Combien d'outils expose io.github.kristof-sudo/agentcrush-app ?

io.github.kristof-sudo/agentcrush-app expose 14 outil(s). Le coût de contexte pour les charger tous est d'environ 4036 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / IA & Mémoire / io.github.kristof-sudo/agentcrush-app

io.github.kristof-sudo/agentcrush-app

serveur MCP (Model Context Protocol) · AgentCrush 1.0.0

▸ IA & Mémoire

[ 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

~4036 tokensCoût de contexte

14Outils

Est-ce que io.github.kristof-sudo/agentcrush-app est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.kristof-sudo/agentcrush-app » 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 14 outils

compare_agents≈ 242 tokens
Compare 2-5 AI agents side-by-side across all their categories. Returns full per-agent scoring data + comparison context. Use for "X vs Y" queries. AgentCrush does not declare a universal winner — comparison shows evidence differences.
Paramètres, retour & exemple (1)
Paramètres
- handles · array · requis
  Array of 2-5 agent handles to compare.
Exemple d'appel
```
{"name": "compare_agents", "arguments": {"handles": []}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"agents": [], "compare_url": "texte"}}
```
find_agents≈ 512 tokens
Counterparty discovery: "which agents can do X and are safe to pay?" Returns the top 3 ranked candidates with liveness (30-day Ghost Index rule), trust tier, verified payment rails (x402/MCP/ERC-8004), scores, and endpoints, plus the total match count. The full ranked list (up to 50) is at https://agentcrush.xyz/api/agents/find/full — $0.05 via x402 on Base, or free with an AgentCrush Pro key.
Paramètres, retour & exemple (5)
Paramètres
- q · string · requis
  Capability keyword (required), e.g. "trading", "wallet risk", "code review".
- alive · boolean · optionnel
  true = only agents alive per the 30-day liveness rule.
- rails · string · optionnel
  Payment rail filter, e.g. "x402".
- category · string · optionnel · model_family | tokenized | service | developer | mcp_server
  Restrict to one AgentCrush category.
- min_tier · string · optionnel · evidence_ranked
  Exclude indexed-only agents.
Exemple d'appel
```
{"name": "find_agents", "arguments": {"q": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "filters": {}, "candidates": [], "full_results": {}, "total_matches": 1}}
```
get_agent_changes≈ 227 tokens
Pairwise delta scan over an agent's recent snapshots. Reports material changes in score, rank, github_stars, follower_count, identity_type, etc. Mirror of GET /api/agent/{handle}/changes.
Paramètres, retour & exemple (3)
Paramètres
- limit · number · optionnel
  Max changes to return (1-100, default 30).
- since · string · optionnel
  ISO date cutoff (default 7 days ago).
- handle · string · requis
  Agent handle slug.
Exemple d'appel
```
{"name": "get_agent_changes", "arguments": {"handle": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"since": "texte", "handle": "texte", "changes": [], "change_count": 1}}
```
get_agent_details≈ 429 tokens
Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer). Returns identity, raw signals, sub-scores, evidence-ready status. Returns fuzzy-match suggestions if the handle is not found — LLMs should use these instead of hallucinating "agent doesn't exist".
Paramètres, retour & exemple (1)
Paramètres
- handle · string · requis
  Agent handle slug (e.g. "qwen", "crewai", "aixbt"). Alphanumeric/hyphen/underscore, max 64 chars.
Exemple d'appel
```
{"name": "get_agent_details", "arguments": {"handle": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"bio": "texte", "name": "texte", "tier": "texte", "error": "texte", "handle": "texte", "scores": {}, "identity": {}, "verified": true, "archetype": "texte", "profile_url": "texte", "suggestions": [], "primary_category": "model_family"}}
```
get_agent_history≈ 258 tokens
Get rank and score history for an AI agent over the past 1–90 days. Daily snapshots, deduplicated per calendar day. Returns trend summary (rising/falling/flat). Useful for showing how an agent's standing has evolved.
Paramètres, retour & exemple (2)
Paramètres
- days · number · optionnel
  Days of history to return (1-90, default 30).
- handle · string · requis
  Agent handle slug.
Exemple d'appel
```
{"name": "get_agent_history", "arguments": {"handle": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "handle": "texte", "history": [], "summary": {}, "days_requested": 1, "snapshot_count": 1}}
```
get_agent_trust≈ 286 tokens
Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions. Combines confidence_tier, evidence tier, ERC-8004 verified identity, and risk flags. Mirror of GET /api/agent/{handle}/trust.
Paramètres, retour & exemple (1)
Paramètres
- handle · string · requis
  Agent handle slug.
Exemple d'appel
```
{"name": "get_agent_trust", "arguments": {"handle": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "handle": "texte", "factors": {}, "trust_score": 1, "classification": "verified", "delegation_hint": "texte", "score_breakdown": [], "classification_thresholds": {}}}
