AgentCrush
Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.
使うべきか
品質と安全性
検出事項（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domainfind_agents 内
- LOWTool 'get_protocol_adoption' description lacks action verbget_protocol_adoption 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"agentcrush-app": {
"url": "https://www.agentcrush.xyz/api/mcp/v1"
}
}
}リモートエンドポイント
https://www.agentcrush.xyz/api/mcp/v1streamable-httpできること
ツール一覧
ツール（14）
🟢search_agents(query, filters)
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.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search keyword or partial agent name (1-100 chars)."
},
"filters": {
"type": "object",
"description": "Optional structured filters.",
"properties": {
"primary_category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
],
"description": "Restrict to one of the 4 AgentCrush categories."
},
"evidence_ranked_only": {
"type": "boolean",
"description": "Only return evidence-ranked agents. Default false (include indexed too)."
},
"limit": {
"type": "number",
"description": "Max results (1-50, default 10)."
}
}
}
},
"required": [
"query"
]
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"filters": {
"type": "object"
},
"count": {
"type": "integer",
"description": "Number of results returned."
},
"agents": {
"type": "array",
"items": {
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"primary_category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
]
},
"secondary_categories": {
"type": "array",
"items": {
"type": "string"
}
},
"tier": {
"type": "string"
},
"archetype": {
"type": "string"
},
"ecosystem_layer": {
"type": "string"
},
"profile_url": {
"type": "string",
"format": "uri"
}
}
}
}
}
}🟢get_agent_details(handle)
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".
入力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"description": "Agent handle slug (e.g. \"qwen\", \"crewai\", \"aixbt\"). Alphanumeric/hyphen/underscore, max 64 chars."
}
},
"required": [
"handle"
]
}出力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"tier": {
"type": "string"
},
"archetype": {
"type": "string"
},
"primary_category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
]
},
"secondary_categories": {
"type": "array",
"items": {
"type": "string"
}
},
"verified": {
"type": "boolean"
},
"erc8004_registered": {
"type": "boolean"
},
"bio": {
"type": "string"
},
"profile_url": {
"type": "string",
"format": "uri"
},
"identity": {
"type": "object",
"description": "External identifiers (hf_author, lmarena_keys, paper_ids, virtuals_id, agentverse_id, github_full_name)."
},
"scores": {
"type": "object",
"description": "Per-category scoring data keyed by category slug."
},
"error": {
"type": "string",
"description": "Set when agent not found."
},
"suggestions": {
"type": "array",
"items": {
"type": "object"
},
"description": "Fuzzy-match suggestions when not found."
}
}
}🟢get_agent_history(handle, days)
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.
入力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"description": "Agent handle slug."
},
"days": {
"type": "number",
"description": "Days of history to return (1-90, default 30)."
}
},
"required": [
"handle"
]
}出力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"days_requested": {
"type": "integer"
},
"snapshot_count": {
"type": "integer"
},
"history": {
"type": "array",
"items": {
"type": "object"
}
},
"summary": {
"type": "object",
"description": "rank_start, rank_current, score_start, score_current, trend (rising/falling/flat)."
}
}
}🟢compare_agents(handles)
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.
入力スキーマ
{
"type": "object",
"properties": {
"handles": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2,
"maxItems": 5,
"description": "Array of 2-5 agent handles to compare."
}
},
"required": [
"handles"
]
}出力スキーマ
{
"type": "object",
"properties": {
"compare_url": {
"type": "string",
"format": "uri",
"nullable": true,
"description": "Human-readable comparison page URL (2-agent comparisons only)."
},
"agents": {
"type": "array",
"items": {
"type": "object",
"description": "Full agent details per handle."
}
}
}
}🟢list_categories
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?
入力スキーマ
{
"type": "object",
"properties": {}
}出力スキーマ
{
"type": "object",
"properties": {
"categories": {
"type": "array",
"items": {
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
]
},
"display_name": {
"type": "string"
},
"description": {
"type": "string"
},
"methodology_version": {
"type": "string",
"description": "e.g. v1.4-with-deployment for model_family."
},
"total_tracked": {
"type": "integer"
},
"evidence_ranked": {
"type": "integer"
},
"ranking_url": {
"type": "string",
"format": "uri"
}
}
}
}
}
}🟢get_category_ranking(category, evidence_ready_only, limit)
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.
入力スキーマ
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
],
"description": "Which of the 4 AgentCrush categories to rank."
},
"evidence_ready_only": {
"type": "boolean",
"description": "Filter to evidence-ranked only. Default true."
},
"limit": {
"type": "number",
"description": "Max results to return (1-100, default 50)."
}
},
"required": [
"category"
]
}出力スキーマ
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
]
},
"methodology_version": {
"type": "string"
},
"count": {
"type": "integer"
},
"ranking": {
"type": "array",
"items": {
"type": "object",
"description": "Per-agent ranking row with sub-scores."
}
}
}
}🟢get_methodology(category)
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.
入力スキーマ
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
],
"description": "Which category methodology to retrieve."
}
},
"required": [
"category"
]
}出力スキーマ
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
]
},
"name": {
"type": "string"
},
"methodology_version": {
"type": "string"
},
"description": {
"type": "string"
},
"signals": {
"type": "array",
"items": {
"type": "object",
"description": "Per-signal weight + formula + note."
