Skip to main content
Glama
milkosten

Task API Server

by milkosten

createTask

Add new tasks to the Task API Server by specifying description, category, priority, and status for organized task management.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesThe task description or title
categoryYesTask category (e.g., 'Development', 'Documentation')
priorityNoTask priority level (defaults to 'medium' if not specified)
statusNoInitial task status (defaults to 'not_started' if not specified)

Implementation Reference

  • The handler function for the 'createTask' tool. It constructs a request body from input parameters, calls the external task management API via makeApiRequest to create the task, formats the response, and handles errors.
    async ({ task, category, priority, status }: { 
      task: string; 
      category: string; 
      priority?: string; 
      status?: string 
    }) => {
      try {
        const requestBody: any = {
          task,
          category,
        };
    
        if (priority) requestBody.priority = priority;
        if (status) requestBody.status = status;
    
        const newTask = await makeApiRequest("POST", "/tasks", requestBody);
        
        logDebug(`Created new task with ID ${newTask.id}`);
    
        return {
          content: [
            {
              type: "text",
              text: `Task created successfully with ID: ${newTask.id}`
            },
            {
              type: "text",
              text: JSON.stringify({
                id: newTask.id,
                task: newTask.task || task,
                category: newTask.category || category,
                priority: newTask.priority || priority || "medium",
                status: newTask.status || status || "not_started",
                create_time: newTask.create_time || new Date().toISOString()
              }, null, 2)
            }
          ]
        };
      } catch (error: any) {
        logError(`Error in createTask: ${error.message}`);
        
        return {
          content: [
            {
              type: "text",
              text: `Error creating task: ${error.message}`
            }
          ]
        };
      }
    }
  • Identical handler function for the 'createTask' tool in the HTTP/SSE server implementation.
    async ({ task, category, priority, status }: { 
      task: string; 
      category: string; 
      priority?: string; 
      status?: string 
    }) => {
      try {
        const requestBody: any = {
          task,
          category,
        };
    
        if (priority) requestBody.priority = priority;
        if (status) requestBody.status = status;
    
        const newTask = await makeApiRequest("POST", "/tasks", requestBody);
        
        logDebug(`Created new task with ID ${newTask.id}`);
    
        return {
          content: [
            {
              type: "text",
              text: `Task created successfully with ID: ${newTask.id}`
            },
            {
              type: "text",
              text: JSON.stringify({
                id: newTask.id,
                task: newTask.task || task,
                category: newTask.category || category,
                priority: newTask.priority || priority || "medium",
                status: newTask.status || status || "not_started",
                create_time: newTask.create_time || new Date().toISOString()
              }, null, 2)
            }
          ]
        };
      } catch (error: any) {
        logError(`Error in createTask: ${error.message}`);
        
        return {
          content: [
            {
              type: "text",
              text: `Error creating task: ${error.message}`
            }
          ]
        };
      }
  • Zod input schema for the createTask tool defining required task and category strings, optional priority and status enums.
    {
      task: z.string().min(1, "Task description is required")
        .describe("The task description or title"),
      category: z.string().min(1, "Category is required")
        .describe("Task category (e.g., 'Development', 'Documentation')"),
      priority: z.enum(["low", "medium", "high"]).optional()
        .describe("Task priority level (defaults to 'medium' if not specified)"),
      status: z.enum(["not_started", "started", "done"]).optional()
        .describe("Initial task status (defaults to 'not_started' if not specified)")
    },
  • src/index.ts:372-435 (registration)
    Registration of the createTask tool on the MCP server, including name, input schema, and handler reference.
    server.tool(
      "createTask",
      {
        task: z.string().min(1, "Task description is required")
          .describe("The task description or title"),
        category: z.string().min(1, "Category is required")
          .describe("Task category (e.g., 'Development', 'Documentation')"),
        priority: z.enum(["low", "medium", "high"]).optional()
          .describe("Task priority level (defaults to 'medium' if not specified)"),
        status: z.enum(["not_started", "started", "done"]).optional()
          .describe("Initial task status (defaults to 'not_started' if not specified)")
      },
      async ({ task, category, priority, status }: { 
        task: string; 
        category: string; 
        priority?: string; 
        status?: string 
      }) => {
        try {
          const requestBody: any = {
            task,
            category,
          };
    
          if (priority) requestBody.priority = priority;
          if (status) requestBody.status = status;
    
          const newTask = await makeApiRequest("POST", "/tasks", requestBody);
          
          logDebug(`Created new task with ID ${newTask.id}`);
    
          return {
            content: [
              {
                type: "text",
                text: `Task created successfully with ID: ${newTask.id}`
              },
              {
                type: "text",
                text: JSON.stringify({
                  id: newTask.id,
                  task: newTask.task || task,
                  category: newTask.category || category,
                  priority: newTask.priority || priority || "medium",
                  status: newTask.status || status || "not_started",
                  create_time: newTask.create_time || new Date().toISOString()
                }, null, 2)
              }
            ]
          };
        } catch (error: any) {
          logError(`Error in createTask: ${error.message}`);
          
          return {
            content: [
              {
                type: "text",
                text: `Error creating task: ${error.message}`
              }
            ]
          };
        }
      }
    );
  • Core helper function used by createTask handler to perform authenticated POST request to the external Task Manager API.
    async function makeApiRequest(method: string, endpoint: string, data: any = null, params: any = null): Promise<any> {
      const url = `${API_BASE_URL}${endpoint}`;
      
      // Validate that API_KEY is defined
      if (!API_KEY) {
        throw new Error("TASK_MANAGER_API_KEY environment variable is not defined. Please check your .env file.");
      }
      
      logDebug(`API Request: ${method} ${url}`);
      
      // Standard headers
      const headers = {
        "X-API-Key": API_KEY,
        "Content-Type": "application/json; charset=utf-8",
        "Accept": "application/json, text/plain, */*",
        "User-Agent": "TaskMcpServer/1.0",
        "Connection": "close",
        "Cache-Control": "no-cache"
      };
    
      try {
        // Log request details
        const logEntry = `Timestamp: ${new Date().toISOString()}\nMethod: ${method}\nURL: ${url}\nParams: ${JSON.stringify(params)}\nData: ${JSON.stringify(data)}\nHeaders: ${JSON.stringify(headers)}\n\n`;
        fs.appendFileSync("api_debug.log", logEntry);
    
        // Configure axios request options
        const requestConfig: any = {
          method,
          url,
          headers,
          data,
          params,
          maxRedirects: 0,
          timeout: 20000,
          decompress: false,
          validateStatus: function (status: number) {
            return status < 500; // Don't reject if status code is less than 500
          }
        };
        
        // Ensure proper data encoding for all requests
        if (data) {
          requestConfig.data = JSON.stringify(data);
        }
        
        // Add transform request for properly handling all requests
        requestConfig.transformRequest = [(data: any, headers: any) => {
          // Force proper content type
          headers['Content-Type'] = 'application/json; charset=utf-8';
          return typeof data === 'string' ? data : JSON.stringify(data);
        }];
        
        // Add specific URL handling for individual task endpoints
        if (endpoint.startsWith('/tasks/') && method === 'GET') {
          // Fix to retrieve individual task by adding specific query parameters
          requestConfig.params = { ...params, id: endpoint.split('/')[2] };
        }
        
        const response = await axios(requestConfig);
        
        // Check for HTTP error status codes we didn't automatically reject
        if (response.status >= 400 && response.status < 500) {
          logError(`HTTP error ${response.status} from API`, response.data);
          
          // Enhanced error logging
          const errorLogEntry = `Timestamp: ${new Date().toISOString()}\nError: HTTP ${response.status}\nURL: ${url}\nMethod: ${method}\nResponse: ${JSON.stringify(response.data)}\n\n`;
          fs.appendFileSync("api_error.log", errorLogEntry);
          
          throw new Error(`API Error (${response.status}): ${JSON.stringify(response.data)}`);
        }
        
        // Check if response has expected format
        if ((method === "POST" && endpoint === "/tasks/list") || (method === "GET" && endpoint === "/tasks")) {
          logDebug(`listTasks response`, response.data.tasks || []);
          if (!response.data || !response.data.tasks || response.data.tasks.length === 0) {
            logDebug("API returned empty tasks array");
          }
        }
        
        return response.data;
      } catch (error: any) {
        logError(`API Error: ${error.message}`);
        
        // Enhanced error logging with more details
        const errorDetails = error.response 
          ? `Status: ${error.response.status}, Data: ${JSON.stringify(error.response.data || 'No response data')}` 
          : (error.request ? 'No response received' : error.message);
        
        const errorLogEntry = `Timestamp: ${new Date().toISOString()}\nError: ${error.message}\nDetails: ${errorDetails}\nURL: ${url}\nMethod: ${method}\n\n`;
        fs.appendFileSync("api_error.log", errorLogEntry);
        
        if (error.response) {
          throw new Error(
            `API Error (${error.response.status}): ${JSON.stringify(error.response.data || 'No response data')}`,
          );
        } else if (error.request) {
          throw new Error(`API Request Error: No response received (possible network issue)`);
        }
        throw error;
      }
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/milkosten/task-mcp-server'

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