mcp server

OpenWarrant — Document Verification Suite

Document forensics: tamper/AI checks, extract, identity, PII, adverse media. No API key needed.

Description as published by the maintainer. Source

• version 0.2.2
• active
• data extraction
• document understanding

active — Registry entry last updated 2026-07-23. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

12 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

check_document(sha256)

Cheap cache-check: has this exact document already been inspected? Hash the file yourself (sha256, lowercase hex) and call this before verify_document to skip a redundant (paid) inspection. Returns {cached, warrant_id, permalink}. Required: sha256.

check_pack(scheme, documents, requirements)

Check whether a SET of documents satisfies a checklist — completeness, cheaply. USE THIS WHEN you have an application / onboarding pack and need "do we have the required documents, and what's still missing?" Each document is CLASSIFIED (one cheap page-1 read — never full field extraction or multi-page), then matched against the checklist's required slots. (For "is a document genuine?" use verify_document; to identify ONE document use classify_document; for the identity gate use verify_identity.) Define the checklist ONE of two ways: - `scheme`: a named preset — "income_proof", "lending_prequal", "rental_application". - `requirements`: an ad-hoc checklist — a list of document-type names like ["payslip","bank_statement"], or objects {"key":..., "accepts":[types], "optional":bool}. `documents` is a list (up to 12), each ONE of: {"url": "https://..."} (public link, fetched server-side) or {"bytes_b64": "...", "filename": "statement.pdf"} (inline). Returns `{complete, slots[] (key, satisfied, matched), missing[], documents[] (filename, classified_type), unmatched_documents[]}`. COVERAGE, not approval — that the right document TYPES are present, NOT that any is genuine (run verify_document) or that an application is approved. Documents are never stored. Required: documents.

classify_document(url, filename, bytes_b64)

Classify a FINANCIAL document's type and issuing country. Specialised in financial-services documents: payslip, tax_invoice, bank_statement, salary_certificate, payg_summary, receipt. USE THIS WHEN someone shares a document (or a link to one) and asks: what kind of document is this? is this a payslip / invoice / bank statement? route this document. Also use it as the FIRST step before verify_document, so the right checks run. Provide the document ONE way: `url` (a public http(s) link to a PDF or image — fetched server-side, the cheapest call) OR `bytes_b64` (inline base64, plus `filename` for PDF-vs-image routing). Returns `{document_type, country_code, confidence, is_financial_document, evidence, ...}`. HONEST SCOPE: type classification only — NOT an authenticity or fraud judgment (use verify_document for that). Below the confidence threshold it abstains with 'unknown' rather than guessing; non-financial documents classify as 'other'. The document is never stored.

detect_ai_text(url, text, filename, bytes_b64)

Estimate the PROBABILITY that a document's text was AI-GENERATED (LLM-written prose). USE THIS WHEN someone shares prose — an essay, cover letter, article, review, application, or report (or a link to one) — and asks: did an AI / ChatGPT write this? is this human-written? detect AI text. Provide the document ONE way: `text` (pasted markdown/plain prose), `url` (a public http(s) link to a page or PDF — fetched server-side, the cheapest call), OR `bytes_b64` (a base64 PDF/file, plus `filename` for routing). Returns `{probability, lean, tells, reasoning, applicable}`. HONEST SCOPE: the probability is the model's CONFIDENCE, not a calibrated truth — it can false-flag templated/coached or non-native-English writing. It works on PROSE only: for a form/table/numeric document (payslip, statement) it returns `applicable: false` and abstains, because AI-text detection false-positives badly there — use `verify_document` (the authenticity engine) for those, and `verify_references` to check a doc's citations/claims.

extract_fields(url, fields, country, filename, template, bytes_b64, max_pages)

