INDIVIDUAL MCP TOOL

get_top_movers

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

agentcrush.xyznone authenticationAvailability not checked

Input schema

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

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

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "agentcrush-xyz",
  "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.

search_agents — Search AI agents by name or keyword across AgentCrush's evidence-ranked index.
get_agent_details — Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer).
get_agent_history — Get rank and score history for an AI agent over the past 1–90 days.
compare_agents — Compare 2-5 AI agents side-by-side across all their categories.
list_categories — List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions.
get_category_ranking — Get the full ranking for one of the 5 categories.
get_methodology — Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations.
get_agent_trust — Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions.