Combien d'outils expose com.agentavow/agentavow-trust ?

com.agentavow/agentavow-trust expose 8 outil(s). Le coût de contexte pour les charger tous est d'environ 4724 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Dev & Code / com.agentavow/agentavow-trust

com.agentavow/agentavow-trust

serveur MCP (Model Context Protocol) · agentavow-trust 0.16.0

▸ Dev & Code

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~4724 tokensCoût de contexte

8Outils

Est-ce que com.agentavow/agentavow-trust est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.agentavow/agentavow-trust » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 8 outils

about_agentavow≈ 107 tokens
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.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "about_agentavow", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
check_interaction_safety≈ 203 tokens
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, risk_level, the score, and a recommendation. Read-only, no auth.
Paramètres, retour & exemple (2)
Paramètres
- interaction_type · string · requis · delegate | trade | collaborate | follow
- target_entity_id · string · requis
  UUID of a registered target entity (resolve one with lookup_identity).
Exemple d'appel
```
{"name": "check_interaction_safety", "arguments": {"interaction_type": "delegate", "target_entity_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_trust_badge≈ 150 tokens
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 auth.
Paramètres, retour & exemple (1)
Paramètres
- entity_id · string · requis
  UUID of a registered AgentAvow entity (resolve one with lookup_identity).
Exemple d'appel
```
{"name": "get_trust_badge", "arguments": {"entity_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
lookup_identity≈ 157 tokens
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 identity before checking its trust.
Paramètres, retour & exemple (1)
Paramètres
- query · string · requis
  A did:web:... or a display name.
Exemple d'appel
```
{"name": "lookup_identity", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
scan_mcp_server≈ 1302 tokens
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 one of three answers with its reason (Safe to connect, Review before you connect, or Do not connect), a 0-100 trust score, findings, and a signed attestation. Read-only; calls the agentavow.com public API.
Paramètres, retour & exemple (2)
Paramètres
- force · boolean · optionnel
  Re-scan now instead of returning the cached verdict (results cache ~1h).
- endpoint_url · string · requis
  The MCP server's https:// URL.
Exemple d'appel
```
{"name": "scan_mcp_server", "arguments": {"endpoint_url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"high": 1, "tier": "texte", "cached": true, "signed": true, "target": "texte", "install": "texte", "sandbox": {}, "verdict": "safe", "adoption": {}, "critical": 1, "decision": "safe", "incident": {}}}
```
scan_package≈ 1493 tokens
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 before you connect, or Do not connect), a 0-100 trust score, an adoption score from real usage (downloads per week), findings with remediation, and a signed attestation. Also reports published advisories that affect the scanned version, the maintainer's deprecation notice, repo-vs-artifact drift (files shipped that aren't in the source), and AgentAvow's behavioral sandbox results when available. Scans the latest version unless `version` (or a pin in the name) names one. Read-only; calls agentavow.com.
Paramètres, retour & exemple (6)
Paramètres
- name · string · requis
  Package name, e.g. 'chalk' (or 'org/model' for hf).
- force · boolean · optionnel
  Re-scan now instead of returning the cached verdict (results cache ~1h). Use after a new version ships.
- surface · string · optionnel
  Alias for registry.
- version · string · optionnel
  Exact version to scan, e.g. '5.3.0'. Optional: the latest version by default. A pin in the name ('chalk@5.3.0', 'requests==2.32.5') works too.
- registry · string · optionnel
  Package registry: npm, pypi, crates, docker, or hf.
- ecosystem · string · optionnel
  Alias for registry.
Exemple d'appel
```
{"name": "scan_package", "arguments": {"name": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"high": 1, "tier": "texte", "cached": true, "signed": true, "target": "texte", "install": "texte", "sandbox": {}, "verdict": "safe", "adoption": {}, "critical": 1, "decision": "safe", "incident": {}}}
```
scan_repo≈ 1369 tokens
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, Review before you connect, or Do not connect), a 0-100 trust score, an adoption score from real usage (stars), 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.
Paramètres, retour & exemple (3)
Paramètres
- repo · string · requis
  Repo as 'owner/name' (e.g. 'vercel/next.js'), or just the name when 'owner' is given separately.
- force · boolean · optionnel
  Re-scan now instead of returning the cached verdict (results cache ~1h). Use after the target has changed.
- owner · string · optionnel
  Repo owner (optional if 'repo' is already 'owner/name').
Exemple d'appel
```
{"name": "scan_repo", "arguments": {"repo": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"high": 1, "tier": "texte", "cached": true, "signed": true, "target": "texte", "install": "texte", "sandbox": {}, "verdict": "safe", "adoption": {}, "critical": 1, "decision": "safe", "incident": {}}}
```
verify_trust≈ 200 tokens
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, no auth. Use before interacting with an unknown agent.
Paramètres, retour & exemple (2)
Paramètres
- entity_id · string · requis
  UUID of a registered AgentAvow entity (resolve one with lookup_identity; unknown ids return guidance, not an error).
- min_trust · number · optionnel
  Min score, 0-1.
Exemple d'appel
```
{"name": "verify_trust", "arguments": {"entity_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://agentavow.com/mcp