$ loading_
Run terminal commands, execute Python, and manage files for local automation.
This tool declares local terminal command execution, Python execution, and file/folder operations, making it a high-privilege general-purpose MCP by design. No remote endpoint or secret requirement is stated, but it comes from a third-party registry with low adoption and unclear maintenance, so cautious use is appropriate.
The materials explicitly state that no keys or environment variables are required, and there is no request for API tokens, account credentials, or other sensitive secrets, so credential exposure appears low.
No remote endpoint is declared in the materials, and the system metadata also lists no remote host. Based on the available facts, there is no explicit data egress path, though actual runtime network behavior should still be constrained because it can execute commands.
The system flags executes-code, and the description explicitly includes running commands and running Python, indicating it can execute local commands/code. This is an inherent high-privilege capability of terminal-style MCPs and warrants restricting usage scope and runtime account privileges.
The description states it can work with files and folders, implying local filesystem read/write or at least file operation capabilities. The materials do not specify directory boundaries, sandboxing, or least-privilege controls, so broad access should be assumed and carefully constrained.
A positive factor is that it is open source and auditable. However, it comes from a third-party registry, the GitHub repo has 0 stars, no declared license, unknown maintenance status, and no README, which limits confidence in verification and ongoing support. There are not enough concrete red flags to rate it as high risk, but supply-chain trust is only moderate.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-pypi" yet — see the docs or source repo.
In the current project directory, run: pwd, ls -la, python --version, and pip list. Then summarize the environment, key dependencies, and any likely issues.
Command outputs plus a concise summary of the environment, notable dependencies, and troubleshooting suggestions.
Read data.csv, use Python to calculate missing values for each column plus mean and median for numeric columns, and save the results to summary.json.
A saved summary file along with a brief explanation of the processing steps and key results.
Scan the reports folder, move all .txt files into a text subfolder and all .csv files into a csv subfolder; create subfolders if needed, then output an organization report.
Files are organized into created subfolders, with a report of moved files and the final folder structure.
Build and manage MCP servers and clients quickly with Python.
Secure file and directory operations for autonomous AI development workflows.
Use one MCP server for filesystem, database, web, and system operations.
Enables secure local development with files, shell, editing, and persistent sessions.
Let AI read, write, search files, and run local commands.
A modular MCP tool for echo, system info, time, math, and file reading.