Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
1–24 of 187 tools for “command-line-utilities”
Clear allToken-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.
SkillMIT★ 116No key
An MCP server that wraps the hackrf_tools command-line utilities, letting AI assistants inspect and control a connected HackRF software-defined radio.
PythonMIT★ 2Few starsNo key
open source CLI to control Anythink from the command line
Hosted by authorMIT★ 6No key
Rust MCP server giving AI agents filesystem superpowers: view, edit, batch-edit, shell and workdir tools with hash-verified line ids, gitignore-aware search, and transparent SSH/SFTP
SkillApache-2.0★ 16No key
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the
OfficialSkillApache-2.0★ 11k in collectionNo key
Open-source Rust agent engine and terminal client for Codewhale, with provider choice, tools, approvals and receipts.
SkillMIT★ 41kNo key
Democratizing AI scientists with ToolUniverse
PythonApache-2.0★ 1.7kNo key
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section.
PythonMIT★ 1.2kNo key
Install, run and deploy your own decentralized AI agent service
SkillGPL-3.0★ 5.0kNo key
PythonApache-2.0★ 226No key
Avrotize is a command-line tool for converting data structure definitions between different schema formats, using Apache Avro Schema as the integration schema model.
PythonApache-2.0★ 132No key
A tool to produce a map of a codebase within a git repository. Based entirely on the "Repo Map" functionality in Aider.chat
PythonMIT★ 217No key
Control plane for the tools agents run: inventory, evidence, policy, enforcement. Clean is only emitted when every check ran. · agent 工具层的控制面:清单、证据、策略、执行;只有每个检查都跑完,才会给出 clean。
Node.jsAGPL-3.0★ 102No key
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
SkillMIT★ 777No key
MedMCP: An Open Agentic Ecosystem for Medical Imaging Workflows
PythonApache-2.0★ 42No key
PythonMIT★ 10No key
Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools
SkillMIT★ 82No key
PythonMIT★ 39Needs a key
Powerful MCP debugging proxy and CLI inspection tool.
Node.jsMIT★ 125No key
Who stands behind it