AgentAvow Trust

AgentAvow scans any MCP server, package (npm/PyPI/crates/Docker/Hugging Face), or GitHub repo and returns a signed, offline-recomputable 0–100 trust score…

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Scan Repo: Scan a public GitHub repository with AgentAvow and return whether it is safe for an agent to connect to: a 0-100 trust score, a plain safe / needs-review verdict, the findings behind it (wi
  • Scan Package: Scan a published package (npm, PyPI, crates, Docker, or Hugging Face) with AgentAvow. Returns a 0-100 trust score, a safe / needs-review verdict, findings with remediation, and a signed
  • 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. Returns a 0-100 trust

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

AgentAvow scans any MCP server, package (npm/PyPI/crates/Docker/Hugging Face), or GitHub repo and returns a signed, offline-recomputable 0–100 trust score with a plain safe / needs-review verdict. Authless and read-only — no account.

Eight tools: scan_repo, scan_package, scan_mcp_server, verify_trust, check_interaction_safety, lookup_identity, get_trust_badge, about_agentavow. Every result links to a full report and an Ed25519/JWS attestation you can verify offline.

Список инструментов сервера (8)

Технические названия из tools/list. Нужны только разработчикам.

scan_repoScan a public GitHub repository with AgentAvow and return whether it is safe for an agent to connect to: a 0-100 trust score, a plain safe / needs-review verdict, the findings behind it (with where and how to fix), and a signed, offline-verifiable attestation. Read-only, no account. Calls the AgentAvow public API at agentavow.com.
scan_packageScan a published package (npm, PyPI, crates, Docker, or Hugging Face) with AgentAvow. Returns a 0-100 trust score, a safe / needs-review verdict, findings with remediation, and a signed attestation. Also reports repo-vs-artifact drift (files shipped that aren't in the source). Read-only; calls agentavow.com.
scan_mcp_serverScan a live MCP server's tool definitions for tool-poisoning, prompt-injection, invisible-unicode, and manifest-execution risks before your agent connects to it. Returns a 0-100 trust score, a safe / needs-review verdict, findings, and a signed attestation. Read-only; calls the agentavow.com public API.
verify_trustVerify 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, no auth. Use before interacting with an unknown agent.
check_interaction_safetyCheck 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, risk_level, the score, and a recommendation. Read-only, no auth.
lookup_identityLook 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 identity before checking its trust.
get_trust_badgeGet 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 auth.
about_agentavowWhat 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.