Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.omitly/omitly-mcp

NPM · OMITLY-MCP

Omitly's local, verifiable PDF redaction for AI agents — your documents never leave your device.

Available components

−1 this week 82 Trust /100

Last scanned (16 hours ago)

Scores higher than 71% of npm servers

Category Documents and Files

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 33 of 99 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
  • Actively maintained (last published 1 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 4752 tokens (~250/item across 19 items; 18 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • License in Provenance & TransparencyLicence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 0
    • Stability: 0.97 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Stability: 0.97 → pass security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • First check of Capabilities: pass functional
    • Package version: 5.5.0 → 5.6.2 functional
    • Package version: 5.5.0 → 5.6.1 functional
  • 17 Nov 26 −1
    • Stability: pass → 0.93 functional
  • 11 Nov 26 +1
    • Stability: 0.97 → pass security
    • Schema quality: 3424 → 4647 ▼ functional
    • Destructive annotations: pass → 100 functional
    • Package version: 5.4.0 → 5.5.0 functional
  • 9 Nov 26 +8
    • Stability: 0.90 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Source repository: unverified → pass ▲ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: 100 functional
    • First check of Schema quality: unverified functional
    • Package version: 5.3.0 → 5.4.0 functional
  • 8 Nov 26 −5
    • Provenance: pass → unverified ▼ security
  • 7 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Nov 26 −2
    • Stability: pass → 0.80 functional
  • 4 Nov 26 +25
    • Malware scan: unverified → pass ▲ security
    • Known CVEs: unverified → pass ▲ security
    • Dependency health: unverified → 0.85 ▲ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/omitly-mcp@5.6.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 99 packages
Packages resolved 99
Stale 33
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 18 exposed · ~4,731 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_license ~224

Report 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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
daysLeft–yes–
deviceBoundbooleanyes–
expiresAtstring|nullyes–
licensedTostring|nullyes–
provenanceAvailablebooleanyes–
reasonstring|nullyes–
renewalNoticestring|nullyes–
resolutionStepstring|nullyes–
statestringyes–
tier–yes–

No examples provided.

check_redaction ~513

Audit 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 carry a short notice that the check removes nothing and is not a removal certificate; there is no usage limit. `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. `clean` is a scan fact (the pattern scan listed nothing), not a verdict. The result also carries `verdict`, the engine's presented-document check as 'needs_review' or 'cannot_verify' (or 'safe_to_send' only beside a pass), which covers hidden, covered and recoverable content (text under boxes, metadata, layers, attachments, earlier versions, comments, alternate text). `outcome` is the only verdict field. `safe_to_send` is given only when the engine's check passed, the scan read the whole file and found nothing, and the file's own seal or report played no part. `needs_review`, `not_a_pass` and `incomplete` are not passe…

NameTypeReqDescription
pdfPathstringyesabsolute path to the supposedly-redacted PDF to audit
NameTypeReqDescription
byKindobjectyes–
cleanbooleanyes–
coverageobjectyes–
evaluationboolean––
offPagearrayyes–
outcomestringyes–
regionsarrayyes–
scanCompletebooleanyes–
survivorsarrayyes–
totalFindingsintegeryes–
verdictobjectyes–

No examples provided.

create_pdf ~184

Generate 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.

NameTypeReqDescription
cssstring–extra CSS appended after the default print styles
formatstring–input format (default: markdown)
outputPathstringyesabsolute path to write the PDF
sourcestring–inline Markdown/HTML (omit if using sourcePath)
sourcePathstring–absolute path to a Markdown/HTML file
titlestring–document <title> / metadata
NameTypeReqDescription
outputstringyes–

No examples provided.

edit_pages ~341

Reorder, 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.

NameTypeReqDescription
outputPathstringyesnew .pdf to create; must not exist
pagesarrayyesthe final page list
pdfPathstringyespath to the PDF, inside the allowed folder
NameTypeReqDescription
byteSizeintegeryes–
layoutarrayyes–
lostarrayyes–
outputPathstringyes–
pageCountintegeryes–
warningsarrayyes–

No examples provided.

extract_pages ~257

Copy 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.

NameTypeReqDescription
outputPathstringyesnew .pdf to create; must not exist
pagesarrayyespages to keep, 1-based, in output order
pdfPathstringyespath to the PDF, inside the allowed folder
NameTypeReqDescription
byteSizeintegeryes–
lostarrayyes–
outputPathstringyes–
pageCountintegeryes–
sourcePagesarrayyes–
warningsarrayyes–

No examples provided.

extract_pdf_text ~471

Extract 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.

