Skip to main content
Glama
sailay1996

Cursor Agent MCP Server

by sailay1996

cursor_agent_chat

Chat with an AI agent to analyze code, edit files, and plan tasks using prompts with configurable output formats.

Instructions

Chat with cursor-agent using a prompt and optional model/force/output_format.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYes
output_formatNotext
extra_argsNo
cwdNo
executableNo
modelNo
forceNo
echo_promptNo

Implementation Reference

  • server.js:276-297 (registration)
    Registration of the 'cursor_agent_chat' MCP tool, including name, description, Zod input schema, and inline handler function that normalizes args and calls runCursorAgent.
    server.tool(
      'cursor_agent_chat',
      'Chat with cursor-agent using a prompt and optional model/force/output_format.',
      CHAT_SCHEMA.shape,
      async (args) => {
        try {
          // Normalize prompt in case the host nests under "arguments"
          const prompt =
            (args && typeof args === 'object' && 'prompt' in args ? args.prompt : undefined) ??
            (args && typeof args === 'object' && args.arguments && typeof args.arguments === 'object' ? args.arguments.prompt : undefined);
    
          const flat = {
            ...(args && typeof args === 'object' && args.arguments && typeof args.arguments === 'object' ? args.arguments : args),
            prompt,
          };
    
          return await runCursorAgent(flat);
        } catch (e) {
          return { content: [{ type: 'text', text: `Invalid params: ${e?.message || e}` }], isError: true };
        }
      },
    );
  • Inline handler function for cursor_agent_chat tool. Normalizes input arguments to handle both flat and nested 'arguments' structures from different MCP hosts, then delegates execution to the shared runCursorAgent helper.
    async (args) => {
      try {
        // Normalize prompt in case the host nests under "arguments"
        const prompt =
          (args && typeof args === 'object' && 'prompt' in args ? args.prompt : undefined) ??
          (args && typeof args === 'object' && args.arguments && typeof args.arguments === 'object' ? args.arguments.prompt : undefined);
    
        const flat = {
          ...(args && typeof args === 'object' && args.arguments && typeof args.arguments === 'object' ? args.arguments : args),
          prompt,
        };
    
        return await runCursorAgent(flat);
      } catch (e) {
        return { content: [{ type: 'text', text: `Invalid params: ${e?.message || e}` }], isError: true };
      }
    },
  • Zod schema definitions for cursor_agent_chat: CHAT_SCHEMA requires 'prompt' string and spreads shared COMMON fields for optional CLI options like output_format, model, force, etc.
    const COMMON = {
     output_format: z.enum(['text', 'json', 'markdown']).default('text'),
     extra_args: z.array(z.string()).optional(),
     cwd: z.string().optional(),
     executable: z.string().optional(),
     model: z.string().optional(),
     force: z.boolean().optional(),
     // When true, the server will prepend the effective prompt to the tool output (useful for Claude debugging)
     echo_prompt: z.boolean().optional(),
    };
    
    // Schemas
    const CHAT_SCHEMA = z.object({
     prompt: z.string().min(1, 'prompt is required'),
     ...COMMON,
    });
  • Shared helper invoked by cursor_agent_chat (and other tools) to construct argv from prompt and extra_args, invoke the cursor-agent CLI executable, handle output formatting, debug logging, and optional prompt echoing.
    async function runCursorAgent(input) {
      const source = (input && typeof input === 'object' && input.arguments && typeof input.prompt === 'undefined')
        ? input.arguments
        : input;
    
      const {
        prompt,
        output_format = 'text',
        extra_args,
        cwd,
        executable,
        model,
        force,
      } = source || {};
    
      const argv = [...(extra_args ?? []), String(prompt)];
      const usedPrompt = argv.length ? String(argv[argv.length - 1]) : '';
     
      // Optional prompt echo and debug diagnostics
      if (process.env.DEBUG_CURSOR_MCP === '1') {
        try {
          const preview = usedPrompt.slice(0, 400).replace(/\n/g, '\\n');
          console.error('[cursor-mcp] prompt:', preview);
          if (extra_args?.length) console.error('[cursor-mcp] extra_args:', JSON.stringify(extra_args));
          if (model) console.error('[cursor-mcp] model:', model);
          if (typeof force === 'boolean') console.error('[cursor-mcp] force:', String(force));
        } catch {}
      }
     
      const result = await invokeCursorAgent({ argv, output_format, cwd, executable, model, force });
     
      // Echo prompt either when env is set or when caller provided echo_prompt: true (if host forwards unknown args it's fine)
      const echoEnabled = process.env.CURSOR_AGENT_ECHO_PROMPT === '1' || source?.echo_prompt === true;
      if (echoEnabled) {
        const text = `Prompt used:\n${usedPrompt}`;
        const content = Array.isArray(result?.content) ? result.content : [];
        return { ...result, content: [{ type: 'text', text }, ...content] };
      }
     
      return result;
    }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sailay1996/cursor-agent-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server