All servers / Docs / Omitly MCP server
Omitly MCP server
Model Context Protocol server exposing Omitly's local, verifiable PDF redaction to AI agents. Redaction runs on-device — documents are never uploaded.
Tested by ConnectATDScore 86 out of 100. Tested 2026-11-19 on package version 5.5.0. Package: omitly-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 8 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (3.8 seconds including download)
- Tools offered: 18
- Last published: 2026-11-11
- Weekly downloads (npm): 577
- License: SEE LICENSE IN LICENSE · Direct dependencies: 3
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
find_sensitive_regions2 of 2 parameters describedScan a PDF on-device and return candidate regions that look like PII — emails, US SSNs, phone numbers, card numbers, and Australian identifiers (TFN, ABN, ACN, Medicare, Centrelink CRN, IHI, BSB; kinds 'tfn'/'abn'/'acn'/'medicare'/'crn'/'ihi'/'bsb') — each with the page and exact coordinates (in PDF points) the redaction engine needs. Use this FIRST so you select regions by entity ('redact every TFN') and pass the returned coordinates straight to redact_pdf, instead of guessing geometry from a rendered page. Numeric kinds are check-digit validated where a published algorithm exists (CRN has none — its matches are format-only). Candidates are best-effort pattern matches for review — not a completeness guarantee and not a compliance assessment; the file is never uploaded — detection runs locally. Each candidate carries a MASKED preview (e.g. '•••-••-6789'), never the raw value: the secret stays on the machine. You don't need the plaintext to redact — drive it by page + coordinates. (A human reviewer has the file open locally for full context.) Free tier (no native engine): results are EVALUATION-marked and limited (by default) to 10 attempts a month, shared with check_redaction and counted locally — past the cap this tool returns a structured 'free-cap' refusal. A configured native engine is not capped.
locate_text2 of 2 parameters describedLocate exact text strings in a PDF and return each occurrence's page and coordinates (in PDF points). Use this for what pattern-matching can't catch — names, addresses, account references — by doing the entity recognition YOURSELF and passing the literal strings here; the engine resolves where they sit so you never guess geometry from a rendered page. Feed the returned regions straight to redact_pdf. Case-insensitive; a string the PDF splits across text operators may not match as one run. Each hit returns a masked preview, not the raw text. Nothing is uploaded.
redact_by_entity5 of 5 parameters describedFind and redact PII in a PDF in ONE on-device step: scan, keep only the requested entity kinds (email/ssn/phone/card plus the Australian tfn/abn/acn/medicare/crn/ihi/bsb — omit `kinds` to redact every kind detected), remove them, verify, and return what was redacted plus the audit log. This is the 'just scrub the obvious PII' shortcut; when you need to review before removing, call find_sensitive_regions first. Same caveat as the detector: matches are best-effort pattern matching, not a completeness guarantee and not a compliance assessment. Nothing is uploaded.
redact_pdf3 of 3 parameters describedPermanently redact regions of a PDF on-device using Omitly. Removes the underlying text and image data (not a black box over it), verifies nothing survives in each region, and returns a signed audit log. The file is never uploaded — redaction happens locally.
verify_redaction1 of 1 parameter describedRe-scan an already-redacted PDF on-device and confirm nothing recoverable remains. With a configured native engine and this file's own `<path>.audit.json` sidecar (written by redact_pdf/redact_by_entity), this re-checks exactly the regions that were redacted — the strongest form of this check. Without a native engine (or without that sidecar — e.g. the file wasn't redacted by this tool), it falls back to a general on-device re-scan of the whole file and reports whether anything is still detectable — a good-faith re-check, not a claim of the same rigor as the sidecar-based path. This is a self-check for the person who just redacted, typically the one holding the sidecar file — a third-party recipient who only has the delivered PDF should use `verify_document` instead, which checks the embedded audit report and seal rather than re-scanning region bytes.
