Openclaw Skill Vetter MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 201 installs a week from pypi.
Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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.
claude mcp add openclaw-skill-vetter-mcp -- uvx openclaw-skill-vetter-mcp
{
"mcpServers": {
"openclaw-skill-vetter-mcp": {
"args": [
"openclaw-skill-vetter-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.openclaw-skill-vetter-mcp]
command = "uvx"
args = ["openclaw-skill-vetter-mcp"]
{
"mcpServers": {
"openclaw-skill-vetter-mcp": {
"args": [
"openclaw-skill-vetter-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"openclaw-skill-vetter-mcp": {
"args": [
"openclaw-skill-vetter-mcp"
],
"command": "uvx"
}
}
}
Research-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules).
Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
Normalize AGENTS.md / CLAUDE.md / .cursor/rules / .clinerules / .windsurf/rules from one source.
OzBridge: run Warp Oz agents from any MCP client — Claude Code, Cursor, Codex, VS Code.
Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
Answers built from our own checks of this server.