Document extraction against a JSON Schema with a calibrated confidence per field; async job status.
Velrim is a remote MCP server published at mcp.velrim.com. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 1,087 ms, a delay an agent will notice. It offers a narrow, focused set of 2 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
velrim_extract — Description lacks concise use-case scenarios despite being technically detailed.velrim_job_status — Description is truncated, making it unclear how it handles invalid job_ids.Risk: low
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
velrim_extractExtract structured data from a document (PDF or image, passed as document_base64 or as the upload_key of a staged upload) against a JSON Schema you supply. Returns a typed object and, for every field, a state (present, null, or missing), a calibrated confidence score, and an anchor (the source page and bounding box). The confidence is calibrated against published reliability curves (https://velrim.com/reliability), so a 0.9 means the field is right about 90% of the time on that document class — branch on it directly: act on a field at or above your accept threshold, escalate the fields below it and any that are missing. Use each field's anchor to check it against the source page.
schemaobjectrequireddocument_base64stringupload_keystringdoc_classstringhintsobjectvelrim_job_statusPoll an asynchronous extraction job by its job_id (from POST /v1/jobs on the Velrim API; velrim_extract itself is synchronous and never creates jobs). Returns the job status and, once complete, the same typed result as velrim_extract: per field a state (present, null, or missing), a calibrated confidence score, and an anchor (source page and bounding box). Confidence is calibrated against published reliability curves (https://velrim.com/reliability) — branch the same way: act on a field at or above your accept threshold, escalate the rest, and use each anchor to check a field against its source page.
job_idstringrequiredDerived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/com-velrim-extract)<a href="https://mcpmetrics.io/servers/com-velrim-extract"><img src="https://mcpmetrics.io/badge/com.velrim/extract/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
JSON Schema keyword count, body discarded
Validates JSON against a JSON Schema, lists violations. x402 payment required (testnet USDC).
Instatus status page scraper turns any company's Instatus page into clean JSON — components…
Document forensics: tamper/AI checks, fields, tables, identity, screening, tenders, citations.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
JSON syntax validation, JSON Schema checking, structure stats. x402 micropayment.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 01:33:33 | Legacy | 401 | 980 | 200 | 1482 | 2025-11-25 |
| 2026-09-12 23:31:36 | Legacy | 401 | 1048 | 200 | 1496 | 2025-11-25 |
| 2026-09-12 21:29:15 | Legacy | 401 | 898 | 200 | 1353 | 2025-11-25 |
| 2026-09-12 19:27:29 | Legacy | 401 | 987 | 200 | 1380 | 2025-11-25 |
| 2026-09-12 17:24:09 | Legacy | 401 | 543 | 200 | 1087 | 2025-11-25 |
| 2026-09-12 15:21:42 | Legacy | 401 | 659 | 200 | 2482 | 2025-11-25 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Comments
Sign in to write a comment
No comments yet. Be the first.