"How to implement intent recognition in MCP" 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 agentic co-authoring of feature specs, decomposition into architecture-validated tickets, and idempotent syncing to Linear as projects with epics, sub-issues, and dependencies.

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.

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.

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.

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 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.

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.

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.

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.

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.

Enables AI agents to interact with Redmine through intent-shaped tools for issue tracking, time logging, project management, and more.