Perceive URLs in Batch
perceive_batchBatch-render up to 1000 URLs with one shared options block, returning markdown, PDFs, screenshots, and structured data. Poll by job ID for progress and download all artifacts as a ZIP.
Instructions
Render up to 1000 URLs with one shared options block. Small batches (about 10 or fewer) complete inline in the response; larger ones return status 'queued', so poll get_perceive_batch with the job_id.
Use when: the same outputs are needed from many known URLs (e.g. markdown of every doc page you just discovered with discover_urls).
Do NOT use when: one URL (use perceive_url); the goal is RAG-ready chunked output (use start_ingest); the URLs are unknown (use discover_urls or web_search first).
Returns: job_id, status (queued/processing/completed/failed/partial), per-URL counts, and one full perceive result per URL once processed. output_mode 'zip' bundles every artifact into one ZIP.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | URLs to render with the shared options. | |
| mobile | No | Emulate a mobile device. Default false. | |
| schema | No | JSON schema for LLM structured extraction (plan-gated). Combine with outputs including 'structured'. | |
| context | Yes | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." | |
| extract | No | Heuristic extraction targets. Implemented today: tables, metadata, main_content, headings, structured_data; others return a warning. | |
| js_code | No | JavaScript executed after page load, before capture. | |
| outputs | No | Artifacts to produce. Default: ['markdown','structured']. | |
| wait_for | No | CSS selector (optionally 'css:...') or 'js:<expr>' to await after navigation. | |
| cache_mode | No | Default 'enabled' (~1h cache). 'bypass' skips the cache; 'refresh' re-renders. | |
| output_mode | No | 'manifest' (default) or 'zip' (bundle all artifacts once complete). | |
| pdf_options | No | Only meaningful when outputs includes 'pdf'. | |
| respect_robots | No | Default false. | |
| viewport_width | No | Default 1920. | |
| block_resources | No | Resource types the browser should not load (faster, cheaper renders). | |
| viewport_height | No | Default 1080. | |
| wait_timeout_ms | No | Default 30000. |