"How to Create 2D Fighting Games in Godot Engine" matching MCP servers:

One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose

Enables AI assistants to run the real Obsidian Tasks query language against a Markdown vault via MCP, supporting filters, relative dates, dependencies, grouping, sorting, and query explanations without requiring Obsidian to be running.

Enables agentic co-authoring of feature specs, decomposition into architecture-validated tickets, and idempotent syncing to Linear as projects with epics, sub-issues, and dependencies.

Lets AI agents turn a repository's git history into proposed GitHub issues grouped into units of work, each with a commit checklist and links, then create and close them only after approval. Planning is read-only and creation defaults to a dry run, skipping anything that already exists.

Enables AI clients like Claude to read and manage Microsoft To Do task lists and tasks via the Microsoft Graph API, running locally over stdio with secure token storage.

Enables managing Microsoft To Do lists and tasks through MCP, including creating, updating, completing, deleting, searching, and checklist operations via Microsoft Graph.

Enables to manage to-do items through natural language, with tools for creating, reading, updating, and deleting tasks.

Enables Claude to create, read, update and delete Microsoft To Do lists, tasks and checklist items, and Microsoft Planner plans, buckets and tasks, through Microsoft Graph as the signed-in user. Lists, plans and buckets can be referenced by ID or exact name, with destructive deletes requiring confirmation.

Provides programmatic access to all Scoring Engine API functionality for managing Red/White/Blue team cybersecurity competitions, including scoreboard, overview, team management, service management, injects, notifications, and admin tools.

Lets Claude and other AI clients read and modify Microsoft To Do through natural language, adding, completing, searching, updating, and deleting tasks and sub-steps by title and list name instead of ids. Personal Microsoft accounts need no Azure app registration — a single device-code sign-in grants access, with optional read-only and no-delete modes available.

Connects Claude AI to Google Sheets, Gmail, and Calendar for comprehensive revenue tracking and business management. Enables lead pipeline management, email handling, calendar scheduling, task tracking, and file operations through natural language.

Enables OAuth-capable MCP clients to connect to personal Microsoft To Do accounts and read lists, create or update tasks, manage checklist items, set due dates, and complete tasks.

Enables coding agents to manage Microsoft To Do lists and tasks through Microsoft Graph, with optional support for checklist items, linked resources, attachments, and delta synchronization.

Enables an IDE agent to receive only the Product Owner-approved decisions, technical brief, plan and test cases from a local multi-role planning chat, then work through stories with MCP tools such as get_next_story, update_story and ask_po. Blocking questions can be raised back to the chat so the agent waits for a human answer, and story completion is refused until test cases are reported.

A Model Context Protocol (MCP) server that enables AI assistants like Claude and Cursor to interact with Microsoft To Do via the Microsoft Graph API.

Enables an AI assistant to manage a simple to-do list stored in a local JSON file, with tools to add, list, get, complete, and delete tasks, plus a read-only pending tasks resource.

Enables AI agents to read and edit Microsoft To Do tasks, lists, and steps via Microsoft Graph, including due dates, reminders, and subtasks.

Enables comprehensive management of OpenProject work packages, projects, comments, and relations through natural language. Supports creating, updating, and organizing tasks with assignees, watchers, hierarchies, and inter-task relationships.

Enables AI tools to collaboratively write novels by managing chapters, characters, and story state through commands like validate, context, draft, review, and approve.

MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed.

Goodday‑MCP is a lightweight Model Context Protocol (MCP) server designed to seamlessly integrate with the Goodday project management platform via its API v2. It enables querying of projects, tasks, and users—without altering any data—making it ideal for secure context-aware applications

Lightweight project management for teams and AI agents.

Enables AI agents to manage Kanban boards, cards, sessions, and automations through a unified MCP interface with real-time updates, supporting delegation, agent sessions, and human-in-the-loop interactions.

A Model Context Protocol (MCP) server for Hubstaff API integration, enabling seamless time tracking, project management, and team collaboration through AI assistants.

Provides AI assistants with tools and a resource to manage a personal to-do list, enabling adding, listing, retrieving, completing, and deleting tasks over stdio.

MCP server for managing test cases, cycles, and results in Zephyr Scale on self-hosted Jira. Enables AI agents to create, search, update, and delete test artifacts through natural language.

Lets any MCP client drive the recruiting workflow in natural language: create roles, screen CVs, schedule and manage candidate interviews, and read back scored reports with transcripts.

Enables agents to write to Microsoft Planner: create tasks and buckets, list plans and tasks, and complete or reopen tasks using delegated Entra device-code sign-in.

MCP server for managing a task graph with live visualization. Enables Claude Code to create, update, and link nodes (tasks, subtasks, ideas, etc.) while a browser viewer displays the graph in real time.

Enables AI clients to read, search, comment on, create, update, assign, and move tickets and sprints in a mini-Jira platform via a personal access token. It runs locally over stdio and respects token permissions and project scope.