MCP 서버
Stipple — Document Verification & Extraction
sh.stipple/openwarrant
이 MCP로 할 수 있는 일
Inspects documents for authenticity, tampering, AI-generation indicators, extracted fields, citations, identity evidence, sanctions, adverse media, and procurement opportunities.
기능
도구
16
도구
buyer_awards
Contract awards and signals for a buyer
What a buyer has awarded, what is ending, and what they plan. FREE.
USE THIS WHEN someone asks about a specific buyer before a bid: "who holds Transport for
NSW's work", "what is ending soon at Queensland Health", "what does this agency usually
pay". Give `buyer` (the organisation name as published) or `buyer_key` (from a tender's
buyer, or a previous answer).
Returns `{buyer, expiring[], planned[], recent_awards[], top_suppliers[], open_tenders[],
computed_at, sources}`: the nightly rollup (awards in the window, value quartiles as
published, median response window), contracts ending within 12 months with the incumbent,
planned procurements with their quarter and spend band, the suppliers who win from them
(name and share), and open tenders under the same name.
ANONYMOUS CALLERS SEE COUNTS, VALUES, DATES AND BUYERS; supplier and incumbent names are
withheld and `withheld_reason` says so. Relay that sentence as it is. Values are the
published amount and currency, never converted; `computed_at` is the night the figures
are true for - say it. Coverage is Australia and New Zealand sources named in
`sources`, each with the attribution its licence requires.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'buyer_awardsArguments', 'properties': {'buyer': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Buyer', 'default': None}, 'buyer_key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Buyer Key', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'buyer_awardsDictOutput', 'additionalProperties': True}
check_document
Check for a cached inspection
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}.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'check_documentArguments', 'required': ['sha256'], 'properties': {'sha256': {'type': 'string', 'title': 'Sha256'}}}
출력 스키마
{'type': 'object', 'title': 'check_documentDictOutput', 'additionalProperties': True}
check_pack
Check a document pack's completeness
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
extract_fields with options={"classify": true}; 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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'check_packArguments', 'required': ['documents'], 'properties': {'scheme': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Scheme', 'default': None}, 'documents': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Documents'}, 'requirements': {'anyOf': [{'type': 'array', 'items': {}}, {'type': 'null'}], 'title': 'Requirements', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'check_packDictOutput', 'additionalProperties': True}
check_source_overlap
Check text against published web sources
Check whether text OVERLAPS text published on the public web — a plagiarism-style
check: does this text appear elsewhere? was this copied? find the source of this text.
Provide the document ONE way: `text` (pasted prose), `url` (a public http(s) link —
fetched server-side; that page and its host are excluded from matches), OR `bytes_b64`
(a base64 PDF/.docx/text file, plus `filename` for routing).
Returns two evidence tiers, never mixed: `matches` are EXACT/near-verbatim overlaps
confirmed against the fetched source page — each carries the quoted text from both
sides, the source URL, and char spans for highlighting. `possible_paraphrases` are
model JUDGEMENTS (reworded overlap), clearly labelled, never quotes, and alone they
cap the overlap band at "low". `overlap_band` summarises: none | low | notable | high.
HONEST SCOPE: this searches the PUBLIC WEB within capped queries — it is not an
academic-database check, absence of matches is never an originality certificate, and
overlap says nothing about who published first or intent. Plagiarism is a judgement
this tool never makes. English-language prose only; non-prose and unsupported
languages abstain (`applicable: false`). Free within the weekly cap.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'check_source_overlapArguments', 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Text', 'default': None}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'check_source_overlapDictOutput', 'additionalProperties': True}
detect_ai_text
Detect AI-written prose
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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'detect_ai_textArguments', 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Text', 'default': None}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'detect_ai_textDictOutput', 'additionalProperties': True}
extract_fields
Extract fields from a document
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; "what kind of document is this?" is
`options={"classify": true}` right here.)
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.
`"question"` works instead of `"description"` if you would rather just ask:
{"name":"customer_name", "question":"What is the customer name?"}.
- `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).
