Skip to main content
Glama
Sign In
MCP Server

MCP Server

by zchaffee1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

mcp-server

By: Zack Chaffee A20478873

A server implementing Model Coupling Protocol (MCP) capabilities for HDF5 file operations and Slurm job management.

Features

HDF5 file operations:

  • Read datasets

  • List file contents

Slurm job management:

  • Submit jobs

  • Check job status

Node Hardware Operations

  • Get CPU information

  • Get memory information

  • Get disk information

  • Get comprehensive system information

Compression Operations

  • Compress string data with gzip or zlib

  • Compress files with gzip or zlib

  • Decompress data

Initialization

Once you clone this reponsitory cd into it

After this hwe will create a virtual enviornment and install all dependincies:

uv venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .
uv pip install -e ".[test]"

Running

To startup the server run:

python -m src.server

This will autoclocate the server at http://localhost:8000.

Related MCP server: MCP Server

Endpoints

  • POST /mcp: Main endpoint for MCP requests

  • GET /health: Health check endpoint

Examples:

import httpx

async with httpx.AsyncClient() as client:
    # Read a dataset
    response = await client.post("http://localhost:8000/mcp", json={
        "capability": "hdf5",
        "action": "read_dataset",
        "parameters": {
            "file_path": "/path/to/data.h5",
            "dataset_path": "/path/to/dataset"
        }
    })
    
    # List contents
    response = await client.post("http://localhost:8000/mcp", json={
        "capability": "hdf5",
        "action": "list_contents",
        "parameters": {
            "file_path": "/path/to/data.h5",
            "group_path": "/"
        }
    })
curl -X POST http://localhost:8000/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "mcp/listTools", 
    "params": {}, 
    "id": "1"
  }'

Testing

For testing rung: 

pytest

For tests with coverage:

pytest --cov=src

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server

    jalzoubi
    F
    license
    Not graded
    quality
    D
    maintenance
    A JSON-RPC 2.0 compliant server that enables interaction with HDF5 data files and Slurm job scheduling through standardized API endpoints.
    -

  • HPC-MCP

    TomMelt
    A
    license
    B
    quality
    D
    maintenance
    A server that provides Model Control Protocol (MCP) tools for High Performance Computing, designed to integrate with Large Language Models in IDEs like Cursor and VSCode for debugging and other HPC tasks.
    1
    3
    MIT

  • jlab-mcp

    kdkyum
    F
    license
    A
    quality
    C
    maintenance
    An MCP server that enables LLMs to execute Python code on GPU-accelerated compute nodes within SLURM-managed HPC environments. It bridges local clients to remote clusters by launching JupyterLab sessions via SLURM jobs to facilitate high-performance notebook-based computation.
    7
    -

Appeared in Searches