Extract structured FIELDS from a document (PDF or image) with a vision model. USE THIS WHEN you need specific values OUT of a document — a payslip's gross/net, an invoice's total/ABN, a form's checkboxes, a table's cells — rather than a yes/no about the document. (For "is this genuine?" use verify_document; for "what kind of document is this?" classify_document.) Say WHAT to pull, four ways: - `fields`: an ad-hoc list — names like ["gross_pay","abn"], or objects {"name":..., "type":"text|amount|date|boolean", "description":...}. THE general case: ask for exactly the fields your task needs. Use type "boolean" for a checkbox/tickbox. - `template`: a named preset — "payslip", "tax_invoice", "bank_statement", "receipt". - NEITHER: AUTO — the document is classified and that type's fields are used. - auto on an unrecognised type: schema-free — every labelled field is returned. Provide the document ONE way: `url` (a public http(s) link — fetched server-side, the cheapest call) OR `bytes_b64` (inline base64, plus `filename` for PDF-vs-image routing). `country` is an optional hint; `max_pages` caps how many pages are read (default a few; hard ceiling 10). Returns `{mode, document_type, fields{name:{value,confidence,page}}, not_found, pages_read, page_limit}`. EXTRACTION, not verification — values are what the document SHOWS, not proof it is genuine. A field that isn't clearly present comes back in `not_found` (it abstains rather than guessing). The document is never stored.

get_warrant(warrant_id, as_markdown)

Retrieve a stored warrant by id (e.g. 'warrant_<hex>') — the full bundle as JSON, or a human-readable Markdown report when as_markdown=True. USE THIS WHEN you have a warrant_id from an earlier verify_document / check_document call and need the FULL evidence — every signal that fired, per-page findings, provenance — rather than the summary the original call returned. Use as_markdown=True to get a report you can show a human verbatim. Required: warrant_id.

redact_pii(url, filename, bytes_b64, max_pages)

Detect and MASK personally identifiable information in a document (PDF or image). USE THIS WHEN you need to know what PII a document contains, or to get a redacted copy before forwarding / logging / passing it to another model. Two layers: a deterministic regex+checksum pass for structured identifiers (emails, payment cards, SSN, PAN, ABN) and a vision model for the unstructured PII — names, addresses, dates of birth, phone numbers, and photo/signature presence. Provide the document ONE way: `url` (a public http(s) link, fetched server-side) or `bytes_b64` (inline base64, plus `filename`). `max_pages` caps how many pages are read (default a few; ceiling 10). Returns `{pii_found, by_type, items[] (type, masked preview, method), redacted_text, has_photo, has_signature}`. Values are MASKED in the response — the raw PII is never returned. DETECTION coverage, not a guarantee: it may miss PII or over-flag, so review before relying on it for compliance. The document is never stored.

screen_adverse_media(dob, url, name, role, aliases, country, employer, filename, bytes_b64)

Screen a person or organisation for ADVERSE MEDIA and SANCTIONS/PEP exposure (KYC/AML). USE THIS WHEN onboarding or due-diligence asks: does this subject appear in negative news (fraud, money laundering, bribery, sanctions, trafficking, enforcement action), or on a sanctions / politically-exposed-person list? Pairs naturally after verify_identity. Identify the subject ONE of two ways: pass `name` (plus any of `dob` as YYYY-MM-DD, `country`, `aliases`, `employer`, `role` — these sharpen matching and cut same-name false positives), OR pass an identity document via `url`/`bytes_b64` (+`filename`) and the subject is read from it. Returns `{subject, sanctions{...}, adverse_media{...}, risk_flag, headline, limitations}`: sanctions candidates are corroboration-gated (a name-only hit is `possible`, NEVER confirmed — one common name matches several different people); media hits are entity-disambiguated and classified, with same-name articles surfaced under `excluded`. This is screening COVERAGE, not a determination — a hit means "review this", not "guilty"; "nothing found" is not a clean record. Stateless — nothing is stored.

submit_feedback(note, verdict, warrant_id)

Record thumbs up/down on a warrant's rating (the engine's precision-flywheel label source). verdict must be 'up' or 'down'; note is optional free text. USE THIS WHEN the ground truth became known after a verify_document call — e.g. the document was later confirmed genuine or fraudulent — so the engine learns from the outcome. Tell it what happened; it sharpens future inspections for everyone. Required: warrant_id, verdict.

verify_document(url, fresh, filename, bytes_b64)