NameTypeReqDescription
maskedboolean–false is an explicit opt-in to RAW (unmasked) text — the raw PII values will then appear verbatim in this response. Omit, or pass true, for the default masked behaviour.
pdfPathstringyesabsolute path to the PDF to extract text from
regionsarray–narrow which PII kinds are detected/masked to these regional packs (generic kinds like email/card always apply regardless); omit to scan everything — the safe default
NameTypeReqDescription
maskedbooleanyes–
notestring––
pagesarrayyes–

No examples provided.

find_sensitive_regions ~333

Scan 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 carry a short notice that the scan removes nothing; there is no usage limit.

NameTypeReqDescription
pdfPathstringyesabsolute path to the PDF to scan
regionsarray–narrow LISTED pattern kinds to these regional packs (generic kinds always listed; confirmed under-mark survivors always report); omit to scan everything — the safe default
NameTypeReqDescription
analysisIdstring––
countintegeryes–
evaluationboolean––
notestring––
outcomestringyes–
regionsarrayyes–
scanCompletebooleanyes–

No examples provided.

get_proposal_status ~88

Report 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 and sealed by the desktop app, with the output path and verdict), failed, or expired. Free; reads no document.

NameTypeReqDescription
proposalIdstringyesthe proposalId returned when the proposal was queued
NameTypeReqDescription
createdAtstring|nullyes–
decidedRevisionstring|nullyes–
notestring|nullyes–
outputstring|nullyes–
proposalIdstringyes–
recordedByDesktopstring|nullyes–
resolvedAtstring|nullyes–
statusstringyes–
tool–yes–
unverifiedboolean––

No examples provided.

locate_text ~145

Locate 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.

NameTypeReqDescription
pdfPathstringyesabsolute path to the PDF to search
textsarrayyesliteral strings to locate
NameTypeReqDescription
analysisIdstring––
countintegeryes–
regionsarrayyes–

No examples provided.

merge_pdfs ~187

Join 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.

NameTypeReqDescription
inputsarrayyesPDFs to join, in order
outputPathstringyesnew .pdf to create; must not exist
NameTypeReqDescription
byteSizeintegeryes–
lostarrayyes–
outputPathstringyes–
pageCountintegeryes–
sourcesarrayyes–
warningsarrayyes–

No examples provided.

pdf_info ~128

Read 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.

NameTypeReqDescription
pdfPathstringyespath to the PDF, inside the allowed folder
NameTypeReqDescription
byteSizeintegeryes–
encryptedboolean|nullyes–
formFieldCount–yes–
hasCommentsboolean|nullyes–
hasFormboolean|nullyes–
hasLayersboolean|nullyes–
hasSignaturesboolean|nullyes–
hasXfa–yes–
pageCountintegeryes–
pagesarrayyes–
pagesTruncatedbooleanyes–

No examples provided.

propose_redactions ~308

Propose 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, checks the file for copies left behind 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 (a region `reason` may not be AI_PROPOSAL, MANUAL or OCR_CORRECTED: those words are reserved for what a person decides, and the request is refused). The regions must come from a scan of this document: pass the analysisId that find_sensitive_regions or locate_text returned with them. Nothing is uploaded.

NameTypeReqDescription
analysisIdstring–the analysisId returned by find_sensitive_regions or locate_text for THIS document; required when the Omitly desktop app is running and the regions would be queued for a person to accept (it ties the…
outputPathstringyesyour suggested path for the redacted PDF; the person picks the real one in Omitly's save dialog
pdfPathstringyesabsolute path to the source PDF
regionsarrayyesregions proposed for removal
NameTypeReqDescription
clientobjectyes–
notestringyes–
pdfPathstringyes–
proposalIdstringyes–
revisionstringyes–
statusstringyes–
toolstringyes–

No examples provided.

redact_by_entity ~233

Find 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.

NameTypeReqDescription
drawBoxboolean–also paint a black bar (default: opaque fill only)
kindsarray–entity kinds to redact; omit to redact all detected
outputPathstringyesabsolute path to write the redacted PDF
pdfPathstringyesabsolute path to the source PDF
regionsarray–narrow to these regional packs (intersects with `kinds`); omit for all
NameTypeReqDescription
clientobject––
engineAudit–––
notestring––
outcomestring––
outputstring|null––
pdfPathstring––
proposalIdstring––
redactedarray––
redactedCountinteger––
revisionstring––
statusstringyes–
toolstring––

No examples provided.

redact_pdf ~229

Redact regions of a PDF on-device using Omitly. Removes the underlying text and image data (not a black box over it), checks the file for copies of the removed text that editing software leaves behind, and returns a signed audit log. The file is never uploaded — redaction happens locally. A region's `reason` is your own audit label (e.g. 'PII: SSN'); the words AI_PROPOSAL, MANUAL and OCR_CORRECTED are reserved for what a person decided in the Omitly app, and a request using one is refused whole, with nothing written.

