Verifiable document memory for MCP agents

Ready to connect? The how-to lives in docs — key, host config, first tool call, verify.

Why does verifiability matter for MCP users?

MCP hosts invoke tools on behalf of users. Without bundle_id and manifest_sha256, an agent cannot prove which document version it read. DocImprint MCP tools return the same signed evidence envelope as REST — so hosts can audit, cite, and verify agent outputs.

What MCP tools does DocImprint expose?

extract_text, extract_tables, parse_invoice, check_claims, extract_structured, verify_bundle, search_collection, and ask_collection — all returning citation-grounded results with optional Merkle proofs when store=true.

How do I connect Claude Desktop to DocImprint MCP?

Follow the Agent Quickstart at /docs/agents: use the mcp-remote stdio bridge with Authorization: Bearer dr_live_… pointing to https://api.docimprint.com/mcp, then run extract_text and verify_bundle.

Does MCP support offline verification?

Yes. Download the evidence bundle ZIP, recompute manifest SHA-256, verify the platform secp256k1 signature against GET /v1/keys — same flow as REST. verify_bundle runs server-side checks; offline verify needs no ongoing API trust.

Tools at a glance

Full setup steps are in the Agent Quickstart.

jsonClaude Desktop preview

{
  "mcpServers": {
    "docimprint": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.docimprint.com/mcp",
        "--header",
        "Authorization:${DOCIMPRINT_AUTH}"
      ],
      "env": {
        "DOCIMPRINT_AUTH": "Bearer dr_live_YOUR_KEY"
      }
    }
  }
}

Preview only — copy the complete configs and verify steps from docs.

Document

extract_textPDF or image → raw text via OCR
extract_tablesPDF or image → Markdown tables
parse_invoiceInvoice/receipt → merchant, line items, totals
check_claimsDocument + claims[] → supported / contradicted / not_found
extract_structuredDocument + JSON schema → typed fields with citations
summarize_documentDocument → summary + key_points[]

URL

extract_urlHTTPS URL → page text
summarize_urlHTTPS URL → summary + key_points[]
qa_urlHTTPS URL + question → cited answer
translate_urlHTTPS URL + target language → translated text

Bundle

verify_bundlebundle_id → integrity check (returns receipt)
get_bundlebundle_id → metadata + artifacts (returns receipt)
notarize_bundleAnchor manifest hash on Base L2 (returns receipt)
verify_action_receiptrcpt_… → signature + manifest binding check

Collections

create_collectionCreate a named document corpus
list_collectionsList collections you own
add_document_to_collectionIndex a bundle into a collection (returns receipt)
search_collectionSemantic search over indexed chunks
ask_collectionCross-document Q&A with citations

Ops

get_job_statusPoll async job by job_id
get_quotaCredits used / remaining (free)

Agent Quickstart

Config, first tool, verify

For agents

Discovery & marketplace copy

Document memory

Concept reference