Stipple — Reference Verification

sh.stipplePublished by stipple.shOfficial publisherv0.1.5Updated Oct 25, 2026

Fact-check citations: resolve, match, support claims. Arithmetic rechecked. Free to start.

The publisher's own server: Stipple - Government Tenders and Grants

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

A hosted Stipple MCP server whose verify_references tool fact-checks a report's citations and claims, checking that references resolve, match and support what's

What you can do
Fact-check a document's references and claims: check that citations resolve, match their sources and support the claims made, and flag unsupported claims and arithmetic that does not recompute, reporting verification coverage rather than a truth verdict.
When to use it
Use it when someone shares an AI-generated report, article, whitepaper or deep-research export and asks whether its citations are real or the content is accurate, especially before trusting or republishing it.
Requirements
A remote Streamable HTTP endpoint; no install or signup is needed and an anonymous free tier works immediately. An optional free API key can be sent as an Authorization Bearer header for a private credit allowance. The endpoint must use the www host.
Before you install
The tool reports verification coverage, not a truth verdict, so results should be read as signals rather than confirmation. Documents or links submitted are sent to a third-party hosted service operated by Stipple AI Pty Ltd, and paid calls may consume credits beyond the free tier.

Installation

In SourceWeft

  1. Open Stipple — Reference Verification in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/sh.stipple%2Fopenwarrant-verify/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "stipple-reference-verification": {
      "type": "http",
      "url": "https://www.stipple.sh/mcp-verify"
    }
  }
}

README

Stipple MCP server

Documents in. Answers your agents can act on.

Stipple is a hosted MCP server for document work: forensic authenticity signals, structured field extraction, Australian identity checks, adverse-media and sanctions screening, AU/NZ government tender search, AI-written-text detection, and citation verification for research reports.

No install, no signup — an anonymous free tier works immediately.

Connect

bash
claude mcp add --transport http stipple https://www.stipple.sh/mcp

Or in any MCP client config:

json
{ "mcpServers": { "stipple": { "type": "http", "url": "https://www.stipple.sh/mcp" } } }
  • Endpoint: https://www.stipple.sh/mcp (Streamable HTTP)
  • Always the www. host — the apex domain redirects, and a POST through the redirect fails for non-browser clients.
  • Auth: none required. An optional free API key (POST /v1/keys) gives a private credit allowance; send it as Authorization: Bearer stp_....

Tools (13)

ToolWhat it doesWhat it is NOT
verify_documentForensic authenticity inspection of a PDF/image (URL or base64): risk_band + inspection_quality + evidenceA fraud verdict — it is a signal with the evidence behind it
extract_fieldsStructured fields from a document: ad-hoc field lists, templates (payslip, tax invoice, bank statement, receipt, contract), tables, per-value grounding, redaction, layout, chunking, splittingA judgment — values are what the document shows; absences come back in not_found
verify_identityAustralian identity check over a document set: AFP 100-point or AUSTRAC safe-harbour, with exactly what is missingA forgery check — pair with verify_document
check_packDoes a document set satisfy a checklist (named scheme or ad-hoc requirements)?Approval — presence of the right types, not genuineness
screen_adverse_mediaAdverse media + corroboration-gated sanctions/PEP screening of a person or organisationA determination — "review", never "guilty"; "nothing found" is not a clean record
find_tendersFree. Search open AU/NZ government tenders—
match_tendersRank open tenders against what a company's own website says it does, with why[] and gaps[]A win probability
tender_sourcesFree. Where tender data comes from, and why a search can be empty—
detect_ai_textProbability a document's prose is AI-written, with the linguistic tells; abstains on non-proseCalibrated truth — and style, not authenticity
verify_referencesFor a report: citations resolve and match, internal arithmetic recomputes, unsupported claims flaggedA truth verdict — it reports verification coverage
check_documentHas this exact file (sha256) been inspected already? Skips a paid call—
get_warrantFetch a stored result bundle (JSON or Markdown)—
submit_feedbackThumbs up/down on a rating—

Prompts (8)

Guided workflows shipped with the server: Verify a document's authenticity · What kind of document is this? · Run a 100-point identity check · Screen a person for adverse media · Find tenders my company could bid for · Was this written by AI? · Fact-check a report URL · Fact-check pasted text.

How results read

Every inspection reports two independent axes: risk_band (how authentic the document looks) and inspection_quality (how completely it could be inspected). A clean phone photo of a real payslip is commonly low risk + limited quality — "nothing looks tampered, but we couldn't read everything". Low coverage is not risk.

Identical documents are cached by content hash — resubmitting the same bytes returns the stored result instantly and free.

Credits

Anonymous callers share a free weekly allowance per IP. A free API key gets its own allowance and metering. Tender search and source listing cost nothing. Details: stipple.sh/pricing.

Also available

  • REST API — the same engines at /v1/*; OpenAPI contract at /openapi.json
  • Agent docs — /agents.md (short form /llms.txt)
  • Scoped servers — /mcp-aitext (AI-text detection only) and /mcp-verify (reference verification only), for installs that want a single tool

Operated by Stipple AI Pty Ltd · Privacy · Terms

Source: README.md at commit b0cc70c

Tools

1

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.

Parametersurldeeptextfilenamebytes_b64

Version history

1
  1. v0.1.5LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Stipple integrations

Stipple - Government Tenders and Grants

sh.stippleOfficial publisher

Hosted MCP server for searching Australian and NZ government tenders and grants, matching them to a company, and checking buyer awards and upcoming signals.

Streamable HTTPWeb executable
Web Search & Scraping5 toolsOct 30, 2026

Stipple — Government Tenders

sh.stippleOfficial publisher

A hosted MCP server for searching Australian and New Zealand government tenders and ranking them against a company's capabilities.

Streamable HTTPWeb executable
Web Search & Scraping5 toolsOct 25, 2026

Stipple — AI Text Detection

sh.stippleOfficial publisher

Stipple's hosted MCP server exposes a detect_ai_text tool that estimates the probability a piece of prose was written by an AI, with the linguistic tells…

Streamable HTTPWeb executable
Knowledge & Memory1 toolNov 2, 2026