# Heurist Mesh: Exa URL Scrape & Digest Agent

> Heurist Mesh: Exa URL Scrape & Digest Agent is a paid API for AI agents from mesh.heurist.xyz, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Scrapes full content from up to 5 URLs in a single batch and uses an LLM to summarize or extract structured information from the pages

## Facts

- Endpoint: POST https://mesh.heurist.xyz/x402/solana/agents/ExaSearchDigestAgent/exa_scrape_url
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/heurist-mesh-exa-url-scrape-digest-agent-f0226f95
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1vt8P4N48j8uselCrktns

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 heurist-mesh-exa-url-scrape-digest-agent-f0226f95 -d '<json body>'
```

Example prompt: Scrape these three URLs and give me a concise summary of what each page is about: https://example.com/article1, https://example.com/article2, https://example.com/article3 — focus on the key findings and any statistics mentioned.

## When to prefer this

Choose this endpoint when you need to scrape and immediately digest or summarize web page content using an LLM in a single call, rather than running a separate scrape-then-summarize pipeline. It is ideal for batching up to 5 URLs at once and getting AI-processed output rather than raw HTML. Prefer this over generic scraping tools when you want structured extraction or summaries directly, not just raw text. Do not use for Twitter/X URLs — use dedicated Twitter agent tools for those.

## Known failure modes

- URL is behind a login wall or paywall — scrape returns empty or access-denied content
- URL is a Twitter/X link — endpoint explicitly does not support x.com or twitter.com; use Twitter agent tools instead
- Batch exceeds 5 URLs — request will fail or be rejected
- URL returns a non-HTML resource (PDF, binary) — content extraction may be incomplete or fail
- Target site blocks scrapers via robots.txt or rate limiting — returns empty or partial content
- LLM summary may omit details if page content is very long and exceeds context limits

## How this service works

Scrape full contents from URLs and use LLM to create a summary or extract information. Max 5 URLs per batch. (Do not use this for x.com twitter.com links - use Twitter agent tools instead)

## Output

Returns LLM-processed output derived from the scraped page content — either a natural language summary of each URL, extracted structured information (e.g. prices, names, statistics), or a combined digest, depending on the instruction provided. Content is cleaned and made LLM-ready before processing.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json"
     ]
    },
    "body": {
     "type": "object",
     "properties": {
      "urls": {
       "type": "array",
       "items": {
        "type": "string"
       },
       "description": "List of source URLs to scrape (max 5 URLs per batch)",
       "maxItems": 5
      },
      "extract_prompt": {
       "type": "string",
       "description": "Instruction to LLM to process the scraped contents. Max 3 sentences. Use this when you want to extract specific information from the page. If this field is empty, a summary will be returned."
      },
      "debug": {
       "type": "boolean",
       "description": "Debug mode flag. ALWAYS use false.",
       "default": false
      }
     },
     "required": [
      "urls"
     ]
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "result": {
       "type": "object",
       "additionalProperties": true
      }
     }
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/heurist-mesh-exa-url-scrape-digest-agent-f0226f95/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mesh.heurist.xyz](https://www.zero.xyz/host/mesh.heurist.xyz/llms.txt)