# AgentCrush MCP server

Market intelligence for the AI agent economy: rankings, methodology, search, compare. tools.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-kristof-sudo-agentcrush-app
- Repository: https://github.com/kristof-sudo/agentcrush-app
- Website: https://www.agentcrush.xyz

## Install
- Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- Auth: Not captured

## Setup notes
- Remote endpoint: https://www.agentcrush.xyz/api/mcp/v1

## Tools
- search_agents (Search AgentCrush Index) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_agent_details (Get Full Agent Details) - 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". Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_agent_history (Get Agent Rank/Score History) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- compare_agents (Compare AI Agents Side-by-Side) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- list_categories (List AgentCrush 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? Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_category_ranking (Get Category Ranking) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_methodology (Get Scoring Methodology) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_agent_trust (Get Composite Trust Score) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- verify_counterparty (Verify Counterparty (pre-transaction check)) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_top_movers (Get Top Weekly Movers) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_protocol_adoption (Get Protocol Adoption Counts) - How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_agent_changes (Get Per-Agent Change Feed) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- get_ecosystem_summary (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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1
- find_agents (Find Payable Counterparty Agents) - 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. Endpoint: https://www.agentcrush.xyz/api/mcp/v1

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.kristof-sudo
- Version: 1.0.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 17, 2026
- Source: https://registry.modelcontextprotocol.io