StacklokLabs/model-context-shell
Unix-style pipelines for MCP. Deterministic tool calls.
This project helps AI agents automate multi-step data processing by creating command pipelines. Instead of calling tools one-by-one and managing all intermediate data, agents define a single workflow that takes structured data (like a list of URLs or user profiles) and transforms it using a series of commands, outputting only the final, filtered result. This is for developers building and operating AI agents that need to perform complex data orchestration.
Use this if you are developing AI agents that frequently perform multi-step data processing or make numerous API calls, and you want to reduce context window usage and improve the reliability of complex workflows.
Not ideal if your AI agent only performs simple, single-step tool calls or if you require full, unrestricted shell access for your data transformations.
Stars
19
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/StacklokLabs/model-context-shell"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cfdude/super-shell-mcp
Super Shell MCP
sonirico/mcp-shell
Give hands to AI. MCP server to run shell commands securely, auditably, and on demand.
yaniv-golan/mcp-bash-framework
Portable Bash-only framework for building stdio Model Context Protocol (MCP) servers with zero...
fawdyinc/shellguard
MCP server that gives LLM agents read-only shell access over SSH
codelion/dynamic-shell-server
Dynamic Shell Command MCP Server