# AgentCrush

Protocol-neutral market intelligence for the AI agent economy. Multi-signal ranking of AI agents across 4 category methodologies (model families, tokenized agents, service agents, developer agents). …

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add kristof/agentcrush

# Browse available tools
npx -y smithery tool list kristof/agentcrush

# Get full schema for a tool
npx -y smithery tool get kristof/agentcrush search_agents

# Call a tool
npx -y smithery tool call kristof/agentcrush search_agents '{}'
```

## Direct MCP Connection

Endpoint: `https://agentcrush--kristof.run.tools`

## Tools (7)

- `search_agents` — Search AI agents by name or keyword across AgentCrush's evidence-ranked index. Returns matching agents with category, t…
- `get_agent_details` — Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, servi…
- `get_agent_history` — Get rank and score history for an AI agent over the past 1–90 days. Daily snapshots, deduplicated per calendar day. Ret…
- `compare_agents` — Compare 2-5 AI agents side-by-side across all their categories. Returns full per-agent scoring data + comparison contex…
- `list_categories` — List the 4 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions. Use this…
- `get_category_ranking` — Get the full ranking for one of the 4 categories. Returns agents ordered by composite score with all sub-scores visible…
- `get_methodology` — Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limita…

```bash
# Get full input/output schema for a tool
npx -y smithery tool get kristof/agentcrush <tool-name>
```