# AgentUtil Docs Semantic Search

> AgentUtil Docs Semantic Search is a paid API for AI agents from docs.agentutil.net, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-15).

Searches pre-indexed developer documentation across 10+ platforms (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, etc.) using natural language queries and returns relevant content chunks with source URLs.

## Facts

- Endpoint: POST https://docs.agentutil.net/query
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/docs-agentutil-net-76ae017e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3j-YKUJpV0N5Q9SL0jF11

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability docs-agentutil-net-76ae017e -d '<json body>'
```

Example prompt: Search the Stripe documentation for how to handle failed payment webhooks and show me the 5 most relevant chunks.

## When to prefer this

Use this endpoint when an agent needs to answer questions about developer APIs or platforms that are pre-indexed (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, etc.) and wants semantically relevant documentation chunks rather than exact keyword matches. Prefer over generic web search when you need structured documentation with source attribution and relevance scores from trusted developer platforms.

## Known failure modes

- Invalid platform ID not in the indexed list returns an error — must first call GET /platforms to get valid values
- Query too vague or unrelated to any indexed content returns zero or low-relevance results
- max_chunks out of range (below 1 or above 10) causes a validation error
- Platform parameter missing causes a 400-level validation error
- Service unavailable or rate-limited returns an error with no results

## How this service works

Search documentation by meaning. Ask a natural language question, get relevant chunks with source URLs from 10+ pre-indexed platforms (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, etc).

## Output

An array of up to 10 documentation chunks, each containing the text content, source URL, page title, section name, relevance score, and last-crawled timestamp, plus metadata about total matches found and the platform queried.

## Example request

```json
{
 "query": "how to authenticate API requests",
 "platform": "filemaker",
 "max_chunks": 5
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "query",
  "platform"
 ],
 "properties": {
  "query": {
   "type": "string",
   "description": "Natural language search query"
  },
  "category": {
   "type": "string",
   "description": "Optional category filter (e.g. graphql, rest, scripting)"
  },
  "platform": {
   "type": "string",
   "example": "filemaker",
   "description": "Platform ID — must be one of the indexed platforms (e.g. 'filemaker'). Use GET /platforms to retrieve the full list of valid values."
  },
  "max_chunks": {
   "type": "integer",
   "default": 5,
   "maximum": 10,
   "minimum": 1,
   "description": "Maximum number of result chunks to return (1–10, default 5)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "platform",
  "query",
  "results",
  "chunks_returned",
  "total_matches",
  "request_id",
  "service",
  "related_services"
 ],
 "properties": {
  "query": {
   "type": "string"
  },
  "results": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "content",
     "source_url",
     "page_title",
     "section",
     "relevance_score",
     "last_crawled"
    ],
    "properties": {
     "content": {
      "type": "string"
     },
     "section": {
      "type": "string"
     },
     "page_title": {
      "type": "string"
     },
     "source_url": {
      "type": "string"
     },
     "last_crawled": {
      "type": "string"
     },
     "relevance_score": {
      "type": "number"
     }
    }
   }
  },
  "service": {
   "type": "string"
  },
  "platform": {
   "type": "string"
  },
  "request_id": {
   "type": "string"
  },
  "total_matches": {
   "type": "number"
  },
  "chunks_returned": {
   "type": "number"
  },
  "related_services": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "name",
     "url",
     "description"
    ],
    "properties": {
     "url": {
      "type": "string"
     },
     "name": {
      "type": "string"
     },
     "description": {
      "type": "string"
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/docs-agentutil-net-76ae017e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from docs.agentutil.net](https://www.zero.xyz/host/docs.agentutil.net/llms.txt)