# Stipple — Reference Verification

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

- name: sh.stipple/openwarrant-verify
- version: 0.1.5
- connection class: R0 (autonomous)
- trust: 89/100 flags: duplicate-repo
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/sh.stipple%2Fopenwarrant-verify
- tools: https://api.protogrid.dev/v1/servers/sh.stipple%2Fopenwarrant-verify/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "openwarrant-verify": {
      "type": "http",
      "url": "https://www.stipple.sh/mcp-verify"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-52d-ago -duplicate-repo(4 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 1 of 1 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: verify_references (destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 511 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 1, about 511 tokens to load them all
- tool set hash: 3bd08cdf097a229cfdcb9da1e152dec2
- badge: [![protogrid quality](https://protogrid.dev/badge/sh.stipple/openwarrant-verify.svg)](https://protogrid.dev/servers/sh.stipple/openwarrant-verify)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://www.stipple.sh/mcp-verify (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (1)

- `verify_references`: 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.