Task Manager MCP Server

Created By
jhawkins11a year ago
Node.js MCP server using LLMs (Gemini/OpenRouter) for AI-assisted task planning, breakdown, and code review. Designed for Cursor integration.
Overview

What is Task Manager MCP?

Task Manager MCP is a Node.js server designed to integrate with AI code editors like Cursor, utilizing LLMs (Gemini/OpenRouter) for AI-assisted task planning, breakdown, and code review.

How to use Task Manager MCP?

To use Task Manager MCP, clone the repository, install dependencies, configure API keys, and run the server. It can be integrated with Cursor for task management.

Key features of Task Manager MCP?

  • Complex Feature Planning: Generates step-by-step coding plans based on feature descriptions.
  • Integrated UI Server: Provides a user interface to view tasks and progress.
  • Unlimited Context Window: Utilizes Gemini 2.5's extensive context capabilities.
  • Conversation History: Maintains a history of conversations for context.
  • Task CRUD: Allows for creating, reading, updating, and deleting tasks.
  • Code Review: Analyzes code changes and generates new tasks as needed.

Use cases of Task Manager MCP?

  1. Planning and managing software development tasks.
  2. Assisting in code reviews and generating follow-up tasks.
  3. Enhancing productivity in AI-assisted coding environments.

FAQ from Task Manager MCP?

  • Can Task Manager MCP be used without Cursor?

Yes, it can be run independently for local testing.

  • Is there a cost associated with using Task Manager MCP?

The server can be configured to minimize costs by using free models from OpenRouter.

  • How does Task Manager MCP handle clarification requests?

It pauses planning and interacts with the UI for additional information.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
jhawkins11
Star
5
Language
TypeScript
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

5 hours ago
Alloy

2 days ago