mcpbeat

AgentCrush MCP Server

io.github.kristof-sudo/agentcrush-app
not responding

AgentCrush is listed as active in the registry but did not answer our last check. It exposes 14 tools. Last commit 3 Aug 2026.

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

Uptime history 39 hours of history · worst hour 0%
39 hours agonow
2.2%
Uptime 24h
2 of 91 checks
14
Tools
read from the server
760 ms
Response time
average over 24h
0
Stars
last commit 3 Aug 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

run in your terminal
claude mcp add agentcrush-app --transport http https://www.agentcrush.xyz/api/mcp/v1
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agentcrush-app": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}
~/.codex/config.toml
[mcp_servers.agentcrush-app]
url = "https://www.agentcrush.xyz/api/mcp/v1"
.cursor/mcp.json
{
  "mcpServers": {
    "agentcrush-app": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "agentcrush-app": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Available tools 14

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent
get_agent_changes
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.
get_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".
get_agent_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.
get_agent_trust
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.
agents
find_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.
search_agents
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.
categories
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?
category
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.
compare
compare_agents
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.
ecosystem
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.
methodology
get_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.
protocol
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.
top
get_top_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.
verify
verify_counterparty
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.

Endpoints

URLTransportStateLatencyChecked
https://www.agentcrush.xyz/api/mcp/v1 streamable-http answering 137 ms 7 min ago

AgentCrush — questions

Answers built from our own checks of this server.

What can AgentCrush do?
It exposes 14 tools, read directly from the server on our last check. Among them: compare_agents, find_agents, get_agent_changes, get_agent_details, get_agent_history, get_agent_trust and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is AgentCrush mostly used for?
Its tools cluster around agent and agents. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is AgentCrush working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 2 of 91 checks got a reply (2.2%), average response time 760 ms. The bar chart above shows every period we have measured.
The registry lists AgentCrush as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect AgentCrush?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AgentCrush need an API key?
No. AgentCrush completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AgentCrush?
It answers our handshake in 760 ms on average, which is faster than 10% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is AgentCrush open source?
Yes — written in JavaScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.