Forensically inspect a document (PDF or image) for authenticity: tampering signs, AI-generation indicators, arithmetic reconciliation (financial docs), and provenance. USE THIS WHEN someone shares a payslip, bank statement, invoice, receipt, ID, certificate, or contract and asks: is this genuine / real / authentic? has it been edited, doctored, or photoshopped? can I trust this file? (For "did an AI *write* this prose" use detect_ai_text on /mcp-aitext; for "are this report's citations real" use verify_references on /mcp-verify.) Provide the document ONE way: `url` (a public http(s) link — fetched server-side, the cheapest call: no need to download or encode anything) OR `bytes_b64` (inline base64, plus `filename` so PDF-vs-image routing is right). Returns the headline result — `risk_band` (low/medium/high/insufficient/error), `inspection_quality` (coverage, orthogonal to risk), `recommended_action`, a `summary`, the RISK-axis `risk_findings`, and a shareable `permalink`. This is a SIGNAL, not a fraud verdict — a human or agent adjudicates. Use `get_warrant(warrant_id)` for the full evidence bundle. Identical bytes are cached by content hash — `check_document` first skips a redundant, paid inspection.

verify_identity(scheme, documents)

Run an Australian identity check over a SET of identity documents. A vision model reads each document (which ID it is, which fields it shows — name/photo/address/signature — and its issue date); a deterministic engine then tallies them against a scheme and reports whether identity is established, and exactly what's still missing if not. USE THIS WHEN someone needs to verify a person's identity from their documents — KYC / onboarding / "do these documents satisfy the 100-point check?" Pass ALL the person's documents together (a passport alone is 70 points; the check needs >= 100). `documents` is a list, each item ONE of: {"url": "https://..."} (public link, fetched server-side) or {"bytes_b64": "...", "filename": "passport.pdf"} (inline). Up to 10. `scheme`: "afp_100_point" (points, default) or "austrac_safe_harbour" (category combinations). Returns `{established, points/target or satisfied_path, documents[] (per-document: type, fields shown, whether it counted and why-not), reason, accepts, ...}`. This is identity COVERAGE, not a forgery judgment — run verify_document for authenticity. Documents are never stored. Required: documents.

verify_references(url, deep, text, filename, bytes_b64)

Fact-check a document's REFERENCES and CLAIMS — built for AI-generated reports whose citations must be checked before they're trusted. USE THIS WHEN someone shares a report, article, whitepaper, or deep-research export (or a link to one) and asks: is this accurate / legit? are these citations real? fact-check this. did the AI make this up? Also use it proactively before relying on any AI-written document. Provide the document ONE way: `url` (a public http(s) link to a PDF or web page — fetched server-side, the cheapest call: no need to download or encode anything), `text` (pasted markdown/plain prose), OR `bytes_b64` (a base64 PDF; URLs are read from the PDF's link annotations, so they're exact). Default (fast): provenance (is it a ChatGPT deep-research export?), citation resolution (live / archived / dead, papers matched against arXiv/Crossref to catch 'real ID, wrong paper'), and internal MATH (recompute the doc's own arithmetic). Set `deep=true` to also fetch each cited source and judge whether it SUPPORTS or CONTRADICTS the claim (slower, ~a minute). Returns a trust summary, per-item tables, and a shareable `permalink` to the public fact-check record. HONEST BOUNDARY: this reports verification COVERAGE, not truth — 'supported' means evidence-backed (not necessarily true) and 'unsupported' means no evidence found (not necessarily false). It tells a reviewer WHERE to look; it does not bless the document, and it never affects the fraud risk band.

Last successful function declaration observed on 2026-08-13. Source: https://www.stipple.sh/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://www.stipple.sh/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/Sketchjar/openwarrant
• Remote endpoint (streamable-http) — https://www.stipple.sh/mcp

Also from sketchjar

• OpenWarrant — AI Text Detection
  Probability prose is AI-written, with the tells behind the score. No API key — text or URL in.
• OpenWarrant — Reference Verification
  Fact-check citations: resolve, match, support claims; math rechecked. No API key — URL in.