api

{
  "id": "aix_016a6184bf",
  "name": "api",
  "operator": "(unclaimed - source: registry-official · publisher: com.docimprint)",
  "description": "AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-11-09",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "api-integration",
    "blog-article",
    "citation-check",
    "invoice-parsing",
    "ocr-extraction",
    "onchain-data",
    "pdf-to-json",
    "summarize-docs",
    "translation-qa",
    "web-research"
  ],
  "protocols": {
    "mcp": "https://api.docimprint.com/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 5027,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 41,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-11-09T03:01:05.847Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "repository",
      "url": "https://github.com/sawftware-apps/darkroom-gw"
    }
  ],
  "avatar": "https://github.com/sawftware-apps.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/sawftware-apps"
    }
  ],
  "profile": {
    "mcp_server": "DocImprint",
    "mcp_version": "1.0.0",
    "tool_count": 21,
    "tools": [
      {
        "name": "extract_text",
        "description": "Extract plain text from a PDF or image (base64-encoded). Use when you need raw text for downstream AI analysis (summarization, claim checking, structured extraction). For documents at a public URL, use extract_url instead (no base64 encoding needed).\nReturns: { pages: number, text: string }\nExample prompts:\n- \"Extract the text from this scanned contract so I can search it.\"\n- \"Give me the raw text from this PDF document.\"\n- \"OCR this image and return the text content.\""
      },
      {
        "name": "extract_tables",
        "description": "Extract tables and forms as Markdown from a PDF or image (base64-encoded). Use when the document contains structured tabular data such as financial statements, data sheets, or forms. For plain prose documents, use extract_text instead.\nReturns: { pages: number, text: string } — text contains Markdown-formatted tables.\nExample prompts:\n- \"Extract the tables from this financial statement.\"\n- \"Pull the data table from this PDF into Markdown format.\"\n- \"Get the tabular data from this form document.\""
      },
      {
        "name": "parse_invoice",
        "description": "Parse a receipt or invoice document into structured fields. Uses a quality AI model for accuracy. Use when you need to extract line items, totals, and merchant info from financial documents. For general document text, use extract_text instead.\nReturns: {\n  invoice: { merchant, date (YYYY-MM-DD), line_items[], subtotal, tax, total },\n  cited: { <field>: { value, confidence: \"high\"|\"medium\"|\"low\", citations: [{ quote, paragraphs[] }] } }\n}\nExample prompts:\n- \"Parse this invoice and give me the line items and total.\"\n- \"Extract the merchant, date, and amounts from this receipt.\"\n- \"Read this scan"
      },
      {
        "name": "check_claims",
        "description": "Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after extract_text or extract_url when you need to validate specific factual assertions. For open-ended questions about a document, use qa_url instead. For multi-document investigation, use ask_collection.\nTypical workflow: extract_text/extract_url → check_claims.\nReturns: {\n  claims: [{ claim, status: \"supported\"|\"contradicted\"|\"not_found\", evidence: { quote, paragraphs[] }, confidence: \"high\"|\"medium\"|\"low\" }],\n  truncated: boolean\n}\nExample prompts:\n- \"Check whether this contract"
      },
      {
        "name": "extract_structured",
        "description": "Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific data points from a document rather than full text. For invoices with known fields, parse_invoice (prebuilt schema) may be simpler. For general summarization, use summarize_document instead.\nSchema format: { \"field_name\": \"type hint or description\" } — e.g. { \"contract_date\": \"ISO date\", \"party_a\": \"string\", \"penalty_usd\": \"number\" }.\nReturns: {\n  data: { <field>: value },\n  data_cited: { <field>: { value, confidence: \"high\"|\"medium\"|\"low\", citations: [{ qu"
      },
      {
        "name": "summarize_document",
        "description": "Summarize document text into a prose summary and key points with citations. Use after extract_text or extract_url when you need a condensed understanding of a long document. For single-sentence Q&A, use qa_url instead. For extracting specific fields, use extract_structured.\nTypical workflow: extract_text/extract_url → summarize_document.\nReturns: {\n  summary: string,\n  key_points: string[],\n  summary_cited: { value, confidence, citations[] },\n  key_points_cited: [{ text, citations[] }],\n  truncated: boolean,\n  strategy: \"full\"|\"truncated\"|\"chunked\"\n}\nExample prompts:\n- \"Summarize this financia"
      },
      {
        "name": "verify_bundle",
        "description": "Verify the cryptographic integrity of an evidence bundle (ev_...) owned by your API key. Checks manifest hash, EIP-191 signature, and R2 artifact hashes. Free — no credits consumed. Use when you need to confirm a bundle has not been tampered with. For quick metadata lookups (without full crypto verification), use get_bundle instead.\nReturns: {\n  valid: boolean,\n  bundle_id, manifest_sha256,\n  checks: { status, manifest_hash, signature, artifacts: [{ name, ok }] },\n  tampered: string[],\n  signer_address: string|null,\n  attestation_tx: string|null,\n  url: string, captured_at: string\n}\nExample pr"
      },
      {
        "name": "create_collection",
        "description": "Create a named document collection for cross-document semantic search and RAG-based Q&A. Free — no credits consumed. Use when you want to group related evidence bundles for unified search (search_collection) or question answering (ask_collection).\nNOTE: Collections start empty. Add evidence bundles with add_document_to_collection. Indexing is async — once complete, use search_collection or ask_collection.\nReturns: { collection_id: string (col_...), name: string }\nExample prompts:\n- \"Create a collection called Q4 Contracts for my quarterly reports.\"\n- \"Set up a new document group named Due Dili"
      },
      {
        "name": "search_collection",
        "description": "Semantic (vector) search across documents in a collection. Returns ranked text chunks with relevance scores. Free — no credits consumed. Use when you need raw matching chunks from a collection. For a synthesized cited answer from the same context, use ask_collection instead.\nPREREQUISITE: Collection must be populated via add_document_to_collection and async indexing must complete (poll get_job_status) before results appear.\nReturns: { results: [{ bundle_id, chunk_id, text, score: number (0–1), title? }] }\nExample prompts:\n- \"Search my Q4 Contracts collection for mentions of liability cap.\"\n- \""
      },
      {
        "name": "ask_collection",
        "description": "Answer a question using RAG over a document collection. Retrieves relevant chunks then synthesizes a cited answer with source attribution. Use when you need a direct answer grounded in your collection documents. For raw matching chunks (without synthesis), use search_collection instead. For single-document Q&A, use qa_url instead.\nPREREQUISITE: Collection must be populated via add_document_to_collection and indexed before results appear.\nReturns: {\n  answer: string,\n  sources: [{ bundle_id, chunk_id }],\n  retrieval: [{ bundle_id, chunk_id, text, score }]\n}\nExample prompts:\n- \"What are the key "
      },
      {
        "name": "extract_url",
        "description": "Fetch a public HTTPS URL and return extracted text and page metadata. Lean mode — no evidence bundle stored, no bundle_id returned. Use for raw text extraction from web pages and online documents. Use summarize_url for summaries, qa_url for Q&A, translate_url for translation, extract_text for base64 file uploads.\nReturns: { url, title, word_count, text, final_url (after redirects) }\nExample prompts:\n- \"Extract the text from https://example.com/report.pdf for me.\"\n- \"Get me the raw content of this web page: [URL].\"\n- \"Pull the text from this online article so I can analyze it.\""
      },
      {
        "name": "summarize_url",
        "description": "Fetch a public HTTPS URL and return a prose summary with key points. Lean mode — no bundle stored. Use when you need a condensed understanding of a web page. For raw text, use extract_url. For asking a specific question about a page, use qa_url.\nReturns: { url, summary, key_points: string[], truncated: boolean, word_count }\nExample prompts:\n- \"Summarize https://en.wikipedia.org/wiki/Artificial_intelligence for me.\"\n- \"Give me the key points from this blog post: [URL].\"\n- \"What is this article about? Summarize [URL].\""
      },
      {
        "name": "qa_url",
        "description": "Fetch a public HTTPS URL and answer a specific question about its content. Lean mode — no bundle stored. Use when you have a precise question about a web page. For a broad summary, use summarize_url. For multi-document Q&A, use ask_collection instead.\nReturns: { url, answer, answer_cited: { value, confidence, citations[] }, confidence: \"high\"|\"medium\"|\"low\", truncated }\nExample prompts:\n- \"What is the refund policy at https://docs.example.com/policy?\"\n- \"Look at [URL] and tell me what the delivery terms are.\"\n- \"Answer this question based on the content of [URL]: [question].\""
      },
      {
        "name": "translate_url",
        "description": "Fetch a public HTTPS URL and return its content translated into a target language. Lean mode — no bundle stored. Use when you need to understand web content in a different language. For extracting raw untranslated text, use extract_url instead.\nReturns: { url, translated_text, target_lang, truncated }\nExample prompts:\n- \"Translate https://example.de/artikel into English for me.\"\n- \"Translate this German article into Spanish: [URL].\"\n- \"Fetch [URL] and give me the French translation.\""