check_licenseno parametersReport Omitly's current licence or trial state on this machine — free, takes no arguments, and reads no document. Use it to answer 'am I licensed?', to see how many trial days are left, or to confirm a licence the user just saved has been picked up. Re-resolved on EVERY call, so buy → save the licence file → call again works without restarting this server. Reports which resolution step supplied the licence (OMITLY_LICENSE_FILE, the activated desktop licence, or the import inbox ~/.omitly/omitly.license), the tier, the vendor-signed licensee name, whether the licence is bound to this one machine, and whether this build can make licensed-provenance claims at all. It deliberately NEVER returns the device fingerprint (a stable machine identifier) or the licence file's contents — 'device-bound' is reported as a yes/no. Requires a configured native engine (OMITLY_ENGINE_DIR/OMITLY_REDACT_BIN): the wasm free tier has no licence concept, so there is nothing to report without one.
verify_seal1 of 1 parameter describedVerify a PDF's embedded Omitly audit report and whole-file tamper-evidence seal (v1: Ed25519; v2: ML-DSA-87 with ECDSA P-384) — on-device, nothing uploaded. Distinct from `verify_redaction`: that tool re-checks whether redacted regions are still empty; this tool cryptographically checks whether the delivered bytes have changed since they were sealed. The seal proves INTEGRITY, NOT IDENTITY: the signing key travels with the file (per-install, or one-time for a single output), so a valid seal means 'unchanged since sealed by the holder of this key', never 'produced by Omitly'. Compare `sealFingerprint` out-of-band against the fingerprint the sender published if origin matters. Requires a configured native engine — there is no wasm seal-verification path, so this always needs OMITLY_ENGINE_DIR/OMITLY_REDACT_BIN. A `seal_unsupported_version` verdict means this verifier is too old to check the seal at all — that is neither a pass nor a fail; update the verifier rather than trusting or rejecting the file on that basis.
verify_document1 of 1 parameter describedRecipient trust-verification: for someone who RECEIVED a PDF from someone else and wants to confirm it's an authentic, unaltered Omitly output — needs the native engine; no licence required. Confirms the embedded audit report and whole-file tamper-evidence seal (v1: Ed25519; v2: ML-DSA-87 with ECDSA P-384) are valid and unaltered since sealing, and reports the seal's own attested verdict — this does not independently re-scan the document for residual PII. For that self-check (typically run by the person who just redacted, not a recipient), use `verify_redaction` instead. The seal proves INTEGRITY, NOT IDENTITY: the signing key travels with the file (per-install, or one-time for a single output), so a valid seal means 'unchanged since sealed by the holder of this key', never 'produced by Omitly' — compare `sealFingerprint` out-of-band against the fingerprint the sender published if origin matters. Currently requires a configured native engine (OMITLY_ENGINE_DIR/OMITLY_REDACT_BIN) — there is no wasm seal-verification path yet (tracked in issue #113), so a recipient running only `npx omitly-mcp` with no engine installed cannot use this tool until that lands. A `seal_unsupported_version` verdict means this verifier is too old to check the seal at all — that is neither a pass nor a fail; update the verifier rather than trusting or rejecting the file on that basis.
create_pdf6 of 6 parameters describedGenerate a clean PDF from Markdown (or raw HTML) on-device, rendered through a real browser engine so it looks printed — not like a script's best guess. Give it Markdown inline via `source` (or a file via `sourcePath`) and an `outputPath`; it writes the PDF and returns the path. Use this instead of writing a one-off reportlab/LaTeX/pandoc script. Nothing is uploaded.
