mcpField
E
Extreme P Value MCP Server

Extreme P Value MCP Server

Local
github.com/koidoScience & Education0Updated 79w ago

About Extreme P Value MCP Server

Extreme P Value MCP Server exposes extreme p-value calculations through an API built with FastMCP. It is for users who need z, t, F, chi-square, SAIGE, or Wald calculations; most functions rely on the `extreme-P.R` script.

Key features

  1. 01Calculate extreme p-values for z, t, F, and chi-square
  2. 02Support SAIGE and Wald calculations
  3. 03Call R functions from Python with pyper
  4. 04Provide a FastMCP API

Use cases

  1. 01Calculate an extreme p-value for a statistical test
  2. 02Use R-backed calculations from Python

MCP support

It exposes extreme p-value calculation functions to MCP clients through a FastMCP server.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Extreme P-value MCP Server

Overview

This MCP server provides an API interface to extreme p-value calculation functions (z, t, F, chi-square, SAIGE) implemented in the R script extreme-P.R, via Python.

  • Strongly depends on the R script extreme-P.R (except for Wald).
  • Uses pyper to call R from Python.
  • The API server is built with FastMCP.
  • extreme_p_helper.py is a 1-to-1 wrapper for the R functions.
  • server.py provides the API endpoints.

Status

🚧 Under Active Development 🚧

This project is under active development. APIs and features may change without notice.

Dependencies

  • uv
  • pyper
  • fastmcp
  • mcp[cli]

Directory structure

+.
├── server.py              # Main FastMCP server
├── extreme_p_helper.py    # R function wrapper
├── extreme-P.R            # R script for extreme p-value calculation (see acknowledgements)
├── pyproject.toml         # Dependencies
└── README.md              # This document

Setup and Running

Add the MCP server to your MCP server list (Claude, Cursor, etc.)
{
    "mcpServers": {
      "ExtremeP": {
        "command": "uv",
        "args": ["--directory", "where you cloned the repo", "run", "server.py"],
        "env": {}
      }
    }
}
Run MCP Inspector
# Install dependencies
uv sync

# Run MCP Inspector
uv --directory ./ run mcp dev server.py
Run the MCP server
# Install dependencies
uv sync

# Run the MCP server
uv run server.py
Example: Using from Python (not running as MCP server)
from extreme_p_helper import ExtremePHelper
helper = ExtremePHelper()
result = helper.pvalue_extreme_z(10)
print(result)  # {'mantissa': ..., 'exponent': ...}

License

This MCP server is released under the Apache License 2.0.

Acknowledgements

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.