AgentCrush is listed as active in the registry but did not answer our last check. It exposes 14 tools. Last commit 15 Sep 2026.
Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.
Uptime history
51 days of history · worst day 2%
51 days agonow
17.6%
Uptime 24h
16 of 91 checks
14
Tools
read from the server
458 ms
Response time
average over 24h
0
Stars
last commit 15 Sep 2026
What the code does
We read the source, 16 h ago · tools taken from the live server · rules 3dff92dd89df
Capabilities
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
Runs an external command
ops/executor/runner-executor.mjs:9, ops/executor/runner-stepB.mjs:37, ops/executor/runner-stepC.mjs:37 и ещё 10
return execSync(cmd, { cwd: cwd || process.cwd(), stdio: 'pipe' }).toString().trim()
Builds a file path from a variable
ops/executor/runner-executor.mjs:22, ops/executor/runner-stepB.mjs:71, ops/executor/runner-stepC.mjs:64 и ещё 5
const dir = path.join(baseDir, taskId)
Runs an external command
tools/agentcrush-exec.py:66
res = subprocess.run(cmd, cwd=cwd, text=True, capture_output=True)
Sends data to a third-party sink
runtime/ajsa/auto-like-worker.mjs:158, runtime/copydesk/approval-listener.mjs:26, runtime/copydesk/approval-notifier.mjs:18 и ещё 4
await fetch(`https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage`, {
Dumps the whole environment
tools/agentcrush-supabase.py:32
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 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
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://www.agentcrush.xyz/api/mcp/v1 | streamable-http | answering | 167 ms | 6 min ago |
Alternatives to AgentCrush
same job, measured the same wayNewsgurus Intel
by collectorguru
Pay-per-call trading intelligence for AI agents: live market regime, trading signals, composite conv
Agent Watch
by entradox
Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints
Closelook Intelligence
by closelookventure
Closelook AI-market intelligence: 5 indices, 6 ranking families, stock snapshots. 13 tools.
Caelian
by mananmodi-product
Live competitive intelligence for B2B teams — signals, threat rankings, and revenue-driving actions.
Fingerprint
by fingerprintjs
Device intelligence for AI agents: Fingerprint events, smart signals, and API key management.
Profitelligence
by profitelligence
Financial intelligence: insider trades, SEC filings, 13F holdings, and market signals.
Qoory Crypto Intelligence
by qoory-ai
One Data Plane for crypto research, with 42 live tools for markets, entities, news, and signals.
MCP Knowledge
by getgapup
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.
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 16 of 91 checks got a reply (17.6%), average response time 458 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 458 ms on average, which is faster than 34% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is AgentCrush open source?
We cannot say either way: written in JavaScript and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.