check_redaction1 of 1 parameter describedAudit an ALREADY-redacted PDF and report whether sensitive text still survives underneath the redaction — the 'did my black boxes actually remove the data?' check. Most tools redact by drawing a rectangle over text while leaving the characters in the file, where they stay selectable and extractable. This re-extracts the text on-device and flags any emails, SSNs, phone or card numbers that are still present, each with a MASKED preview — the raw value never leaves the machine. It checks the page text layer, text surviving UNDER redaction marks, incremental-update prior revisions (the classic 'redacted then saved, original still in the file' failure), document metadata, AcroForm field values and embedded attachments, and returns a coverage report so a clean result is scoped to what was inspected. A non-empty result means the redaction leaked. Nothing is uploaded. (Pattern-based: names/addresses, image-only text, and the surfaces listed as not-inspected aren't covered; absence of hits isn't proof of completeness.) Free tier (no native engine): reports are EVALUATION-marked — for evaluation, not production reliance — and limited (by default) to 10 attempts a month, shared with find_sensitive_regions and counted locally; past the cap this tool returns a structured 'free-cap' refusal. A configured native engine is not capped. `scanComplete` is false when some page or stream could not be read; then `clean` only means nothing was found in what WAS read (possibly nothing) and the text leads with an INCOMPLETE SCAN warning — never report such a result as clean. The result also carries `verdict`: the same presented-document check the Omitly desktop app's 'Check any PDF' runs, as one of three verdicts about THE CHECK — 'safe_to_send' (every check that applies to this file passed, within what the check covers; `verdict.result.notChecked` lists what it did not), 'needs_review' (something needs a person to look before sending; `blocking` true means a problem such as recoverable text under a box was found), or 'cannot_verify' (the check could not complete, so no verdict is given). The verdict covers hidden, covered and recoverable content (text under boxes, metadata, layers, attachments, earlier versions, comments, alternate text); it does not judge whether VISIBLE text should be there — the pattern findings above do — so a visible identifier can be a finding while the verdict is 'safe_to_send'. None of the verdicts is a statement that the document is safe. The full audit v2 report behind the verdict is not returned here; it is available from the engine's `check` command (`omitly-redact`) and the desktop app.
extract_pdf_text3 of 3 parameters describedExtract a PDF's text, page by page, for reading or summarizing — PII-MASKED BY DEFAULT, so detected emails, SSNs, phone/card numbers and Australian identifiers (TFN/ABN/ACN/Medicare/CRN/IHI/BSB) never flood your context window as raw values. Each page returns its (masked, unless you opt out) text plus 'spans': the CHAR offset (not byte offset — matters for any non-ASCII text) of every detected PII value with its kind, so you can still reason about WHERE something was found even though the value itself reads as a masked preview (e.g. '•••-••-6789'). Pass 'masked: false' ONLY when you deliberately need the raw text for genuine content review and understand the raw PII values will then appear verbatim in this response and in your context — that is the explicit, documented opt-in this tool requires; the default is always masked. A page whose text could not be fully read (a corrupt or size-capped content stream, or characters whose meaning the font does not define) reports 'contentDecoded: false' rather than being silently skipped or counted as blank; any text that was read is still returned, so treat that page as incomplete, not as the whole page. Does NOT render pages to images — text only. Free tier, no licence required; works zero-install via the bundled wasm engine, same as find_sensitive_regions/locate_text/check_redaction/verify_redaction — a configured native engine (OMITLY_ENGINE_DIR) is preferred when available (also enables the 'regions' filter, wasm-only ignores it and scans every pattern) but not required. The file is never uploaded: extraction runs entirely on-device.
propose_redactions3 of 3 parameters describedPropose regions to redact for a PERSON to accept in the Omitly desktop app (omitly#1643, bring your own AI). The explicit, preferred form for agents working alongside a lawyer: nothing is written by this call. The desktop app shows the proposal, the person accepts or rejects, and on acceptance Omitly removes the content, verifies nothing survives and seals the output with a record that a person decided. Requires the Omitly desktop app to be running on this computer; use get_proposal_status to follow the outcome. Same inputs as redact_pdf. Nothing is uploaded.
get_proposal_status1 of 1 parameter describedReport what happened to a proposal queued by propose_redactions (or by redact_pdf / redact_by_entity while accept-in-app was on): pending, accepted, rejected, applied (removed, verified and sealed by the desktop app, with the output path and verdict), failed, or expired. Free; reads no document.