`options` turns on extra capabilities. Every one defaults OFF, and asking for one that this
server does not support is an ERROR naming it — never a silent no-op, so you can always tell
"asked wrongly" from "nothing found". Available today:
- `{"grounding": true}` — every value gains `bbox` (the rectangle it was read from, in PDF
points, origin top-left) and `text_layer_match`. Use it to CITE a value back to the page.
Born-digital PDFs only for now; a scan returns `bbox: null` and `grounding: "none"`.
- `{"flag_below": 0.7}` — adds `needs_review`, the fields under that confidence, weakest
first. Use it to route the doubtful ones to a human instead of checking everything.
- `{"tables": true}` — adds `tables`: whole tables with their rows. On a PDF these are
read from the document's own rules and coordinates (exact cells, merged-cell colspans,
no model call and NO CREDIT for the table pass); on a scan the model reads the rows and
the table says `source: "vlm"` with no cell geometry. `{"tables": {"formats":
["json","markdown","html"], "borderless": true, "cells": true}}` to tune it.
- `{"classify": true}` — adds `classification`: the full verdict (type, country,
confidence, evidence), not just the routing. Free in auto mode.
- `{"redact": true}` — adds `pii` (a MASKED inventory) and `redacted_text`, so you can
extract and check for personal data in ONE call. A field you NAMED is still returned in
full; the inventory never is. Two things to know before turning it on: `redacted_text`
is the document's WHOLE text body with detected PII replaced — for a PDF that means
every page, not just the ones `max_pages` covers — and redaction is best-effort
coverage, so anything it failed to detect stays in that text verbatim. It also costs
an extra page-equivalent per page, because it is a second model pass.
- `{"layout": true}` — adds `layout.blocks`: every text block with its role
(heading/body), font, size, column and reading order. Born-digital PDFs only; free.
- `{"links": true}` — adds `links`: the PDF's own link annotations with uri, anchor
text and bbox. Free. A URL merely PRINTED on the page is not an annotation.
- `{"figures": true}` — adds `figures`: where the embedded images sit (bbox and pixel
size), never the bytes. Free.
- `{"chunks": true}` — adds `chunks`: retrieval-ready pieces that carry provenance a
text splitter cannot give you — `heading_path` (where in the document), `bbox` and
page range (citable back to the page), tables never sliced. Six strategies via
`{"chunks": {"strategy": "section|page|chars|recursive|element|hierarchical",
"max_chars": 1500, "min_chars": 200, "overlap": 100, "include_headings": true}}`.
`hierarchical` adds parent context chunks for small-to-big retrieval. Born-digital
PDFs only; free.
- `{"split": true}` — adds `documents`: the page ranges of the distinct documents in
one file (a bundle of 3 stapled PDFs -> 3 entries with types). One classifier call
per page, so it costs +1 page-equivalent per page read.
`render_scale` (one of 1.0, 1.5, 2.0, 3.0, 4.0; default 2.0) raises rasterisation for small or
dense print. Call `GET /v1/extract/capabilities` for the full machine-readable list.
COST: 1 credit per page read, minimum 1 — with `fields` or a `template` given, a one-page
receipt costs 1 and a ten-page statement costs 10; AUTO mode adds 1 for the routing
classification. Options that add model reads add page-equivalents (`redact` +pages, `split`
+pages replacing the auto/classify +1, `tables` +pages only on a scan); deterministic work
is free, and an encrypted PDF is charged the one-page floor only. Pages charged is
min(`max_pages`, the document's real length), resolved before the call runs, so you can
predict the price. Set `max_pages` to cap your spend on a long document.
CAPABILITY-ONLY: `options.classify` and/or `options.redact` with no `fields`, no
`template` and no other option skips field extraction entirely — classify-only costs
1 credit and redact-only 1 per page, exactly what the retired classify_document and
redact_pii tools charged.
Returns `{mode, document_type, fields{name:{value,confidence,page}}, not_found, pages_read,
page_limit, page_count}`. `page_count` is the document's real length, so you can see when
`max_pages` truncated it. 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).
