mcpbeat Sign in

skillkit MCP Server

local only

skillkit runs on your own machine — the client starts it, so there is no endpoint to ping. 66 installs a week from pypi. Last commit 29 Aug 2026.

Toolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills

Installs per day peak 29 · avg 10 · -20% w/w
a month agotoday
66
Installs / week
pypi · skillkit-cli
0
Stars
0 open issues
29 Aug 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 3 d ago · rules ccca72095570

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add skillkit -- uvx skillkit-cli
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "skillkit": {
      "args": [
        "skillkit-cli"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.skillkit]
command = "uvx"
args = ["skillkit-cli"]
.cursor/mcp.json
{
  "mcpServers": {
    "skillkit": {
      "args": [
        "skillkit-cli"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "skillkit": {
      "args": [
        "skillkit-cli"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to skillkit

same job, measured the same way
Skillmd
by skillmd

Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.

211 installs/wk 5 tools answering
Skill Me
by skillme

Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.

answering
SKILL.md Lint
by moltlinestudio

Lint a SKILL.md for frontmatter, structure, secrets and size. All 6 tools free.

6 tools answering
Modelbound MCP
by modelbound

Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.

426 installs/wk local only
Secureflows MCP Server
by michal-lefler

MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

18 tools answering
Secureflows MCP
by michal-lefler

MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

18 tools answering
Toolfactory
by goatinahat

Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex

636 installs/wk local only
The Agent Forge
by theagentforge

Check skills, MCP servers and APIs against field reports from human-verified AI agents.

answering

skillkit — questions

Answers built from our own checks of this server.

Why is there no uptime for skillkit?
skillkit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package skillkit-cli was installed 66 times last week.
How do I connect skillkit?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls skillkit-cli straight from pypi; nothing to host, nothing to sign up for.
How many people use skillkit?
The pypi package skillkit-cli was installed 66 times in the last week. Week over week that is -20%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is skillkit open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.