AI & Machine Learning

agentcrush.xyz

Searches and compares AI agents across various metrics and categories.

x402 supported3 endpoints32 known toolsFirst detected June 13, 2026Last detected August 29, 2026

ENDPOINT 1

https://agentcrush.xyz/api/mcp/v1

No auth detected

MCP server metadata

Name: AgentCrush
Version: 1.0.0

Capabilities

toolsresourcesprompts

Known tools 14

search_agents

Search AI agents by name or keyword across AgentCrush's evidence-ranked index.

Inferred read-only

get_agent_details

Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer).

Inferred read-only

get_agent_history

Get rank and score history for an AI agent over the past 1–90 days.

Inferred read-only

compare_agents

Compare 2-5 AI agents side-by-side across all their categories.

Inferred read-only

list_categories

List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions.

Inferred read-only

get_category_ranking

Get the full ranking for one of the 5 categories.

Inferred read-only

get_methodology

Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations.

Inferred read-only

get_agent_trust

Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions.

Inferred read-only

verify_counterparty

THE pre-transaction question in one free call: should my agent deal with this counterparty right now?

Inferred read-only

get_top_movers

Returns the top weekly rank movers (up + down) computed from agents.weekly_delta.

Inferred read-only

get_protocol_adoption

How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub).

Inferred read-only

get_agent_changes

Pairwise delta scan over an agent's recent snapshots.

Inferred read-only

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.

Inferred read-only

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.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentcrush]
url = "https://agentcrush.xyz/api/mcp/v1"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "type": "http",
      "url": "https://agentcrush.xyz/api/mcp/v1"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentcrush
Remote MCP URL: https://agentcrush.xyz/api/mcp/v1

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "url": "https://agentcrush.xyz/api/mcp/v1"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentcrush": {
      "type": "http",
      "url": "https://agentcrush.xyz/api/mcp/v1"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcrush",
  "transport": "streamable-http",
  "url": "https://agentcrush.xyz/api/mcp/v1"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://www.agentcrush.xyz/api/mcp/v1

No auth detected

MCP server metadata

Name: AgentCrush
Version: 1.0.0

Capabilities

toolsresourcesprompts

Known tools 14

search_agents

Search AI agents by name or keyword across AgentCrush's evidence-ranked index.

Inferred read-only

get_agent_details

Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer).

Inferred read-only

get_agent_history

Get rank and score history for an AI agent over the past 1–90 days.

Inferred read-only

compare_agents

Compare 2-5 AI agents side-by-side across all their categories.

Inferred read-only

list_categories

List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions.

Inferred read-only

get_category_ranking

Get the full ranking for one of the 5 categories.

Inferred read-only

get_methodology

Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations.

Inferred read-only

get_agent_trust

Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions.

Inferred read-only

verify_counterparty

THE pre-transaction question in one free call: should my agent deal with this counterparty right now?

Inferred read-only

get_top_movers

Returns the top weekly rank movers (up + down) computed from agents.

Inferred read-only

get_protocol_adoption

How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub).

Inferred read-only

get_agent_changes

Pairwise delta scan over an agent's recent snapshots.

Inferred read-only

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.

Inferred read-only

find_agents

Counterparty discovery: "which agents can do X and are safe to pay?

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentcrush]
url = "https://www.agentcrush.xyz/api/mcp/v1"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "type": "http",
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentcrush
Remote MCP URL: https://www.agentcrush.xyz/api/mcp/v1

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentcrush": {
      "type": "http",
      "url": "https://www.agentcrush.xyz/api/mcp/v1"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcrush",
  "transport": "streamable-http",
  "url": "https://www.agentcrush.xyz/api/mcp/v1"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 3

https://agentcrush.xyz/api/mcp

No auth detected

MCP server metadata

Name: AgentCrush
Version: 1.0.0

Capabilities

tools

Known tools 4

lookup_agent

Look up a specific AI agent by handle.

Inferred read-only

search_agents

Search AI agents by name or keyword.

Inferred read-only

compare_agents

Compare two AI agents side-by-side: rank, score, tier, and archetype.

Inferred read-only

get_history

Get rank and score history for an AI agent.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentcrush]
url = "https://agentcrush.xyz/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "type": "http",
      "url": "https://agentcrush.xyz/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentcrush
Remote MCP URL: https://agentcrush.xyz/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentcrush": {
      "url": "https://agentcrush.xyz/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentcrush": {
      "type": "http",
      "url": "https://agentcrush.xyz/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcrush",
  "transport": "streamable-http",
  "url": "https://agentcrush.xyz/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentcrush.xyz was fetched 2026-08-28T09:10:00.432Z.

Trust status Neutral

agentcrush.xyz is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.