Setup & Installation
openclaw skills install @pestafford/credence
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install credence
What This Skill Does
Checks MCP servers and AI tools against the Credence trust registry before installation. Looks up a trust score (0-100), a verdict (Approved, Conditional, Flagged, Rejected), and scan metadata. If a tool isn't in the registry, the user can submit it for scanning.
When to use it
- Verifying an MCP server's trust score before installing it
- Checking whether an unknown AI tool has been scanned for security issues
- Getting a quick safety verdict when someone recommends an MCP server
- Blocking installation of tools flagged with serious concerns
- Submitting unscanned tools to the Credence registry for review
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: "Add the filesystem MCP server"
AGENT
- 1Fetches the Credence registry index from GitHub
- 2Searches for 'modelcontextprotocol/servers/filesystem'
- 3Finds it with score 88 and verdict APPROVED
- 4Reports the score and proceeds with installation
OUTPUT
Credence score: 88/100 (APPROVED). Safe to install.