crypto-whitepapers-mcp

Instructions

Parameters:
    query (str): The search query to find relevant whitepaper content.
    project_name (str, optional): The name of the cryptocurrency project to filter results (e.g., 'bitcoin'). If None, searches all whitepapers.

Returns:
    str: A string containing up to 5 matching results from the knowledge base.

Implementation Reference

• src/crypto_whitepapers_mcp/cli.py:90-114 (handler)

  The core handler function for the 'ask_whitepapers' MCP tool. It is decorated with @mcp.tool(), which registers it. The function searches a vector database of cryptocurrency whitepaper PDFs for relevant content matching the query, optionally filtered to a specific project's whitepaper, and returns the top 5 results concatenated.

  @mcp.tool()
  def ask_whitepapers(query: str, project_name: str = None, ctx: Context = None) -> str:
      """Search the knowledge base for information related to a query, optionally filtered by project.
  
      Parameters:
          query (str): The search query to find relevant whitepaper content.
          project_name (str, optional): The name of the cryptocurrency project to filter results (e.g., 'bitcoin'). If None, searches all whitepapers.
  
      Returns:
          str: A string containing up to 5 matching results from the knowledge base.
      """
      
      # Apply filter if project_name is provided
      filters = [{"source": f"{project_name.lower()}.pdf"}] if project_name else None
      
      results = knowledge_base.search(
          query=query,
          num_documents=5,
          filters=filters
      )
      
      if not results:
          return f"No matches found for query '{query}'" + (f" in {project_name} whitepaper" if project_name else "")
      
      return "\n\n".join([r.content for r in results])

• src/crypto_whitepapers_mcp/cli.py:91-100 (schema)

  Input/output schema defined by the function signature and docstring parameters.

  def ask_whitepapers(query: str, project_name: str = None, ctx: Context = None) -> str:
      """Search the knowledge base for information related to a query, optionally filtered by project.
  
      Parameters:
          query (str): The search query to find relevant whitepaper content.
          project_name (str, optional): The name of the cryptocurrency project to filter results (e.g., 'bitcoin'). If None, searches all whitepapers.
  
      Returns:
          str: A string containing up to 5 matching results from the knowledge base.
      """

• src/crypto_whitepapers_mcp/cli.py:90-90 (registration)

  The @mcp.tool() decorator registers the 'ask_whitepapers' function as an MCP tool.

  @mcp.tool()

• src/crypto_whitepapers_mcp/cli.py:137-152 (helper)

  A prompt that instructs the model to use the 'ask_whitepapers' tool for analyzing tokenomics.

  @mcp.prompt()
  def analyze_tokenomics(project_name: str) -> GetPromptResult:
      """Analyze the tokenomics described in a cryptocurrency whitepaper"""
      return GetPromptResult(
          description="Analyze tokenomics of a cryptocurrency",
          messages=[
              PromptMessage(
                  role="user",
                  content=TextContent(
                      type="text",
                      text=f"Analyze the tokenomics (token distribution, supply, incentives) described in the {project_name} whitepaper. "
                           f"Use the 'ask_whitepapers' tool to search the knowledge base for relevant information."
                  )
              )
          ]
      )