# search_docs_chunks

This tool will take in the user prompt, search shopify.dev, and return relevant documentation and code examples that will help answer the user's question.

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

## Facts

- Tool: `search_docs_chunks`
- Server: Dev (`@shopify/dev-mcp`) — https://policylayer.com/tools/dev.md
- Install: `npx -y @shopify/dev-mcp`
- Homepage: https://www.npmjs.com/package/@shopify/dev-mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 5 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `prompt` | string | yes | The search query for Shopify documentation |
| `version` | string | no | The API version to scope search results to (e.g., '2025-04', '2026-01'). Pass the version you detected or received from learn_shopify_api. When omitted, search |
| `api_name` | string | no | The API name to filter search results by. Pass the same API name you used with learn_shopify_api (e.g., 'polaris-admin-extensions', 'pos-ui', 'admin'). This fil |
| `conversationId` | string | yes | 🔗 REQUIRED: conversationId from learn_shopify_api tool. Call learn_shopify_api first if you don't have this. |
| `max_num_results` | number | no | Maximum number of results to return from the search. Do not pass this when calling the tool for the first time, only use this when you want to limit the number |

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_chunks",
    "arguments": {
      "prompt": "<prompt>",
      "conversationId": "<conversationId>"
    }
  }
}
```

## Why search_docs_chunks is rated Low

This tool performs a search operation that retrieves and returns existing documentation and code examples. It has no side effects, cannot modify or delete data, and does not execute code. It is a straightforward read/query operation with minimal risk even if misused by an AI agent, as the worst outcome would be returning irrelevant search results.

From the tool's own definition: "Tool description states it 'will take in the user prompt, search shopify.dev, and return relevant documentation and code examples' — purely retrieval and querying of documentation without any data modification, deletion, or code execution."

## Use case

AI agents call search_docs_chunks to retrieve information from 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 Dev:

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

## Other tools on Dev (4)

- `learn_shopify_api` — Read — https://policylayer.com/tools/dev/learn-shopify-api.md
- `validate_component_codeblocks` — Read — https://policylayer.com/tools/dev/validate-component-codeblocks.md
- `validate_graphql_codeblocks` — Read — https://policylayer.com/tools/dev/validate-graphql-codeblocks.md
- `validate_theme` — Read — https://policylayer.com/tools/dev/validate-theme.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 · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev