MCP Terminal Server

Instructions

Implementation Reference

• src/index.ts:66-95 (handler)

  Handler function that parses input using ExecuteCommandSchema and executes the command using execa, returning stdout/stderr or error.

  if (name === "execute_command") {
    const { command, args: cmdArgs = [], cwd } = ExecuteCommandSchema.parse(args);
    
    try {
      const result = await execa(command, cmdArgs, {
        cwd,
        shell: true,
      });
  
      return {
        content: [
          {
            type: "text",
            text: result.stdout || result.stderr || 'Command executed successfully with no output',
          },
        ],
        isError: false,
      };
    } catch (execaError: any) {
      return {
        content: [
          {
            type: "text",
            text: execaError?.message || 'Command execution failed',
          },
        ],
        isError: true,
      };
    }
  }

• src/index.ts:15-19 (schema)

  Zod schema for validating the input parameters of the execute_command tool: command (required), args (optional array), cwd (optional).

  const ExecuteCommandSchema = z.object({
    command: z.string(),
    args: z.array(z.string()).optional(),
    cwd: z.string().optional(),
  });

• src/index.ts:37-56 (registration)

  Tool registration in the listTools response, including name, description, and JSON schema mirroring the Zod schema.

  {
    name: "execute_command",
    description: "Execute a command in the local system",
    inputSchema: {
      type: "object",
      properties: {
        command: { type: "string", description: "Command to execute" },
        args: { 
          type: "array", 
          items: { type: "string" },
          description: "Command arguments"
        },
        cwd: { 
          type: "string", 
          description: "Working directory for command execution"
        }
      },
      required: ["command"],
    },
  }