NameTypeReqDescription
analysisIdstring–the analysisId returned by find_sensitive_regions or locate_text for THIS document; required when the Omitly desktop app is running and the regions would be queued for a person to accept (it ties the…
outputPathstringyesabsolute path to write the redacted PDF
pdfPathstringyesabsolute path to the source PDF
regionsarrayyesregions to remove
NameTypeReqDescription
clientobject––
engineAuditobject––
notestring––
outcomestring––
outputstring––
pdfPathstring––
proposalIdstring––
regionCountinteger––
revisionstring––
statusstringyes–
toolstring––

No examples provided.

split_pdf ~310

Split 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.

NameTypeReqDescription
outputDirstringyesexisting folder inside the allowed folder (the allowed folder itself is fine)
pdfPathstringyespath to the PDF, inside the allowed folder
prefixstringyesfile name prefix: letters, digits, . _ -, up to 64
rangesarrayyesone page spec per output file
NameTypeReqDescription
filesarrayyes–
lostarrayyes–
warningsarrayyes–

No examples provided.

verify_document ~235

Reports whether a received PDF's embedded Omitly audit report and whole-file seal still verify (v1: Ed25519; v2: ML-DSA-87 with ECDSA P-384) — on-device, needs the native engine, no licence required. A seal shows integrity, not origin, and is not a check of the content: the signing key travels with the file, so a valid seal means 'unchanged since sealed by the holder of this key', never 'produced by Omitly', and anyone can seal a file with their own key. This tool never gives `safe_to_send`; for the content, run `check_redaction`. A `seal_unsupported_version` verdict means this verifier is too old to check the seal at all; update the verifier rather than trusting or rejecting the file on that basis. `outcome` is the only verdict field; isError false does not mean the file is safe. isError true means the check could not run.

NameTypeReqDescription
pdfPathstringyesabsolute path to the PDF to check for an Omitly audit report and seal
NameTypeReqDescription
embeddedReport–yes–
outcomestringyes–
sealobjectyes–

No examples provided.

verify_redaction ~216

Re-scan an already-redacted PDF on-device and report whether anything recoverable is still found. 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.

NameTypeReqDescription
pdfPathstringyesabsolute path to the redacted PDF to verify
NameTypeReqDescription
cleanbooleanyes–
findingsarrayyes–
modestringyes–
outcomestringyes–
scanCompletebooleanyes–
sidecarobject––
totalFindingsintegeryes–
verdictobjectyes–

No examples provided.

verify_seal ~329

Verify 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. `outcome` is the only verdict field and a seal tool never gives `safe_to_send`: a seal is integrity, not a check of the content (run `check_redaction`). isError false does not mean the file is safe. isError true means the check could not run.

NameTypeReqDescription
pdfPathstringyesabsolute path to the PDF to check for an Omitly audit report and seal
NameTypeReqDescription
embeddedReport–yes–
outcomestringyes–
sealobjectyes–

No examples provided.

Install

How do I install the io.github.omitly/omitly-mcp server?

io.github.omitly/omitly-mcp runs locally as an npm package, launched with npx -y omitly-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · omitly-mcp

# add to Claude Code
claude mcp add omitly-omitly-mcp -- npx -y omitly-mcp
Common questions

What is the io.github.omitly/omitly-mcp server?

io.github.omitly/omitly-mcp is listed in the public MCP registry as io.github.omitly/omitly-mcp. Omitly's local, verifiable PDF redaction for AI agents, your documents never leave your device. This page covers its npm package (omitly-mcp).

Is the io.github.omitly/omitly-mcp server safe to use?

io.github.omitly/omitly-mcp scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.omitly/omitly-mcp server expose?

io.github.omitly/omitly-mcp exposes 18 tools: find_sensitive_regions, locate_text, redact_by_entity, redact_pdf, verify_redaction, and 13 more. Their descriptions and schemas cost roughly 4,731 tokens of context every time the server is loaded.

Is the io.github.omitly/omitly-mcp server still maintained?

io.github.omitly/omitly-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the io.github.omitly/omitly-mcp server?

VerifyMCP ran 16 checks on io.github.omitly/omitly-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. One item could not be completed, a gap on our side rather than a finding about io.github.omitly/omitly-mcp: License. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.