`text_layer_match` is `exact` / `normalised` when the printed value was located on the page,
`multiple` when the same string appears more than once (no box — we will not guess which), and
`absent` when it is not there. It reports whether the string was FOUND, not that the value is
correct. The document is never stored.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'extract_fieldsArguments', 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'fields': {'anyOf': [{'type': 'array', 'items': {}}, {'type': 'null'}], 'title': 'Fields', 'default': None}, 'country': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Country', 'default': None}, 'options': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Options', 'default': None}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'template': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Template', 'default': None}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}, 'max_pages': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Max Pages', 'default': None}, 'render_scale': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Render Scale', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'extract_fieldsDictOutput', 'additionalProperties': True}
find_signals
Find contract expiries and planned procurements
Signals: what may be tendered before it is. FREE.
USE THIS WHEN someone asks what is coming: "which contracts in Queensland end in the next
six months", "what is planned for ICT next quarter", "what is expiring for this buyer".
`kind` is one of contract_expiry (a contract ending, with its incumbent),
planned_procurement (a buyer's stated plan with its quarter and spend band as published)
or recurring_tender (derived from our own history, labelled `derived`). `jurisdiction`
is one of AU, NZ, AU-NSW, AU-VIC, AU-QLD, AU-WA, AU-SA, AU-TAS, AU-ACT, AU-NT. `window_before` is an ISO date: signals whose
window starts on or before it. `q` searches the subject, buyer and incumbent.
Returns `{total, results[], computed_at, sources}`. Each signal carries `confidence`
(`published` or `derived` - a vocabulary, not a score), its window (never invented: an
expiry's window IS the contract's end date; a planned row with no parseable quarter has
none), `evidence_ref` and `evidence_url`. ANONYMOUS CALLERS SEE EVERYTHING BUT THE
INCUMBENT'S NAME; `withheld_reason` says so - relay it as it is.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'find_signalsArguments', 'properties': {'q': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Q', 'default': None}, 'kind': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Kind', 'default': None}, 'buyer': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Buyer', 'default': None}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 25}, 'jurisdiction': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Jurisdiction', 'default': None}, 'window_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Window Before', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'find_signalsDictOutput', 'additionalProperties': True}
find_tenders
Search AU/NZ tenders
Search open tenders across Australia and New Zealand.
FREE, within the weekly cap.
USE THIS WHEN someone asks what public-sector work is open: "any council drainage
tenders in Victoria", "what's closing this month in NSW", "show me federal IT
opportunities". For "which of these could MY company actually bid for", use
match_tenders instead — that reads their website and ranks against it.
`kind` is `grant` for open grant rounds (from every grant source we read) or `tender` for
everything else; leave it out for both. Each result says which it is in `kind`.
`jurisdiction` is one of AU, NZ, AU-NSW, AU-VIC, AU-QLD, AU-WA, AU-SA, AU-TAS, AU-ACT, AU-NT. `tier` is federal, national,
state, council, university or health. `closing_before` is an ISO date.
`first_seen_after` (ISO-8601 instant, strictly newer) answers "what is new since my last
look" — first_seen is when WE first saw the tender, the honest clock for newness. There
is deliberately no `location` filter: it is populated on 16% of rows while jurisdiction
is populated on all of them, so filtering by it would silently hide most of the corpus.
Returns `{total, results[], coverage}`. Each result carries title, buyer, jurisdiction,
closing_date, categories, a summary, a link, and source_id/source_tag/source_name/
source_url/source_refresh — plus `link_is_listing` when the portal publishes no
per-tender URL and the link goes to the list it appeared on.
