search_documents

Instructions

Implementation Reference

• debtstack/mcp_server.py:547-558 (handler)

  MCP server handler for search_documents tool. Parses arguments, calls api_get('/documents/search'), formats results using format_document_result helper.

  elif name == "search_documents":
      params = {k: v for k, v in arguments.items() if v is not None}
      params.setdefault("limit", 10)
      result = api_get("/documents/search", params)
  
      docs = result.get("data", [])
      if not docs:
          return [TextContent(type="text", text=f"No documents found for '{params.get('q', '')}'.")]
  
      text = f"Found {len(docs)} matching sections:\n\n"
      text += "\n\n---\n\n".join(format_document_result(d) for d in docs)
      return [TextContent(type="text", text=text)]

• debtstack/mcp_server.py:362-391 (schema)

  MCP tool registration with input schema for search_documents: query (required string), ticker, section_type (enum), limit (integer).

  Tool(
      name="search_documents",
      description=(
          "Search SEC filing sections for specific terms. "
          "Section types: debt_footnote, credit_agreement, indenture, covenants, mda_liquidity. "
          "Use to find covenant language, credit agreement terms, or debt descriptions."
      ),
      inputSchema={
          "type": "object",
          "properties": {
              "query": {
                  "type": "string",
                  "description": "Search terms"
              },
              "ticker": {
                  "type": "string",
                  "description": "Company ticker(s)"
              },
              "section_type": {
                  "type": "string",
                  "enum": ["debt_footnote", "credit_agreement", "indenture", "covenants", "mda_liquidity", "exhibit_21", "guarantor_list"],
                  "description": "Section type to search"
              },
              "limit": {
                  "type": "integer",
                  "description": "Maximum results (default 10)"
              }
          },
          "required": ["query"]
      }

• debtstack/langchain.py:622-624 (registration)

  LangChain toolkit registration: DebtStackSearchDocumentsTool is included in the get_tools() list.

      DebtStackSearchDocumentsTool(api_wrapper=self.api_wrapper),
      DebtStackGetChangesTool(api_wrapper=self.api_wrapper),
  ]

• debtstack/mcp_server.py:177-189 (helper)

  Helper function to format a single document search result into readable text with ticker, filing info, and snippet.

  def format_document_result(d: dict) -> str:
      """Format document search result."""
      lines = [
          f"**{d.get('section_type', 'Document')}** - {d.get('ticker', '?')}",
          f"Filing: {d.get('doc_type', '?')} ({d.get('filing_date', '?')})"
      ]
  
      if d.get('snippet'):
          # Clean up HTML tags in snippet
          snippet = d['snippet'].replace('<b>', '**').replace('</b>', '**')
          lines.append(f"...{snippet}...")
  
      return "\n".join(lines)

• debtstack/langchain.py:101-103 (helper)

  LangChain API wrapper method that makes the actual HTTP GET request to /documents/search endpoint.

  def search_documents(self, **kwargs) -> Dict[str, Any]:
      """Search SEC filing sections."""
      return self._get("/documents/search", params=kwargs)