sieve_dataroom_add

Instructions

Implementation Reference

• src/sieve_mcp/server.py:196-244 (handler)

  MCP tool handler for sieve_dataroom_add. Decorated with @mcp.tool, accepts title, company_name, deal_id, website_url, document_type, file_path, text, url parameters. Delegates to client.dataroom_add().

  @mcp.tool(
      annotations={
          "readOnlyHint": False,
          "destructiveHint": False,
          "openWorldHint": True,
      }
  )
  async def sieve_dataroom_add(
      title: str,
      company_name: str = "",
      deal_id: str = "",
      website_url: str = "",
      document_type: str = "other",
      file_path: str = "",
      text: str = "",
      url: str = "",
  ) -> dict:
      """Add a document to a deal's data room. Creates the deal if needed.
  
      This is the primary way to get documents into Sieve for screening.
      Upload a pitch deck, financials, or any document -- then call sieve_screen
      to analyze everything in the data room.
  
      Provide company_name to create a new deal (or find existing),
      or deal_id to add to an existing deal.
  
      Provide exactly one content source: file_path (local file),
      text (raw text/markdown), or url (fetch from URL).
  
      Args:
          title: Document title (e.g. "Pitch Deck Q1 2026").
          company_name: Company name -- creates deal if new, finds existing if not.
          deal_id: Add to an existing deal (from sieve_deals or previous sieve_dataroom_add).
          website_url: Company website URL (used when creating a new deal).
          document_type: Type: 'pitch_deck', 'financials', 'legal', or 'other'.
          file_path: Path to a local file (PDF, DOCX, XLSX). The tool reads and uploads it.
          text: Raw text or markdown content (alternative to file).
          url: URL to fetch document from (alternative to file).
      """
      return await client.dataroom_add(
          company_name=company_name,
          deal_id=deal_id,
          website_url=website_url,
          title=title,
          document_type=document_type,
          file_path=file_path,
          text=text,
          url=url,
      )

• src/sieve_mcp/server.py:196-202 (registration)

  Registration of sieve_dataroom_add as an MCP tool via the @mcp.tool decorator with annotations (destructiveHint=False, openWorldHint=True).

  @mcp.tool(
      annotations={
          "readOnlyHint": False,
          "destructiveHint": False,
          "openWorldHint": True,
      }
  )

• src/sieve_mcp/client.py:172-209 (helper)

  Client-side helper function dataroom_add that builds the request body and sends it to POST /api/v1/public/dataroom. Handles file_path (base64 encoding), text, and url content sources.

  async def dataroom_add(
      company_name: str = "",
      deal_id: str = "",
      website_url: str = "",
      title: str = "Document",
      document_type: str = "other",
      file_path: str = "",
      text: str = "",
      url: str = "",
  ) -> dict[str, Any]:
      """Add a document to a deal's data room."""
      body: dict[str, Any] = {"title": title, "document_type": document_type}
      if company_name:
          body["company_name"] = company_name
      if deal_id:
          body["deal_id"] = deal_id
      if website_url:
          body["website_url"] = website_url
  
      if file_path:
          import base64
          import mimetypes
  
          file_name = os.path.basename(file_path)
          content_type = mimetypes.guess_type(file_path)[0] or "application/octet-stream"
  
          with open(file_path, "rb") as f:
              file_bytes = f.read()
  
          body["file_base64"] = base64.b64encode(file_bytes).decode("ascii")
          body["file_name"] = file_name
          body["file_content_type"] = content_type
      elif text:
          body["text"] = text
      elif url:
          body["url"] = url
  
      return await _request("POST", "/dataroom", json_body=body, timeout=60.0)

• src/sieve_mcp/server.py:203-212 (schema)

  Python type annotations defining the input schema for sieve_dataroom_add: title (str, required), company_name (str, optional), deal_id (str, optional), website_url (str, optional), document_type (str, default 'other'), file_path (str, optional), text (str, optional), url (str, optional). Returns dict.

  async def sieve_dataroom_add(
      title: str,
      company_name: str = "",
      deal_id: str = "",
      website_url: str = "",
      document_type: str = "other",
      file_path: str = "",
      text: str = "",
      url: str = "",
  ) -> dict:

• src/sieve_mcp/server.py:13-18 (registration)

  MCP server instructions referencing sieve_dataroom_add as the primary way to add documents to a deal's data room.

  instructions=(
      "Sieve is an AI-powered startup due diligence platform. "
      "It scores startups across 7 IMPACT-X dimensions (each 0-20, total 0-140) "
      "and returns a Take Meeting / Pass / Need More Info recommendation.\n\n"
      "WORKFLOW:\n"
      "1. Add documents: sieve_dataroom_add with company_name + file/text/url\n"