```
get_category_ranking≈ 287 tokens
Get the full ranking for one of the 5 categories. Returns agents ordered by composite score with all sub-scores visible. Defaults to evidence-ranked only.
Paramètres, retour & exemple (3)
Paramètres
- limit · number · optionnel
  Max results to return (1-100, default 50).
- category · string · requis · model_family | tokenized | service | developer | mcp_server
  Which of the 4 AgentCrush categories to rank.
- evidence_ready_only · boolean · optionnel
  Filter to evidence-ranked only. Default true.
Exemple d'appel
```
{"name": "get_category_ranking", "arguments": {"category": "model_family"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "ranking": [], "category": "model_family", "methodology_version": "texte"}}
```
get_ecosystem_summary≈ 174 tokens
One-call ecosystem-level summary: counts (total, evidence-ranked, archived), category mix (model_family/tokenized/service/developer/mcp_server), category leaders, snapshot volume last 30 days. Mirror of GET /api/trends/summary.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "get_ecosystem_summary", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"totals": {}, "leaders": {}, "summary": "texte", "category_mix": {}, "snapshot_window": {}}}
```
get_methodology≈ 314 tokens
Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations. **Methodology travels with data**: call this when explaining HOW a ranking works so the LLM can give a methodology-accurate answer instead of guessing.
Paramètres, retour & exemple (1)
Paramètres
- category · string · requis · model_family | tokenized | service | developer | mcp_server
  Which category methodology to retrieve.
Exemple d'appel
```
{"name": "get_methodology", "arguments": {"category": "model_family"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "signals": [], "category": "model_family", "description": "texte", "limitations": [], "methodology_url": "texte", "evidence_ready_rule": "texte", "methodology_version": "texte"}}
```
get_protocol_adoption≈ 204 tokens
How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "get_protocol_adoption", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"adoption": {}, "last_updated": "texte", "total_agents": 1}}
```
get_top_movers≈ 296 tokens
Returns the top weekly rank movers (up + down) computed from agents.weekly_delta. Useful for surfacing notable changes since last week. Default limit 10 per direction.
Paramètres, retour & exemple (3)
Paramètres
- limit · number · optionnel
  Max results per direction (1-25, default 10).
- category · string · optionnel · model_family | tokenized | service | developer | mcp_server
  Restrict to one category.
- direction · string · optionnel · up | down | both
  Movement direction. Default "both".
Exemple d'appel
```
{"name": "get_top_movers", "arguments": {"limit": 1, "category": "model_family", "direction": "up"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"up": [], "down": [], "direction": "texte"}}
```
list_categories≈ 252 tokens
List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions. Use this for market-level discovery — what kinds of agents does AgentCrush track and how many of each?
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "list_categories", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"categories": []}}
```
search_agents≈ 443 tokens
Search AI agents by name or keyword across AgentCrush's evidence-ranked index. Returns matching agents with category, tier, and rank info. Use the `filters` object for structured constraints; future versions will add filter keys without breaking the API.
Paramètres, retour & exemple (2)
Paramètres
- query · string · requis
  Search keyword or partial agent name (1-100 chars).
- filters · object · optionnel
  Optional structured filters.
Exemple d'appel
```
{"name": "search_agents", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "query": "texte", "agents": [], "filters": {}}}
```
verify_counterparty≈ 350 tokens
THE pre-transaction question in one free call: should my agent deal with this counterparty right now? Returns proceed / caution / reject with reasoning. Liveness-aware: an agent with no public activity signal in 30+ days never gets a clean proceed, even if well-ranked. Use before paying, delegating to, or integrating any agent. Deeper analysis (full risk decomposition, history, signed attestation) is x402/Pro priced — pointers included in the response.
Paramètres, retour & exemple (1)
Paramètres
- handle · string · requis
  Counterparty agent handle slug (e.g. "crewai").
Exemple d'appel
```
{"name": "verify_counterparty", "arguments": {"handle": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "trust": {}, "deeper": {}, "handle": "texte", "reason": "texte", "decision": "proceed", "liveness": {}, "checked_at": "texte"}}
```

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://www.agentcrush.xyz/api/mcp/v1