AgentAvow Trust
by agentavow.com MCP server, indexed and not reviewed
HostedLocalvendor's ownwidely used
Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Facts
- MCP registry
com.agentavow/agentavow-trust· 0.6.5- Endpoint
https://agentavow.com/mcp- Packages
pypiagentavow-trust stdio- PyPI / week
- 1.6k
- Registry entry
- updated 10 Nov 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under agentavow.com, a namespace the registry only gives to whoever proves they control that domain.
- It's in real use: 1,647 PyPI downloads a week.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 8 · about 5,282 tokens of context · checked 19 hours ago
| Tool | What it does | Hint |
|---|---|---|
scan_repoScan a GitHub repo | Is a public GitHub repo safe for an agent to connect to? Returns Safe to connect, Review before you connect, or Do not connect with the reason, a 0-100 trust score, an adoption score, findings with fixes, and a signed… | read-only |
scan_packageScan a package | Scan a published npm, PyPI, crates, Docker or Hugging Face package. Returns Safe to connect, Review before you connect, or Do not connect with the reason, a 0-100 trust score, an adoption score, findings, advisories,… | read-only |
scan_mcp_serverScan an MCP server | Scan a live MCP server's tool definitions for tool poisoning, prompt injection and hidden characters before your agent connects. Returns Safe to connect, Review before you connect, or Do not connect with the reason, a… | read-only |
verify_trustVerify an entity's trust score | Check an AgentAvow entity's trust score (0-1 and 0-100), tier, and whether it meets a minimum. Read-only. Use before working with an unknown agent. Example: {"entity_id": "<uuid from lookup_identity>", "min_trust": 0.5} | read-only |
check_interaction_safetyCheck interaction safety | Is it safe to interact with another agent? Thresholds: delegate 0.6, trade 0.5, collaborate 0.4, follow 0.1. Returns is_safe, risk_level, the score and a recommendation. Read-only. Example: {"target_entity_id":… | read-only |
lookup_identityLook up an agent or tool | Look up an AgentAvow entity by DID or display name. Returns its id, name, type, trust score and tier. Read-only. Example: {"query": "did:web:example.com"} | read-only |
get_trust_badgeGet a trust badge | Get an auto-updating AgentAvow trust badge (SVG) for an entity, with Markdown and HTML to paste. Read-only. Example: {"entity_id": "<uuid>"} | read-only |
about_agentavowAbout AgentAvow | What AgentAvow is, which tool to use when, and how to read a verdict. Call it to get started. Read-only. Example: {} | read-only |
What https://agentavow.com/mcp answered to tools/list, asked without credentials over MCP 2026-07-28. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 0 errors · 1 warning · 1 note
- warnTC11check_interaction_safety1 parameter without a description: interaction_type
- noteTC24server5 of 8 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 5,282 tokens of definitions. Not part of the score yet. Check your own server.