      },
      {
        "name": "get_bundle",
        "description": "Retrieve metadata for an evidence bundle (ev_...) owned by your API key. Free — no credits consumed. Use for quick status/metadata lookups such as checking if a bundle is complete, finding its notarization status, or viewing retention/legal hold info. For deep cryptographic integrity verification (hash + signature + artifact checks), use verify_bundle instead.\nReturns: {\n  bundle_id, source_url, mode, status: \"pending\"|\"complete\"|\"failed\",\n  manifest_sha256, manifest_signature, signer_address,\n  attestation_tx, attestation_at, eas_uid,\n  parent_bundle_id, superseded_by,\n  legal_hold: boolean, "
      },
      {
        "name": "notarize_bundle",
        "description": "Notarize an evidence bundle on-chain by writing its manifest SHA-256 to the blockchain (Base/EVM). Creates a permanent, tamper-evident on-chain record of the document fingerprint. If the bundle is already notarized, returns the existing attestation immediately (idempotent). Use when you need an immutable on-chain timestamp proving a document existed at a point in time. For quick integrity checks without on-chain cost, use verify_bundle instead.\nPREREQUISITE: Bundle status must be \"complete\". Check status with get_bundle first.\nNOTE: Costs gas (ETH). The on-chain record is permanent and cannot "
      },
      {
        "name": "verify_action_receipt",
        "description": "Independently verify a signed action receipt (rcpt_...) returned by get_bundle, verify_bundle, notarize_bundle, or add_document_to_collection. Free — no credits consumed. Proves both that the receipt signature is authentic AND that the manifest_sha256 it was bound to still matches the bundle's current manifest — i.e. that the action was not performed against a stale or since-superseded document. Use for third-party audit of an agent's prior actions.\nReturns: {\n  receipt_id, valid: boolean,\n  signature_valid: boolean, manifest_matches_current: boolean,\n  bundle_id, agent_id, action, manifest_sh"
      },
      {
        "name": "get_job_status",
        "description": "Poll the status of an async job (extract, indexing, batch). Free — no credits consumed. Use after add_document_to_collection or async extract to check when processing completes. Poll this endpoint in a loop until status is \"complete\" or \"failed\". Completed jobs include the bundle_id or result_json in the response.\nJobs are created when you POST /v1/extract with a webhook, or when add_document_to_collection triggers async indexing.\nReturns: {\n  id, type: \"extract\"|\"extract_batch\"|\"index_collection\",\n  status: \"queued\"|\"processing\"|\"complete\"|\"failed\"|\"cancelled\",\n  progress_pct: number (0–100),"
      },
      {
        "name": "list_collections",
        "description": "List all document collections owned by your API key. Free — no credits consumed. Use before search_collection or ask_collection when you need the collection ID. Supports pagination with limit and offset.\nReturns: { collections: [{ id, name, created_at }] }\nExample prompts:\n- \"List all my document collections.\"\n- \"Show me the collections I have created.\"\n- \"What collections do I own? List them.\""
      },
      {
        "name": "add_document_to_collection",
        "description": "Add an evidence bundle to a collection and trigger async vector indexing. Use after create_collection to populate a collection with documents. Once indexed, documents become searchable via search_collection and ask_collection. Indexing is async — poll get_job_status with the returned job_id until status is \"complete\".\nPREREQUISITE: Bundle must have status \"complete\" (check with get_bundle). Collection must be owned by your API key.\nReturns: { collection_id, bundle_id, job_id (poll for indexing completion) }\nExample prompts:\n- \"Add my contract bundle ev_550e8400 to the Q4 Contracts collection.\""
      },
      {
        "name": "get_quota",
        "description": "Get current credit balance and plan details for your API key. Free — no credits consumed. Check this before running credit-consuming operations (extract, summarize, etc.) to avoid QUOTA_EXCEEDED errors. Returns plan tier, billing period, and usage breakdown.\nReturns: {\n  plan_id, billing_period (YYYY-MM),\n  credits_used, credits_limit, credits_remaining,\n  status: \"active\"|\"suspended\"\n}\nExample prompts:\n- \"How many credits do I have left this month?\"\n- \"Check my current quota and plan status.\"\n- \"Am I going to hit my credit limit soon?\""
      }
    ],
    "profiled_at": "2026-11-09T03:01:05.847Z"
  },
  "unreachable": false,
  "payment_method": "auth"
}