read_page
Read-onlyIdempotent
Extract page content as DOM, accessibility tree, CSS diagnostics, semantic summary, or clean Markdown. Use for reading structure, verifying content, or extracting articles.
Instructions
Get page as DOM, accessibility tree (ax), CSS diagnostics, semantic summary, or clean Markdown (article-shaped).
When to use: Reading page structure, verifying content, extracting the full DOM tree, or reducing article-like pages to Markdown. When NOT to use: Use inspect for targeted state queries or find to locate a specific element.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | Tab ID to read from | |
| taskId | No | Task id when using a task-scoped browser lane. | |
| laneId | No | Task-scoped browser lane id; validates tabId or defaults to the lane current target. | |
| depth | No | Max tree depth. Default: 8 (all), 5 (interactive) | |
| filter | No | Filter: interactive for form/button/link only | |
| ref_id | No | Parent ref for subtree scoping | |
| selector | No | CSS selector (css mode only) | |
| mode | No | Output mode: dom (default), ax, css, semantic, or markdown (clean article extraction). | |
| onlyMainContent | No | Markdown mode only: strip nav/header/footer/aside/ads. Default: true. | |
| includeLinks | No | Markdown mode only: preserve <a> as markdown links. Default: true. | |
| contentFilter | No | Markdown mode only: deterministic fit_markdown filter. Default: none. | |
| query | No | Markdown mode only: required when contentFilter="bm25". | |
| returnRaw | No | Markdown mode only: include raw_markdown in JSON response. Default: false. | |
| returnFit | No | Markdown mode only: include fit_markdown and use it as content when filtering. Default: true when filtered. | |
| filterOptions | No | Markdown mode only: minWords, maxSections, bm25Threshold, pruneThreshold. | |
| includePagination | No | Include pagination info. Default: true | |
| cursor | No | Markdown mode only: opaque cursor returned as nextCursor from a prior paginated read_page markdown call. | |
| compression | No | Compression mode. "delta" returns only changes since last read. | |
| planningProfile | No | DOM mode only: stable omits decorative/noisy serialization details without mutating the live page. Default: default. | |
| fallback | No | AX mode only: use "dom" to explicitly fall back to DOM output if AX output exceeds the output budget. Default: none. | |
| compact | No | AX mode only: return a compact AX snapshot that keeps actionable/ref-bearing nodes, value/state nodes, and ancestors. Default: false, or true when OPENCHROME_PROFILE=fast. | |
| diagnostics | No | Include structured read_page timing diagnostics in the MCP result metadata. Default: false. | |
| include_metrics | No | When true, include approximate returned size/token metrics in the emitted payload. Default: false. | |
| boundaryMarkers | No | Wrap page-origin plaintext in <oc:page>. Default true; false disables. |