# search_models

Search for models using semantic search

Agent View of the PolicyLayer registry record for `search_models`. HTML page: https://policylayer.com/tools/deepfates-mcp-replicate/search-models

## Facts

- Tool: `search_models`
- Server: Replicate MCP Server (`deepfates/mcp-replicate`) — https://policylayer.com/tools/deepfates-mcp-replicate.md
- Homepage: https://github.com/deepfates/mcp-replicate
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_models",
    "arguments": {}
  }
}
```

## Why search_models is rated Low

This tool performs a search query to discover available models. It is purely informational—it retrieves data without creating, modifying, executing, or deleting anything. No external operations are triggered, and the action is reversible with no blast radius if misused by an agent.

From the tool's own definition: "Tool name 'search_models' and description 'Search for models using semantic search' indicate a query operation that retrieves information without modification or side effects."

## Use case

AI agents call search_models to retrieve information from Replicate MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Replicate MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_models": {}
  }
}
```

## Other tools on Replicate MCP Server (12)

- `clear_image_cache` — Destructive — https://policylayer.com/tools/deepfates-mcp-replicate/clear-image-cache.md
- `cancel_prediction` — Execute — https://policylayer.com/tools/deepfates-mcp-replicate/cancel-prediction.md
- `create_and_poll_prediction` — Execute — https://policylayer.com/tools/deepfates-mcp-replicate/create-and-poll-prediction.md
- `create_prediction` — Execute — https://policylayer.com/tools/deepfates-mcp-replicate/create-prediction.md
- `get_collection` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/get-collection.md
- `get_image_cache_stats` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/get-image-cache-stats.md
- `get_model` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/get-model.md
- `get_prediction` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/get-prediction.md
- `list_collections` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/list-collections.md
- `list_models` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/list-models.md
- `list_predictions` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/list-predictions.md
- `view_image` — Read — https://policylayer.com/tools/deepfates-mcp-replicate/view-image.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=deepfates-mcp-replicate · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepfates-mcp-replicate