pdf_info1 of 1 parameter describedRead basic facts about a PDF without opening it in a viewer: page count, each page's size and rotation (first 500 pages), and flags for encryption, forms, signatures, comments, XFA and layers. Returns counts and flags only, never text or field values. Works on encrypted files (reports encrypted: true). Page numbers start at 1 (the check tools return 0-based `page` values: add 1). Example: {"pdfPath":"invoice.pdf"}. Nothing is uploaded.
merge_pdfs2 of 2 parameters describedJoin 2 to 50 PDFs, in the order given, into one new PDF. All pages of every input are kept. Writes a NEW .pdf inside the allowed folder and never changes or overwrites an existing file. Form fields are kept (a clashing field name is renamed, with a warning). The result starts from an empty document, so bookmarks, document metadata, page labels and layers are not carried over; they are listed in `lost`. Digital signatures are removed (the output is a new, unsigned document). Example: {"inputs":["a.pdf","b.pdf"],"outputPath":"merged.pdf"}. This is not redaction and does not sanitise. Use redact_pdf to remove sensitive content. Nothing is uploaded.
extract_pages3 of 3 parameters describedCopy chosen pages of a PDF into one new PDF, in the order listed. Page numbers start at 1 (the check tools return 0-based `page` values: add 1). Writes a NEW .pdf inside the allowed folder and never changes or overwrites an existing file. Pages are an array of numbers and ranges; a page may not be listed twice. Bookmarks to kept pages, metadata and form fields on kept pages are kept; layers and static XFA are dropped (listed in `lost`). Digital signatures are removed. A dynamic XFA form or an encrypted PDF is refused. Example: {"pdfPath":"report.pdf","pages":[1,"3-5"],"outputPath":"report-part.pdf"}. This is not redaction and does not sanitise: pages you leave out are not copied, but document metadata, bookmark titles and anything a kept page shares with an omitted page can remain. Use redact_pdf to remove sensitive content. Nothing is uploaded.
split_pdf4 of 4 parameters describedSplit a PDF into several new PDFs, one per range. Page numbers start at 1 (the check tools return 0-based `page` values: add 1). Each range is a page spec (numbers and ranges) of consecutive pages in order, such as ["1-3"] or [4,5]; each file is named `<prefix>-p<first>-<last>.pdf` (or `<prefix>-p<first>.pdf` for one page) inside `outputDir`. All files are created or none are. Writes a NEW .pdf inside the allowed folder and never changes or overwrites an existing file. Layers and static XFA are dropped (listed in `lost`); digital signatures are removed. Example: {"pdfPath":"book.pdf","ranges":[["1-10"],["11-20"]],"outputDir":"parts","prefix":"book"}. This is not redaction and does not sanitise: pages you leave out are not copied, but document metadata, bookmark titles and anything a kept page shares with an omitted page can remain. Use redact_pdf to remove sensitive content. Nothing is uploaded.
edit_pages3 of 3 parameters describedReorder, delete, rotate and insert blank pages in one step by giving the FINAL page list. Each entry is `{"source": n, "rotate": 0|90|180|270}` (n is a page of the ORIGINAL document, 1-based) or `{"blank": true, "size": "previous"|"A4"|"Letter"}`. A page you leave out is deleted; the list order is the new order; a source page may appear only once; at least one entry must be a source page. Page numbers start at 1 (the check tools return 0-based `page` values: add 1). Writes a NEW .pdf inside the allowed folder and never changes or overwrites an existing file. Page labels are removed when pages are reordered or a blank is inserted; layers and static XFA are dropped (listed in `lost`); digital signatures are removed. `layout` in the result says where each output page came from. Example: {"pdfPath":"deck.pdf","pages":[{"source":2},{"source":1,"rotate":90},{"blank":true}],"outputPath":"deck-edited.pdf"}. This is not redaction and does not sanitise: pages you leave out are not copied, but document metadata, bookmark titles and anything a kept page shares with an omitted page can remain. Use redact_pdf to remove sensitive content. Nothing is uploaded.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.