Document MCP Server

Instructions

Implementation Reference

• mcp_server.py:20-26 (handler)

  The handler function 'read_document' implements the 'read_doc_contents' tool logic. It takes a doc_id parameter, validates that the document exists in the docs dictionary, and returns the document contents or raises a ValueError if not found.

  def read_document(
      doc_id: str = Field(description="Id of the document to read")
  ):
      if doc_id not in docs:
          raise ValueError(f"Doc with id {doc_id} not found")
      
      return docs[doc_id]

• mcp_server.py:16-19 (registration)

  The @mcp.tool decorator registers the 'read_doc_contents' tool with the MCP server. It defines the tool name and description that appears in the tool registry.

  @mcp.tool(
      name="read_doc_contents",
      description="Read the contents of a document and return it as a string."
  )

• mcp_server.py:6-13 (schema)

  The 'docs' dictionary defines the data schema and available documents that the read_doc_contents tool operates on. It maps document IDs to their content strings.

  docs = {
      "deposition.md": "This deposition covers the testimony of Angela Smith, P.E.",
      "report.pdf": "The report details the state of a 20m condenser tower.",
      "financials.docx": "These financials outline the project's budget and expenditures",
      "outlook.pdf": "This document presents the projected future performance of the system",
      "plan.md": "The plan outlines the steps for the project's implementation.",
      "spec.txt": "These specifications define the technical requirements for the equipment"
  }

• mcp_server.py:21-21 (schema)

  The Field definition for the doc_id parameter specifies the input schema for the tool, describing what the parameter represents.

  doc_id: str = Field(description="Id of the document to read")