AgentCrush

kristof-sudo/agentcrush-app

Think CoinMarketCap but for AI agents. This connects Claude to a cross-protocol index tracking 1,300+ agents from HuggingFace, LMArena, GitHub citations, ERC-8004 registries, Virtuals tokenized protocols, and machine-payable endpoints. You get seven tools: search agents by name or category, pull detailed rankings with methodology weights, compare agents side by side, retrieve scoring history, and list available categories (model families, tokenized agents, service agents, developers). Reach for this when you need evidence-based intelligence on the agent economy instead of manually hunting across scattered leaderboards and registries. All read-only, methodology transparent, no community voting.

tools: 7
transport: HTTP
last updated: Jun 12, 2026

View on GitHub

Tools

7 tools

Public tool metadata for what this MCP can expose to an agent.

search_agentsSearch 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.2 params

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* required

filtersobject

Optional structured filters.

querystring

Search keyword or partial agent name (1-100 chars).

get_agent_detailsGet 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...1 params

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...

Parameters* required

handlestring

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

get_agent_historyGet 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.2 params

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* required

daysnumber

Days of history to return (1-90, default 30).

handlestring

Agent handle slug.

compare_agentsCompare 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.1 params

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* required

handlesarray

Array of 2-5 agent handles to compare.

list_categoriesList the 4 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?

List the 4 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?

No parameter schema in public metadata yet.

get_category_rankingGet the full ranking for one of the 4 categories. Returns agents ordered by composite score with all sub-scores visible. Defaults to evidence-ranked only.3 params

Get the full ranking for one of the 4 categories. Returns agents ordered by composite score with all sub-scores visible. Defaults to evidence-ranked only.

Parameters* required

categorystring

Which of the 4 AgentCrush categories to rank.one of model_family · tokenized · service · developer

evidence_ready_onlyboolean

Filter to evidence-ranked only. Default true.

limitnumber

Max results to return (1-100, default 50).

get_methodologyGet 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.1 params

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* required

categorystring

Which category methodology to retrieve.one of model_family · tokenized · service · developer

Readme

AgentCrush

Protocol-neutral market intelligence for the AI agent economy.

Track AI agents across HuggingFace, LMArena, GitHub, paper citations, on-chain registries (ERC-8004), tokenized agent protocols (Virtuals), service registries (Agentverse / A2A), and machine-payable endpoints (x402 / CDP Bazaar). Multi-signal methodology, transparent weights, evidence-ranked tiers.

🌐 Live at agentcrush.xyz · 📋 Methodology · 🔌 MCP Server · 📖 API docs · 📡 llms.txt

What AgentCrush is

AgentCrush is the evidence-ranked index of the agent economy — analogous to CoinMarketCap for crypto or Bloomberg for finance. We don't pick winners. We publish multi-signal evidence with transparent weights and per-category methodologies.

Live as of May 2026:

View the full README on GitHub

Details

Repository: github.com/kristof-sudo/agentcrush-app
Website: www.agentcrush.xyz
Category: AI & LLM Tools
Transport: HTTP
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

IBM Code Engine MCP Servermarkusvankempen/code-engine-mcp-serverDeploy to IBM Code Engine from Cursor, Copilot, Claude & Cline. Build, push, deploy via MCP.0stars

VoteShipmattkilmer/voteship-agent-toolkitManage feature requests, votes, roadmaps, and changelogs from any MCP client.0stars

Mercury X402 Mcpmercuryx402/mercury-x402-mcpAgent-payable web data over x402: 18 keyless services an agent pays per call.0stars

OpenClaw Consensusmiconnm/openclaw-consensus-mcp9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.0stars

Gvnrmightbesaad/gvnrBudget & cost control for AI agents — per-agent spend caps + rate limits before each call.0stars

Minuetminuetai/minuet-mcpMCP server exposing Minuet's ERC-8004 agent relationship graph.0stars