Check that what a message says is attached matches the attachments actually supplied
Compares a message's wording with its attachment list: 'see attached' with nothing attached, a named file (report.pdf) that is not in the list, a kind of file mentioned (the spreadsheet, a screenshot, the PDF) that no attachment matches by extension or MIME type, and a stated count ('two files') that differs from the list; attachments the text never mentions are listed. Mentions inside a negation ('no attachment', 'forgot to attach') are ignored. Rule-based and English only; it never opens a file or checks that a file's content matches its name. Offsets for every mention are in UTF-16, code points, UTF-8 bytes and graphemes.
What you get
Catches 'see attached' emails that go out with nothing attached. 20,000 characters per $0.005 call.
Call it
Send the JSON body below to https://agents.writerslogic.com/api/v1/attachment-references. An unpaid request answers 402 with the price and how to pay; a request that fails with a 5xx status is not charged.
curl -i -X POST https://agents.writerslogic.com/api/v1/attachment-references \
-H 'content-type: application/json' \
-d '{"text":"Hi, please find attached the Q3 report (q3-report.pdf) and the budget spreadsheet.","attachments":[{"name":"q3-report.pdf","mimeType":"application/pdf"}]}'
Input
| Field | Type | Required | Description |
|---|---|---|---|
text | string; length 1..20000 | yes | Message body. |
attachments | array<object>; max 50 items | yes | The attachments actually present; may be empty. |
Example request body
{
"text": "Hi, please find attached the Q3 report (q3-report.pdf) and the budget spreadsheet.",
"attachments": [
{
"name": "q3-report.pdf",
"mimeType": "application/pdf"
}
]
}
Result
The response is { "data": ..., "_provenance": ... }. data carries these fields; _provenance is a signed W3C Verifiable Credential with a C2PA-style manifest, checked free at POST /api/v1/verify-provenance.
| Field | Type | Required | Description |
|---|---|---|---|
status | string; one of "pass", "fail", "unknown", "unsupported" | no | pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass. |
claims | array<object>; max 50 items | no | Phrases asserting an attachment. |
namedFiles | array<object>; max 50 items | no | |
kindMentions | array<object>; max 50 items | no | |
count | object | no | |
unmentioned | array<string>; max 50 items | no | Attachment names the text never refers to by name or kind. |
witnesses | array<object> | no | |
versions | object | no | Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile). |
limits | array<string> | no | |
deterministic | boolean | no | Always true: pure code, no model. |
Pay and connect
Available through: x402 (USDC on Base), MCP. MCP clients reach it through the context-evidence-kit package.
Machine-readable
- This agent as JSON (schemas, example, OpenAPI operation)
- Free signed sample response
- OpenAPI 3.1 · Catalog · Index of every agent