Is AgentCrush the same as Crush or Agent Rush?
No. AgentCrush is a web-based ranking index at agentcrush.xyz, unrelated to Crush (a terminal AI coding assistant) or Agent Rush.
AgentCrush MCP Server
@kristof-sudo
基本情報
AgentCrush MCP Server について
Protocol-neutral market intelligence for the AI agent economy. Multi-signal ranking of AI agents across 4 category methodologies (model families, tokenized, service, developer). 7 read-only MCP tools. Free, no auth, 60 req/min.
AgentCrush MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"agentcrush": {
"url": "https://www.agentcrush.xyz/api/mcp/v1"
}
}
}AgentCrush MCP Server のツール
14Search 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.
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".
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.
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.
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?
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.
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.
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.
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.
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.
How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.
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.
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.
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.
概要
What is AgentCrush?
AgentCrush is a protocol-neutral market intelligence index for the AI agent economy. It tracks 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) using a multi-signal methodology with transparent weights and evidence-ranked tiers. It is live at agentcrush.xyz and offers 7 read-only MCP tools, flat JSON endpoints, and an OpenAPI 3.1 spec.
How to use AgentCrush?
Connect any MCP client (Claude Desktop, Cursor) to the MCP server URL https://www.agentcrush.xyz/api/mcp/v1 or use the Smithery CLI (smithery mcp add kristof/agentcrush). For retrieval LLMs that don't speak MCP, use the provided flat JSON endpoints (e.g., GET /api/agent/{handle}/llm-summary).
Key features of AgentCrush
- Evidence-ranked multi-signal index for AI agents
- Tracks agents across 6+ distinct data ecosystems
- 1,338+ total agents indexed with transparent weights
- 7 read-only MCP tools for programmatic access
- Protocol-neutral, no single-protocol dependence
- Commercial readiness audits via AgentCrush Labs
Use cases of AgentCrush
- Market intelligence and competitive analysis of the AI agent economy
- Ranking and comparing AI agents across model, tokenized, service, and developer categories
- Agent Commerce Readiness audits for startups (starting at $299)
- Research on agent ecosystem trends and cross-protocol activity
よくある質問
Is AgentCrush a community-vote leaderboard?
No. Scores come from documented signal weights, not opinion polls.
「開発者ツール」の他のコンテンツ
Vibgrate MCP
VibgrateQuery your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
3
Leadpages MCP
LeadpagesLeadpages MCP is a remote MCP server available at https://mcp.leadpages.com.
DocBin
DocBinGive an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Official Porkbun MCP Server
Porkbun LLCOfficial Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac
32
Modelglass
ModelglassModelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
1
コメント