Chain of Draft (CoD) MCP Server

Instructions

Implementation Reference

• server.py:82-100 (handler)

  Primary handler for the 'math_solve' MCP tool. Registered via @app.tool() decorator in FastMCP. Delegates to chain_of_draft_solve with domain set to 'math'.
  @app.tool() async def math_solve( problem: str, approach: str = None, max_words_per_step: int = None ) -> str: """Solve a math problem using Chain of Draft reasoning. Args: problem: The math problem to solve approach: Force "CoD" or "CoT" approach (default: auto-select) max_words_per_step: Maximum words per step (default: adaptive) """ return await chain_of_draft_solve( problem=problem, domain="math", approach=approach, max_words_per_step=max_words_per_step )
• server.py:36-80 (helper)

  Core helper function implementing the Chain of Draft reasoning logic, used by math_solve and other domain tools.
  @app.tool() async def chain_of_draft_solve( problem: str, domain: str = "general", max_words_per_step: int = None, approach: str = None, enforce_format: bool = True, adaptive_word_limit: bool = True ) -> str: """Solve a reasoning problem using Chain of Draft approach. Args: problem: The problem to solve domain: Domain for context (math, logic, code, common-sense, etc.) max_words_per_step: Maximum words per reasoning step (default: adaptive) approach: Force "CoD" or "CoT" approach (default: auto-select) enforce_format: Whether to enforce the word limit (default: True) adaptive_word_limit: Adjust word limits based on complexity (default: True) """ # Track execution time start_time = time.time() # Process the request with the client result = await cod_client.solve_with_reasoning( problem=problem, domain=domain, max_words_per_step=max_words_per_step, approach=approach, enforce_format=enforce_format, adaptive_word_limit=adaptive_word_limit ) # Calculate execution time execution_time = (time.time() - start_time) * 1000 # ms # Format the response formatted_response = ( f"Chain of {result['approach']} reasoning ({result['word_limit']} word limit):\n\n" f"{result['reasoning_steps']}\n\n" f"Final answer: {result['final_answer']}\n\n" f"Stats: {result['token_count']} tokens, {execution_time:.0f}ms, " f"complexity score: {result['complexity']}" ) return formatted_response
• index.js:459-480 (schema)

  Explicit input schema definition for the math_solve tool in the JavaScript MCP server.
  const MATH_TOOL = { name: "math_solve", description: "Solve a math problem using Chain of Draft reasoning", inputSchema: { type: "object", properties: { problem: { type: "string", description: "The math problem to solve" }, approach: { type: "string", description: "Force 'CoD' or 'CoT' approach" }, max_words_per_step: { type: "number", description: "Maximum words per reasoning step" } }, required: ["problem"] } };
• index.js:618-637 (handler)

  Handler block for 'math_solve' tool execution in the JavaScript MCP server call handler.
  if (name === "math_solve") { const result = await chainOfDraftClient.solveWithReasoning({ ...args, domain: "math" }); const formattedResponse = `Chain of ${result.approach} reasoning (${result.word_limit} word limit):\n\n` + `${result.reasoning_steps}\n\n` + `Final answer: ${result.final_answer}\n\n` + `Stats: ${result.token_count} tokens, ${result.execution_time_ms.toFixed(0)}ms, ` + `complexity score: ${result.complexity}`; return { content: [{ type: "text", text: formattedResponse }] }; }
• index.js:581-591 (registration)

  Registration of math_solve tool (as MATH_TOOL) in the ListTools request handler for the JS MCP server.
  server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: [ CHAIN_OF_DRAFT_TOOL, MATH_TOOL, CODE_TOOL, LOGIC_TOOL, PERFORMANCE_TOOL, TOKEN_TOOL, COMPLEXITY_TOOL ], }));