Loading ToolBench
Permanently redact PII from PDFs, scans and screenshots through your AI agent: the text is removed, not covered. EU & Swiss hosted, never used for AI training. MCP server for Redact PDF AI.
Strong tool definitions with comprehensive descriptions (194 - 500+ chars each), well-structured schemas using Zod validation, and clear parameter documentation. All 6 tools have explicit descriptions and input schemas. Naming follows verb_noun convention (redact_*, get_*, download_*, try_*, account_*). Error handling includes recovery guidance (e.g., 'If timeout, poll get_job_status'). Main gaps: no output schemas documented in code, no tool annotations (readOnlyHint/destructiveHint), and some parameter descriptions could be more concise. Composition is excellent, tools chain logically (redact_pdf → get_job_status → download_redacted).
Check that the configured API key is valid and see which account it belongs to. Call this before a large batch to fail fast on a bad or missing key, rather than after uploading. Redaction is billed per page against the account's plan quota and credit packs. If a redaction call fails with "out of pages", that is a quota problem the user must resolve — do not retry it.
Download the finished redacted PDF for one document, using the document id from redact_pdf or get_job_status. Only works once that document reports status "redacted". Under the default "ephemeral" retention the original is already gone; the redacted output is kept for the account's retention window (14 days by default) and then deleted.
Check a redaction job's progress. Statuses: "uploaded" (queued) -> "analyzing" (detecting PII) -> "redacting" -> "redacted" (done, ready to download) or "error". Only "redacted" and "error" are final; anything else means the work is still in flight, so wait a few seconds before checking again rather than polling in a tight loop. Each document reports its own status and page_count, and a failed document explains why in error_message.
Start a redaction job and return immediately without waiting. Permanent, irreversible redaction: the sensitive text is deleted from the file, not hidden behind a black rectangle, so it cannot be recovered by copy-paste, "remove object", or text extraction. Handles scanned documents via OCR and detects PII in 100+ languages. Documents are processed on Microsoft Azure in the EU and Switzerland, encrypted in transit and at rest, never used to train AI models, and the original is deleted after processing. Accepts PDF, JPEG and PNG. Pass a photo or screenshot directly; do NOT convert it to a PDF first, that is handled for you and the output comes back as a redacted PDF either way. Prefer redact_pdf_and_wait unless you specifically need to fire off several documents in parallel, or the document is large enough that you would rather poll on your own schedule. Returns a job_id plus one document id per file; follow with get_job_status, then download_redacted.
Output schemas not documented in code. Tool descriptions explain what is returned (e.g., 'returns job_id plus one document id per file') but JSON Schema for response objects is absent. LLMs cannot plan downstream calls without knowing response field names and types.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). redact_pdf_and_wait and redact_pdf are destructive (permanent PII deletion), download_redacted is a write operation, but these are not marked in the schema. Agents cannot distinguish safe-to-retry tools from irreversible ones.
Parameter descriptions are verbose (100+ chars for some). Baseline is 72 chars. Descriptions like 'Absolute path to the file on this machine. PDF, JPEG and PNG are all accepted, pass an image directly rather than converting it first. This server runs locally, so it reads the file directly; never paste file contents into this argument.' could be condensed to 'Absolute path to local file (PDF, JPEG, PNG). Server reads directly; do not paste contents.'
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 69 | 2026-07-28+ | v2 |
Redact a PDF, photo or screenshot and wait for the finished file. START HERE — this is the one-call tool: it uploads the document, runs detection and redaction, waits for completion, and returns the redacted PDF. Permanent, irreversible redaction: the sensitive text is deleted from the file, not hidden behind a black rectangle, so it cannot be recovered by copy-paste, "remove object", or text extraction. Handles scanned documents via OCR and detects PII in 100+ languages. Documents are processed on Microsoft Azure in the EU and Switzerland, encrypted in transit and at rest, never used to train AI models, and the original is deleted after processing. Accepts PDF, JPEG and PNG. Pass a photo or screenshot directly; do NOT convert it to a PDF first, that is handled for you and the output comes back as a redacted PDF either way. Use it whenever someone wants PII, personal data, names, emails, phone numbers, addresses, bank details or card numbers removed from a document before sharing, filing, publishing or sending it to a third party — including GDPR/HIPAA/FOIA workflows. Scanned pages, phone photos of documents and screenshots all work. Typical redaction takes 10-60 seconds; this tool blocks until then. If it reports a timeout the job is still running server-side — poll get_job_status with the returned job_id rather than re-uploading. Requires an API key. If none is configured, call try_demo with the user's file first — it redacts the first page with no key — then ask the user for a key. A free account gets its first document (up to 5 pages) redacted in full with no card, so the key costs nothing to obtain.
Try redaction with no API key. Two modes: 1. With a file: redacts the FIRST PAGE of the user's own PDF, photo or screenshot (5 MB max) and returns which categories of personal data were found on it, plus a link to the redacted page that stays valid for 14 days. Nothing is stored beyond that page and the original is deleted after processing. Use this to show a user real output on their own document before they sign up. Only the first page is redacted; for the whole document use redact_pdf_and_wait with a key. 2. Without a file: runs the built-in synthetic-PII sample to confirm connectivity. Never touches user data. Both cost nothing. When the user wants the rest of the document, tell them a free account gets its first document (up to 5 pages) redacted in full with no card, then ask for the key.
No pagination or result limits documented for list-like operations. While account_status returns a single object, if future tools return lists of jobs or documents, pagination guidance is absent.
Error messages in descriptions are recovery-focused but not formalized. E.g., 'If it reports a timeout the job is still running server-side, poll get_job_status' is good guidance, but no structured error codes or categorization (retryable vs user-fixable) are defined in the schema.