`coverage` names which sources were searched and which returned nothing. Quote it if
the result is empty: "no match in what we searched" is true, "there are none" is not.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'find_tendersArguments', 'properties': {'q': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Q', 'default': None}, 'kind': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Kind', 'default': None}, 'tier': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Tier', 'default': None}, 'limit': {'type': 'integer', 'title': 'Limit', 'default': 25}, 'source': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Source', 'default': None}, 'category': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Category', 'default': None}, 'jurisdiction': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Jurisdiction', 'default': None}, 'closing_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Closing Before', 'default': None}, 'include_closed': {'type': 'boolean', 'title': 'Include Closed', 'default': False}, 'first_seen_after': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'First Seen After', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'find_tendersDictOutput', 'additionalProperties': True}
get_warrant
Fetch a stored warrant
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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'get_warrantArguments', 'required': ['warrant_id'], 'properties': {'warrant_id': {'type': 'string', 'title': 'Warrant Id'}, 'as_markdown': {'type': 'boolean', 'title': 'As Markdown', 'default': False}}}
match_tenders
Match tenders to a company
Rank open tenders against what a company actually does. Free, inside the weekly cap.
USE THIS WHEN someone asks which opportunities suit a specific business: "what could we
bid for", "is there anything for a civil contractor in Victoria", "find work for
acme.com.au". Give `company_url` — a plain domain is fine, we resolve it — and we read
their site, build a capability profile, and score the shortlist against it.
`example` runs a built-in profile (civil, it, facilities) with no site read, for
demonstrating the shape of the answer.
Returns `{profile, matched, shown, withheld, withheld_reason, matches[], degraded,
score_means, coverage}`. Each match has `score`, `band`, `why[]` — the company's own
stated capabilities this tender needs — and `gaps[]`, things the tender asks for that
their website does not mention. An anonymous call shows the strongest few and says
how many were withheld; relay `withheld_reason` as it is.
TELL THE USER WHAT THE SCORE IS: relative fit within these results, against what their
website says. NOT a probability of winning. And `gaps` is what to check before bidding,
not a list of everything the tender requires — that is in the tender documents.
When `degraded` is true, scoring was unavailable and the order is keyword relevance
only, with no `why`/`gaps`. Say so rather than presenting it as a judged ranking.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'match_tendersArguments', 'properties': {'example': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Example', 'default': None}, 'company_url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Company Url', 'default': None}, 'jurisdiction': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Jurisdiction', 'default': None}, 'closing_before': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Closing Before', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'match_tendersDictOutput', 'additionalProperties': True}
screen_adverse_media
Screen for adverse media and sanctions
Screen a person or organisation for ADVERSE MEDIA and SANCTIONS exposure (KYC/AML).
PEP lists are not screened: `sanctions.flags.pep` is always false and `sanctions.note` says so.
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 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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'screen_adverse_mediaArguments', 'properties': {'dob': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Dob', 'default': None}, 'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Name', 'default': None}, 'role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Role', 'default': None}, 'aliases': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Aliases', 'default': None}, 'country': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Country', 'default': None}, 'employer': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Employer', 'default': None}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'screen_adverse_mediaDictOutput', 'additionalProperties': True}
submit_feedback
Rate a warrant
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.
멱등성
입력 스키마
{'type': 'object', 'title': 'submit_feedbackArguments', 'required': ['warrant_id', 'verdict'], 'properties': {'note': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Note', 'default': None}, 'verdict': {'type': 'string', 'title': 'Verdict'}, 'warrant_id': {'type': 'string', 'title': 'Warrant Id'}}}
출력 스키마
{'type': 'object', 'title': 'submit_feedbackDictOutput', 'additionalProperties': True}
tender_sources
List tender data sources
Every source we search, what it is allowed to do, and what the last run returned.
FREE.
USE THIS WHEN someone asks where the data comes from, whether a particular portal is
covered, or why a search came back empty. It is the honesty surface: it names sources
behind login walls, sources whose robots.txt refuses us, and sources that returned
nothing on the last run and why.
Returns `{sources[], coverage}` — per source: id, tag, name, URL, refresh mode,
jurisdiction, tier, how it is accessed, what its robots.txt says, how many tenders we
hold from it, and its status on the most recent run. Snapshot sources include their
observed date and are not presented as nightly feeds.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'tender_sourcesArguments', 'properties': {}}
출력 스키마
{'type': 'object', 'title': 'tender_sourcesDictOutput', 'additionalProperties': True}
verify_document
Verify a document's authenticity
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`; for "are this report's citations real" use `verify_references`. Both are
available in this canonical suite.)
