productive-io-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@productive-io-mcplist my open tasks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Productive.io MCP Server
A Model Context Protocol (MCP) server for interacting with Productive.io task management platform.
Features
š§ Extensible Architecture - Plugin-based tool system for easy extension
š¦ Modular Design - Clean separation of concerns with TypeScript
š Type-Safe - Full TypeScript support with strict type checking
āļø Configuration Management - Environment-based configuration
šÆ Easy to Extend - Add new tools by creating a single class
Related MCP server: productive-mcp-rb2
Installation
# Install dependencies
pnpm install
# Build the project
npm run buildConfiguration
For Claude Desktop
Add the MCP server to your Claude Desktop config file with environment variables:
Location:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Configuration:
{
"mcpServers": {
"productive.io": {
"command": "node",
"args": ["/Users/joelkrause/dev/productive-mcp/build/index.js"],
"env": {
"PRODUCTIVE_API_TOKEN": "your-api-token-here",
"PRODUCTIVE_ORGANIZATION_ID": "your-organization-id",
"PRODUCTIVE_USER_ID": "your-user-id"
}
}
}
}For Development/Testing
You can also use a .env file (use .env.example as a template):
cp .env.example .envRequired environment variables:
PRODUCTIVE_API_TOKEN- Your Productive.io API tokenPRODUCTIVE_ORGANIZATION_ID- Your organization IDPRODUCTIVE_USER_ID- Your user ID
Available Tools
get_task
Get a single task from Productive.io by URL.
Parameters:
url(string) - Productive.io task URL
get_tasks
Get multiple tasks with optional filters.
Parameters:
assignee_id(string, optional) - Filter by assignee IDstatus(number, optional) - Filter by status (1=Open, 2=Closed)project_id(string, optional) - Filter by project ID
Project Structure
src/
āāā config/ # Configuration management
ā āāā index.ts # Environment-based config loader
āāā services/ # API clients and services
ā āāā ProductiveApiClient.ts # Typed Productive.io API client
āāā tools/ # MCP tools (plugins)
ā āāā base/ # Base tool class
ā ā āāā BaseTool.ts
ā āāā get-task/ # Individual tool modules
ā ā āāā index.ts # Tool implementation
ā ā āāā handler.ts # Business logic (includes URL extraction)
ā ā āāā schema.ts # Zod validation schema
ā āāā get-tasks/
ā ā āāā index.ts
ā ā āāā handler.ts
ā ā āāā schema.ts
ā āāā index.ts # Tool registry and auto-registration
āāā types/ # TypeScript type definitions
ā āāā config.types.ts
ā āāā productive.types.ts
ā āāā tool.types.ts
āāā index.ts # Main entry pointAdding a New Tool
Adding a new tool is simple with the extensible architecture:
1. Create a new tool directory
mkdir -p src/tools/your-tool2. Create the schema (src/tools/your-tool/schema.ts)
import { z } from "zod";
export const YourToolSchema = z.object({
param1: z.string().describe("Description of param1"),
param2: z.number().optional().describe("Optional param2"),
});
export type YourToolInput = z.infer<typeof YourToolSchema>;3. Create the handler (src/tools/your-tool/handler.ts)
import { ProductiveApiClient } from "../../services/ProductiveApiClient.js";
import { ToolResponse } from "../../types/tool.types.js";
export async function handleYourTool(
input: YourToolInput,
apiClient: ProductiveApiClient
): Promise<ToolResponse> {
try {
// Your logic here
const result = await apiClient.someMethod();
return {
content: [{ type: "text", text: "Success!" }],
};
} catch (error) {
return {
content: [
{
type: "text",
text: `Error: ${error instanceof Error ? error.message : "Unknown"}`,
},
],
isError: true,
};
}
}4. Create the tool class (src/tools/your-tool/index.ts)
import { BaseTool } from "../base/BaseTool.js";
import { ProductiveApiClient } from "../../services/ProductiveApiClient.js";
import { ToolResponse } from "../../types/tool.types.js";
import { YourToolSchema, YourToolInput } from "./schema.js";
import { handleYourTool } from "./handler.js";
export class YourTool extends BaseTool<YourToolInput> {
readonly name = "your_tool";
readonly description = "Description of what your tool does";
readonly schema = YourToolSchema;
private apiClient: ProductiveApiClient;
constructor(apiClient?: ProductiveApiClient) {
super();
this.apiClient = apiClient || new ProductiveApiClient();
}
async execute(input: YourToolInput): Promise<ToolResponse> {
return handleYourTool(input, this.apiClient);
}
}5. Register the tool (src/tools/index.ts)
import { YourTool } from "./your-tool/index.js";
export function getAllTools(): Tool[] {
return [
new GetTaskTool(),
new GetTasksTool(),
new YourTool(), // Add your tool here
];
}That's it! Your new tool will be automatically registered and available.
Development
# Build the project
npm run build
# Watch mode for development
npm run dev
# Type checking only
npm run typecheck
# Clean build directory
npm run clean
# Clean and rebuild
npm run rebuildArchitecture Benefits
Extensibility
Plugin-based: New tools are self-contained modules
Auto-registration: Tools are automatically registered from the registry
No core changes: Adding tools doesn't require modifying the main server code
Type Safety
Full TypeScript: Strict type checking enabled
Type inference: Zod schemas provide runtime validation and compile-time types
API types: Fully typed Productive.io API responses
Maintainability
Separation of concerns: Each tool has its own directory with schema, handler, and implementation
Reusable components: BaseTool provides common functionality
Clear structure: Easy to navigate and understand
Best Practices
Error handling: Consistent error responses across all tools
Configuration: Environment-based configuration management
Documentation: JSDoc comments throughout the codebase
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner.
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Create and manage MeisterTask projects, tasks, and notes from your AI assistant.
Agent-complete, permission-scoped product operations for Priorify workspaces.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with Todoist for comprehensive task and project management, including creating tasks with natural language, managing projects, sections, labels, comments, and tracking productivity statistics.2964MIT
- AlicenseAqualityDmaintenanceEnables interaction with Productive.io for task management, time tracking, budget monitoring, and project overview through natural language.8316ISC
- AlicenseNot gradedqualityDmaintenanceEnables LLM applications to interact with OpenProject for project management, work package tracking, and task creation.76MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage Trackfusion projects and tasks, including listing, creating, updating, and filtering tasks.1
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/dotcollective-joel/productive-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server