}
},
"evidence_ready_rule": {
"type": "string"
},
"limitations": {
"type": "array",
"items": {
"type": "string"
}
},
"methodology_url": {
"type": "string",
"format": "uri"
}
}
}🟢get_agent_trust(handle)
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.
入力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"description": "Agent handle slug."
}
},
"required": [
"handle"
]
}出力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"trust_score": {
"type": "number",
"description": "0-100 composite score."
},
"classification": {
"type": "string",
"enum": [
"verified",
"provisional",
"unverified",
"low_trust"
]
},
"classification_thresholds": {
"type": "object"
},
"factors": {
"type": "object",
"description": "confidence_by_category, tier, risk_flags, surfaces."
},
"score_breakdown": {
"type": "array",
"items": {
"type": "object"
}
},
"delegation_hint": {
"type": "string"
}
}
}🟢verify_counterparty(handle)
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.
入力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"description": "Counterparty agent handle slug (e.g. \"crewai\")."
}
},
"required": [
"handle"
]
}出力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"decision": {
"type": "string",
"enum": [
"proceed",
"caution",
"reject"
]
},
"reason": {
"type": "string"
},
"trust": {
"type": "object",
"description": "score, tier, verified, rank."
},
"liveness": {
"type": "object",
"description": "alive (30d activity window), last_code_or_event_signal_at."
},
"checked_at": {
"type": "string"
},
"deeper": {
"type": "object",
"description": "Paid x402/Pro endpoints for full evaluation, history, signed attestation."
}
}
}🟢get_top_movers(direction, limit, category)
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.
入力スキーマ
{
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": [
"up",
"down",
"both"
],
"description": "Movement direction. Default \"both\"."
},
"limit": {
"type": "number",
"description": "Max results per direction (1-25, default 10)."
},
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
],
"description": "Restrict to one category."
}
}
}出力スキーマ
{
"type": "object",
"properties": {
"direction": {
"type": "string"
},
"up": {
"type": "array",
"items": {
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"weekly_delta": {
"type": "number"
},
"tier": {
"type": "string"
},
"primary_category": {
"type": "string"
},
"profile_url": {
"type": "string"
}
}
}
},
"down": {
"type": "array",
"items": {
"type": "object"
}
}
}
}🟢get_protocol_adoption
How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.
入力スキーマ
{
"type": "object",
"properties": {}
}出力スキーマ
{
"type": "object",
"properties": {
"total_agents": {
"type": "integer"
},
"adoption": {
"type": "object",
"properties": {
"erc_8004_verified": {
"type": "integer"
},
"virtuals_token": {
"type": "integer"
},
"agentverse_listed": {
"type": "integer"
},
"github_mapped": {
"type": "integer"
},
"x402_bazaar_endpoint": {
"type": "integer"
}
}
},
"last_updated": {
"type": "string"
}
}
}🟢get_agent_changes(handle, since, limit)
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.
入力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"description": "Agent handle slug."
},
"since": {
"type": "string",
"description": "ISO date cutoff (default 7 days ago)."
},
"limit": {
"type": "number",
"description": "Max changes to return (1-100, default 30)."
}
},
"required": [
"handle"
]
}出力スキーマ
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"since": {
"type": "string"
},
"change_count": {
"type": "integer"
},
"changes": {
"type": "array",
"items": {
"type": "object"
}
}
}
}🟢get_ecosystem_summary
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.
入力スキーマ
{
"type": "object",
"properties": {}
}出力スキーマ
{
"type": "object",
"properties": {
"summary": {
"type": "string"
},
"totals": {
"type": "object"
},
"category_mix": {
"type": "object"
},
"leaders": {
"type": "object"
},
"snapshot_window": {
"type": "object"
}
}
}🟢find_agents(q, category, rails, alive, min_tier)
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.
入力スキーマ
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Capability keyword (required), e.g. \"trading\", \"wallet risk\", \"code review\"."
},
"category": {
"type": "string",
"enum": [
"model_family",
"tokenized",
"service",
"developer",
"mcp_server"
],
"description": "Restrict to one AgentCrush category."
},
"rails": {
"type": "string",
"description": "Payment rail filter, e.g. \"x402\"."
},
"alive": {
"type": "boolean",
"description": "true = only agents alive per the 30-day liveness rule."
},
"min_tier": {
"type": "string",
"enum": [
"evidence_ranked"
],
"description": "Exclude indexed-only agents."
}
},
"required": [
"q"
]
}出力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"filters": {
"type": "object"
},
"total_matches": {
"type": "integer"
},
"candidates": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rank": {
"type": "integer"
},
"handle": {
"type": "string"
},
"name": {
"type": "string"
},
"primary_category": {
"type": "string"
},
"tier": {
"type": "string"
},
"verified": {
"type": "boolean"
},
"liveness": {
"type": "string",
"enum": [
"alive",
"ghost"
]
},
"payment_rails": {
"type": "array",
"items": {
"type": "object"
}
},
"scores": {
"type": "object"
},
"profile_url": {
"type": "string",
"format": "uri"
},
"trust_eval_url": {
"type": "string",
"format": "uri"
}
}
}
},
"full_results": {
"type": "object",
"description": "Pointer to the paid full-list endpoint when more matches exist."
}
}
}コミュニティ
エビデンス