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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'verify_documentArguments', 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'fresh': {'type': 'boolean', 'title': 'Fresh', 'default': False}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'verify_documentDictOutput', 'additionalProperties': True}
verify_identity
Run an Australian identity check
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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'verify_identityArguments', 'required': ['documents'], 'properties': {'scheme': {'type': 'string', 'title': 'Scheme', 'default': 'afp_100_point'}, 'documents': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Documents'}}}
출력 스키마
{'type': 'object', 'title': 'verify_identityDictOutput', 'additionalProperties': True}
verify_references
Verify a report's citations
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.
읽기 전용
입력 스키마
{'type': 'object', 'title': 'verify_referencesArguments', 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Url', 'default': None}, 'deep': {'type': 'boolean', 'title': 'Deep', 'default': False}, 'text': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Text', 'default': None}, 'filename': {'type': 'string', 'title': 'Filename', 'default': 'document.pdf'}, 'bytes_b64': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Bytes B64', 'default': None}}}
출력 스키마
{'type': 'object', 'title': 'verify_referencesDictOutput', 'additionalProperties': True}
기록
최근 도구 변경
변경됨
find_tenders
2026년 9월 29일 2:59 AM
추가됨
find_signals
2026년 9월 17일 12:55 PM
추가됨
buyer_awards
2026년 9월 17일 12:55 PM
추가됨
tender_sources
2026년 9월 17일 12:55 PM
추가됨
match_tenders
2026년 9월 17일 12:55 PM
추가됨
find_tenders
2026년 9월 17일 12:55 PM
추가됨
check_source_overlap
2026년 9월 17일 12:55 PM
추가됨
verify_references
2026년 9월 17일 12:55 PM
추가됨
detect_ai_text
2026년 9월 17일 12:55 PM
추가됨
screen_adverse_media
2026년 9월 17일 12:55 PM
추가됨
check_pack
2026년 9월 17일 12:55 PM
추가됨
verify_identity
2026년 9월 17일 12:55 PM
추가됨
extract_fields
2026년 9월 17일 12:55 PM
추가됨
submit_feedback
2026년 9월 17일 12:55 PM
추가됨
get_warrant
2026년 9월 17일 12:55 PM
추가됨
check_document
2026년 9월 17일 12:55 PM
추가됨
verify_document
2026년 9월 17일 12:55 PM
탐색
유사한 MCP 서버
ampel
io.tooloracle/ampel
Assesses regulated entities and providers against DORA and related ESG, MiCA, and AML requirements, with contract analysis, evide…
Didit
io.github.pipeworx-io/didit
Provides identity and compliance capabilities including AML screening against sanctions and PEP lists, business verification, ben…
Compliance & Sanções
io.github.mcp-dir/compliance-mcp
Performs Brazilian due-diligence checks across PEP, sanctions, criminal, regulatory, fraud, tax, and government restriction datab…
WhiteIntel — Ownership Intelligence
dev.whiteintel/whiteintel
Resolves companies and people and maps ownership, beneficial ownership, sanctions, offshore exposure, financials, corporate filin…
outris-identity-mcp
io.github.outris-dev-user/outris-identity-mcp
Performs identity, KYC, fraud, business, phone, email, bank-account, PAN, GST, vehicle, and due-diligence lookups, including digi…
Ni Biashara Shelves — Africa FX, freight & compliance checks (x402)
biz.nibiashara/shelves
Provides African FX rates, freight carrier and broker authority checks, safety checks, OFAC sanctions screening, and Texas insura…
tlpt
io.tooloracle/tlpt
Supports TIBER-EU and DORA threat-led penetration testing with scenario generation, MITRE mapping, findings, evidence, scheduling…
ContinueOps Public MCP
com.continueops/continueops-public
Provides compliance framework information, DORA readiness checks, business continuity plan structures, runbook templates, and res…