coverredact.com
Redact a PDF in your browser
First seen 2026-09-14 · Last seen 2026-09-14 · Source: webmcp.com
Answer 4 · Act 9 · Transact 0 · Score: Not yet scored
Tool inspector
get_redaction_result
The result of the engine run on one document: redacted (true/false), status, counts by category (detections and painted bars), tier, names_checked, not_covered, watermark, timings and the event log. It RETURNS PROMPTLY and is meant to be POLLED IN A LOOP: it blocks at most 10 seconds, then returns status "pending" with retry_after_s and a next_step. Pending is NOT a failure and NOT a reason to stop. A first run on a fresh browser needs roughly 60 seconds in total (nearly all of it a one-time ~265 MB name-model download), so EXPECT ABOUT 6 TO 8 CALLS. Do not try to cover that with one long wait - timeout_s is capped at 10 and a longer request is clamped. status is "done" or "refused" when it is final. A refused document returns {error: "needs_ocr" | "encrypted_unsupported", next_step}. In-tab, nothing uploaded; returns geometry and counts, never any text from the document. Limits: Cover redacts a document completely or not at all. Person names and the structured detections are ONE redaction that runs in two stages (the structured pass, then the ~265 MB in-page name model), not two levels you can get separately: a document whose names could not be checked is REFUSED (error daily_limit | incomplete_redaction) rather than returned partly redacted. Scanned or image-only pages are refused (error needs_ocr) and password-protected PDFs are refused (error encrypted_unsupported): OCR and passwords need the Cover Mac app, https://coverredact.com/. Downloads carry the COVER TRIAL watermark unless this browser is registered with a Cover license (https://coverredact.com/): get_status reports the page-level `watermark` and every document reports its own, so read those rather than assuming either way.
Page: /
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
document_id |
string | yes | document_id from get_status (e.g. "doc-1"). |
wait |
boolean | no | Wait for the run to finish (default true). |
wait_for_names |
boolean | no | When waiting, wait for the names tier too, not just the structured tier (default true). |
timeout_s |
integer | no | Seconds to block before returning status "pending" (default 10, max 10). This tool NEVER blocks longer than that: poll it repeatedly instead of asking for one long wait. |
Raw JSON schema
{
"type": "object",
"properties": {
"document_id": {
"type": "string",
"description": "document_id from get_status (e.g. \"doc-1\")."
},
"wait": {
"type": "boolean",
"description": "Wait for the run to finish (default true)."
},
"wait_for_names": {
"type": "boolean",
"description": "When waiting, wait for the names tier too, not just the structured tier (default true)."
},
"timeout_s": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"description": "Seconds to block before returning status \"pending\" (default 10, max 10). This tool NEVER blocks longer than that: poll it repeatedly instead of asking for one long wait."
}
},
"required": [
"document_id"
],
"additionalProperties": false
}
Similar websites
eworker.ca
E-Worker is business infrastructure powered by AI, with focused apps and connected business work.
urban-planning-copilot.heisenbug.in
Urban Planning Copilot
vide.zerdalu.com
Vide
labspace-agent-twin.onrender.com
LabSpace Atlas — design laboratories, index exact locations, and let a browser agent plan, audit, and navigate the spatial twin.