AgentCrush

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AgentCrush": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1",
      "transport": "streamable-http"
    }
  }
}

Measured tools (14)

• search_agents read-only

  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.

  Parameters:

  • query (required) — string — Search keyword or partial agent name (1-100 chars).
  • filters — object — Optional structured filters.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_agent_details read-only

  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".

  Parameters:

  • handle (required) — string — Agent handle slug (e.g. "qwen", "crewai", "aixbt"). Alphanumeric/hyphen/underscore, max 64 chars.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_agent_history read-only

  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.

  Parameters:

  • handle (required) — string — Agent handle slug.
  • days — number — Days of history to return (1-90, default 30).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• compare_agents read-only

  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.

  Parameters:

  • handles (required) — array — Array of 2-5 agent handles to compare.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_categories read-only

  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?

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_category_ranking read-only

  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.

  Parameters:

  • category (required) — string — Which of the 4 AgentCrush categories to rank.
  • limit — number — Max results to return (1-100, default 50).
  • evidence_ready_only — boolean — Filter to evidence-ranked only. Default true.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_methodology read-only

  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.

  Parameters:

  • category (required) — string — Which category methodology to retrieve.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_agent_trust read-only

  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.

  Parameters:

  • handle (required) — string — Agent handle slug.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• verify_counterparty read-only

  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.

  Parameters:

  • handle (required) — string — Counterparty agent handle slug (e.g. "crewai").

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_top_movers read-only

  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.

  Parameters:

  • limit — number — Max results per direction (1-25, default 10).
  • category — string — Restrict to one category.
  • direction — string — Movement direction. Default "both".

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_protocol_adoption read-only

  How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_agent_changes read-only

  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.

  Parameters:

  • handle (required) — string — Agent handle slug.
  • limit — number — Max changes to return (1-100, default 30).
  • since — string — ISO date cutoff (default 7 days ago).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ecosystem_summary read-only

  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.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• find_agents read-only

  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.

  Parameters:

  • q (required) — string — Capability keyword (required), e.g. "trading", "wallet risk", "code review".
  • alive — boolean — true = only agents alive per the 30-day liveness rule.
  • rails — string — Payment rail filter, e.g. "x402".
  • category — string — Restrict to one AgentCrush category.
  • min_tier — string — Exclude indexed-only agents.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.