Velrim is answering right now. Last checked 2 min ago. It exposes 2 tools.
Document extraction against a JSON Schema with a calibrated confidence per field; async job status.
Today is the operative word: we check Velrim every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add extract --transport http https://mcp.velrim.com/mcp
{
"mcpServers": {
"extract": {
"url": "https://mcp.velrim.com/mcp"
}
}
}
[mcp_servers.extract]
url = "https://mcp.velrim.com/mcp"
{
"mcpServers": {
"extract": {
"url": "https://mcp.velrim.com/mcp"
}
}
}
{
"mcpServers": {
"extract": {
"url": "https://mcp.velrim.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
velrim_extract
velrim_job_status
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.velrim.com/mcp | streamable-http | answering | 1018 ms | 2 min ago |
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
Extract schema-valid JSON from text/HTML or document images. Pay per call via x402 V2.
High-fidelity PDF to structured Markdown conversion and document field extraction.
Parse a document into structured, confidence-scored fields. Bring your own model, pay per scan.
Document forensics: tamper/AI checks, fields, tables, identity, screening, tenders, citations.
Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
Documents to schema-valid JSON plus 38 more finished-job AI tools, on one credit wallet.
Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.
Answers built from our own checks of this server.