python-mcp-server

DeadMeme5441/python-mcp-server

3.1

If you are the rightful owner of python-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

A FastMCP-based Model Context Protocol (MCP) server designed for data analysis with a persistent Jupyter kernel.

Tools

Functions exposed to the LLM to take actions

run_python_code

Executes Python code and captures stdout, stderr, results, outputs, and new files.

code_completion

Provides Jupyter-style code completion.

inspect_object

Inspects objects in the code for detailed information.

list_files

Lists files in a directory with options for recursive and tree views.

read_file

Reads a file and returns its content.

write_file

Writes content to a specified file.

delete_file

Deletes a specified file.

save_script

Saves a script to the scripts directory.

run_script

Runs a saved script and captures its output.

install_dependencies

Installs specified Python dependencies.

list_variables

Lists all variables in the current session.

restart_kernel

Restarts the Jupyter kernel.

get_workspace_info

Provides information about the current workspace.

ping

Checks the server status.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources