# search_docs

Search the goldprice.dev FAQ corpus via BM25. Returns top-K matching questions + answers with relevance scores. Use before answering how-to / billing / auth questions so you cite the canonical text instead of guessing from training data.

Agent View of the PolicyLayer registry record for `search_docs`. HTML page: https://policylayer.com/tools/dev-goldprice-mcp/search-docs

## Facts

- Tool: `search_docs`
- Server: Goldprice Dev (`https://api.goldprice.dev/v1/mcp/`) — https://policylayer.com/tools/dev-goldprice-mcp.md
- Homepage: https://github.com/https://api.goldprice.dev/v1/mcp/
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server rate-limited: yes
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `limit` | integer | no |  |
| `query` | string | yes |  |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_docs",
    "arguments": {
      "query": "<query>"
    }
  }
}
```

## Why search_docs is rated Low

This tool performs a read-only search operation on FAQ documentation. It retrieves and returns matching text snippets without creating, modifying, deleting, or executing any operations. The search is bounded to a FAQ corpus and serves a lookup/reference purpose. Low severity because misuse cannot corrupt data, trigger external operations, or affect system state beyond consuming search resources.

From the tool's own definition: "Tool description states it 'Search[es] the goldprice.dev FAQ corpus' and 'Returns top-K matching questions + answers with relevance scores.' The verb 'search' and 'returns' indicate data retrieval with no modification or side effects."

## Use case

AI agents call search_docs to retrieve information from Goldprice Dev 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 Goldprice Dev:

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

## Other tools on Goldprice Dev (7)

- `get_carat` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-carat.md
- `get_forward_view` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-forward-view.md
- `get_historical` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-historical.md
- `get_metadata` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-metadata.md
- `get_physical_price` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-physical-price.md
- `get_spot_price` — Read — https://policylayer.com/tools/dev-goldprice-mcp/get-spot-price.md
- `list_commodities` — Read — https://policylayer.com/tools/dev-goldprice-mcp/list-commodities.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=dev-goldprice-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-goldprice-mcp