Serves as the API framework for the MCP server, providing the endpoints for handling MCP requests and responses.
Hosts the source code repository for the MCP server implementation.
Used for CSV data manipulation and preparation for visualization tools in the MCP server.
Handles data validation and serialization for the MCP API requests and responses.
Provides the testing framework for validating MCP server capabilities and API functionality.
MCP Server Implementation
Name: Esteban Nicolas Student ID: A20593170
I. Implemented MCP Capabilities
1 Data Resources 1.1 HDF5 File Listing
- Lists mock HDF5 files in a directory structure
- Parameters:
path_pattern
(optional file path pattern)
2 Tools 2.1 Slurm Job Submission
- Simulates job submission to a Slurm scheduler
- Parameters:
script_path
(required),cores
(optional, default=1)
2.2 CPU Core Reporting
- Reports number of CPU cores available on the system
- No parameters required
2.3 CSV Visualization
- Plots two columns from a CSV file (defaults to first two columns)
- Parameters:
csv_path
(required),column x
,column y
(both optional)
II. Setup Instructions
- Create virtual environment
uv venv -p python3.10 .venv\Scripts\activate # On Unix: source .venv/bin/activate
- Install dependencies
uv sync uv lock
- Environment configuration The project uses pyproject.toml for dependency management. Key dependencies include:
FastAPI
Uvicorn
Pydantic
Pandas
Matplotlib
Pytest
Pytest-ascyncio
- Running the MCP Server
Start the server cd src uvicorn server --reload
The server will be available at:
API endpoint: http://localhost:8000/mcp Health check: http://localhost:8000/health
III Testing
- Run all tests:
pytest tests/ Run specific test file:
pytest tests/test_capabilities_plot_vis.py pytest tests/test_capabilities_hdf5.py pytest tests/test_capabilities_cpu_core.py pytest tests/test_capabilities_slurm.py pytest tests/test_mcp_handler.py
- Example Requests 2.1 List available resources
curl -X POST http://localhost:8000/mcp
-H "Content-Type: application/json"
-d '{"jsonrpc":"2.0","method":"mcp/listResources","id":1}'
2.2 List HDF5 files
curl -X POST http://localhost:8000/mcp
-H "Content-Type: application/json"
-d '{"jsonrpc":"2.0","method":"mcp/callTool","params":{"tool":"hdf5_file_listing","path_pattern":"/data/sim_run_123"},"id":2}'
2.3 Submit Slurm job
curl -X POST http://localhost:8000/mcp
-H "Content-Type: application/json"
-d '{"jsonrpc":"2.0","method":"mcp/callTool","params":{"tool":"slurm_job_submission","script_path":"/jobs/analysis.sh","cores":4},"id":3}'
2.4 Plot CSV columns
curl -X POST http://localhost:8000/mcp
-H "Content-Type: application/json"
-d '{"jsonrpc":"2.0","method":"mcp/callTool","params":{"tool":"plot_vis_columns","csv_path":"data.csv","column x":"time","column y":"temperature"},"id":4}'
IV Implementation Notes
- Mock Implementations:
-HDF5 file listing uses a simulated directory structure -Slurm job submission generates mock job IDs -CPU core reporting uses os.cpu_count()
- CSV Visualization:
-Creates plots in a plots_results directory -Defaults to first two columns if none specified -Returns path to generated PNG file
- Error Handling:
-Proper JSON-RPC 2.0 error responses -Input validation for all parameters -Graceful handling of missing files/invalid paths
GITHUB: https://github.com/EstebanIIT/cs550_MCP.git
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
A FastAPI-based JSON-RPC 2.0 server implementation that enables users to work with HDF5 files, submit Slurm jobs, retrieve CPU information, and visualize CSV data through standardized API endpoints.
Related MCP Servers
- -securityAlicense-qualityThis server facilitates scalable discovery and execution of OpenAPI endpoints using semantic search and high-performance processing, overcoming limitations of large spec handling for streamlined API interactions.Last updated -68PythonMIT License
- -securityAlicense-qualityA server implementing Model Coupling Protocol for HDF5 file operations, Slurm job management, hardware monitoring, and data compression.Last updated -PythonMIT License
- -securityFlicense-qualityA JSON-RPC 2.0 compliant server that enables interaction with HDF5 data files and Slurm job scheduling through standardized API endpoints.Last updated -Python
- -securityAlicense-qualityA lightweight FastAPI server that allows remote execution of shell commands on Windows, with real-time output streaming and security features like API key authentication and rate limiting.Last updated -1PythonMIT License