process introspection:
overmind_find_procfiles,overmind_is_running,overmind_connectfor connection instructions - Fundamental Analysis server: "run fundamental analysis for AAPL" using the Finnhub API
- Each server installs standalone via
uvx --from git+...
Requirements โ for Overmind: Overmind and tmux installed on the host; for Fundamental Analysis: a Finnhub API account/key (free signup at finnhub.io).
Cost snapshot โ free and MIT-licensed; the Overmind server needs no paid service, but the analysis server depends on the third-party Finnhub API (account required; Finnhub has free and paid tiers).
Setup effort โ per-server uvx --from git+https://... one-liners; Overmind also needs tmux/Overmind pre-installed.
Our take โ Useful if you run Procfile apps and want AI-driven process control, but it's really two unrelated tools bundled together, and the Overmind piece only works on systems with tmux + Overmind installed.
Source: the project README โ summarized 2026-07-08.
โ readme from github โ mirrored (latest on GitHub โ)
MCP Servers Collection
A collection of Model Context Protocol (MCP) servers for enhancing AI tooling capabilities. These servers provide structured interfaces for AI assistants to interact with various development tools and services.
What is MCP?
The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external data sources and tools. MCP servers expose specific functionality as tools that AI assistants can discover and use.
Available Servers
๐ Overmind Server
Path: overmind/
Purpose: Process management for Procfile-based applications using Overmind
Installation:
uvx --from git+https://github.com/geoffjay/mcp-servers#subdirectory=overmind mcp-server-overmind๐ Fundamental Analysis Server
Path: fundamental_analysis/
Purpose: Performs fundamental analysis for a given stock code using the Finnhub API.
Installation:
uvx --from git+https://github.com/geoffjay/mcp-servers#subdirectory=fundamental_analysis mcp-server-fundamental-analysisKey Features:
- Start, stop, and restart processes defined in Procfiles
- Monitor process status and health
- Execute commands within the Overmind environment
- Socket-based detection of running instances
- Support for custom Procfile locations and formations
Tools Available:
overmind_start- Start Overmind with optional configurationovermind_stop- Stop specific processes or all processesovermind_restart- Restart specified processesovermind_status- Get status of all processesovermind_quit- Gracefully quit Overmindovermind_kill- Forcefully kill all processesovermind_run- Run commands in Overmind environmentovermind_connect- Get connection instructions for processesovermind_is_running- Check if Overmind is runningovermind_check_procfile- Validate Procfile existence and contentsovermind_find_procfiles- Find all Procfiles in a directory tree
Requirements: Overmind and tmux must be installed on the system.
Testing: The overmind/test_environment/ directory contains a complete test setup with sample processes and testing utilities. Run ./overmind/test_environment/run_tests.sh for comprehensive testing.
Development
Prerequisites
- Python 3.10 or higher
- uv for dependency management
- direnv (optional, for automatic environment activation)
Project Structure
mcp-servers/
โโโ README.md # This file
โโโ overmind/ # Overmind process manager server
โ โโโ src/mcp_server_overmind/
โ โโโ tests/
โ โโโ pyproject.toml
โ โโโ .envrc
โ โโโ README.md
โโโ [future-servers]/ # Additional servers will be added hereAdding a New Server
- Create a new directory for your server
- Set up the project structure:
your-server/ โโโ src/mcp_server_yourname/ โ โโโ __init__.py โ โโโ server.py โโโ tests/ โโโ pyproject.toml โโโ .envrc โโโ README.md - Configure
pyproject.tomlwith:- Package name:
mcp-server-yourname - Entry point:
mcp-server-yourname = "mcp_server_yourname.server:main" - Dependencies including
mcp>=1.2.0
- Package name:
- Implement your server using the FastMCP framework
- Add comprehensive tests
- Document your server in its README.md
- Update this main README.md to include your server
Running Tests
Each server includes its own test suite:
cd your-server-directory
uv run --extra dev pytest tests/ -vBuilding and Testing Locally
cd your-server-directory
uv build
uv run your-entry-pointResources
Support
For issues with specific servers, please refer to their individual README files. For general project issues or questions, please open an issue in this repository.
Server Status
| Server | Status | Version | Last Updated |
|---|---|---|---|
| overmind | โ Stable | 0.1.0 | January 2025 |
| fundamental_analysis | โ Stable | 0.1.0 | January 2025 |
Roadmap
Future servers under consideration:
- Development environment setup
- Audio processing (MIDI/OSC)
{
"mcpServers": {
"overmind": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/geoffjay/mcp-servers#subdirectory=overmind",
"mcp-server-overmind"
]
}
}
}Quick Start
Using with Claude Desktop
Add any of these servers to your Claude Desktop configuration:
{
"mcpServers": {
"overmind": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/geoffjay/mcp-servers#subdirectory=overmind",
"mcp-server-overmind"
]
}
}
}Using with Other MCP Clients
Each server can be executed directly:
# Overmind server
uvx --from git+https://github.com/geoffjay/mcp-servers#subdirectory=overmind mcp-server-overmindNo common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.
Licensed under MITโ you can use, modify, and redistribute it under that license's terms.
License
This project is licensed under the MIT License. See individual server directories for specific license information.