com.agentavow/agentavow-trust

up checked 2026-11-11T03:38:04.368Z

Unclaimed · Unverified

Publisher-provided title

AgentAvow Trust

Publisher-provided description

Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to

Summary by lookupd

Scores and verifies safety of MCP servers, packages, repos, and agents before connecting; returns trust verdicts and embeddable badges.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http agentavow-trust https://agentavow.com/mcp

Claude Code, pypi package (stdio)

claude mcp add agentavow-trust -- uvx agentavow-trust

Codex, remote (streamable-http)

codex mcp add agentavow-trust --url https://agentavow.com/mcp

Codex, pypi package (stdio)

codex mcp add agentavow-trust -- uvx agentavow-trust

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "agentavow-trust": {
      "url": "https://agentavow.com/mcp"
    }
  }
}

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "agentavow-trust": {
      "command": "uvx",
      "args": [
        "agentavow-trust"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

scan_repo Scan a public GitHub repository with AgentAvow and return whether it is safe for an agent to connect to: one of three answers with its reason (Safe to connect,
scan_package Scan a published package (npm, PyPI, crates, Docker, or Hugging Face) with AgentAvow. Returns one of three answers with its reason (Safe to connect, Review befo
scan_mcp_server Scan a live MCP server's tool definitions for tool-poisoning, prompt-injection, invisible-unicode, and manifest-execution risks before your agent connects to it
verify_trust Verify an AgentAvow entity's trust score. Returns trust_score (0-1), trust_score_pct (0-100), trust_tier, and whether it meets a minimum threshold. Read-only, n
check_interaction_safety Check whether it is safe to interact with another agent by trust threshold. Thresholds: delegate 0.6, trade 0.5, collaborate 0.4, follow 0.1. Returns is_safe, r
lookup_identity Look up an AgentAvow entity by W3C DID or display name. Returns the entity's id, name, type, trust score and tier. Read-only, no auth. Use to resolve an identit
get_trust_badge Get an embeddable AgentAvow trust badge (SVG) for an entity, with ready-to-paste Markdown and HTML. The badge auto-updates as the score changes. Read-only, no a
about_agentavow What AgentAvow is, which tool to use for what, how to read a verdict, and example scans. Call this for an overview or when getting started. No input, read-only.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.agentavow/agentavow-trust.svg)](https://lookupd.com/servers/com.agentavow/agentavow-trust)