"Magasins U" matching MCP servers:

Enables coding agents to query the dependency graph of a GitHub backlog, retrieve ordered ready work and prerequisite chains, atomically claim issues, and report blockers—so agents work in the correct order and safely in parallel.

Wraps UOF (U-Office Force) SOAP/ASMX WebServices as MCP tools, enabling AI agents to perform enterprise workflow tasks like form query, application, approval, and case closure via Model Context Protocol.

Enables persistent, auditable business operations state by storing knowledge, evidence, decisions, tasks, execution receipts, and review results in a local SQLite database, so different sessions can continue the same project.

A production-ready MCP server that connects AI assistants to the D-Tools System Integrator platform, enabling natural language management of AV projects, clients, catalogs, tasks, service orders, and purchase orders.

Connects AI assistants to the Basecamp 2 API, enabling management of projects, todos, messages, and people directly through natural language.

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 AI hosts to preserve and resume task and project state across conversations, process restarts, and worker or model replacement by storing structured records, snapshots, receipts, and bounded context views through a local stdio interface.

Enables AI agents to manage tasks through a structured lifecycle (todo, in_progress, ai_testing, manual_testing, deployment, completed) with human approval gates, providing a single-user task management system with CLI, REST API, and live updates.

Automates generation of Work Breakdown Structure (WBS) diagrams and project documents. Supports Mermaid, PNG, and .docx export for project MINTRANET.

Enables booking flights and hotels, creating investment portfolios, and managing kanban boards directly within a chat interface using generative UI components.

Exposes task-management tools over the Model Context Protocol, letting any MCP client discover and call operations to add, list, and complete tasks persisted to a local JSON file. It serves as the plug layer for a separate task kitchen module, with permissions enforced in the client.

Comprehensive quest orchestration system with KĀDI broker integration, multi-channel approval workflow, and Git-backed data storage.

Provides MCP access to an internal performance and consulting project collaboration system, enabling management of projects, stages, tasks, materials, evidence, approvals, and experience in a traceable chain, with Feishu for organization sync and collaboration.

Enables query and management of Zentao bugs, tasks, projects, and iterations directly from MCP-compatible IDEs like Cursor or Claude Desktop.

Exposes read-only tools that list projects and return a project's status, latest build, and unresolved issues as facts drawn from local sample JSON data. This gives a connected agent the raw evidence it needs to decide release readiness, without the server itself making any judgment.

Session-based development workflow MCP server for Claude Code that structures tasks into sessions with plans, progress tracking, and archiving for context resumption.

Enables AI assistants to manage task lists, tasks, subtasks, due dates, notes, and completion through the Google Tasks API, including reversible completion and syncing changes.

Enables AI assistants to read and write to OmniFocus database, allowing natural language task management, project creation, and GTD workflows.

MCP server for TickTick using the official OAuth 2.0 API. Create, list, update, complete, and delete tasks just by talking to Claude.

Enables assistants to read and analyze construction schedules like a scheduler: CPM, float, critical paths, DCMA 14-point, logic checks, update-to-update comparison, baseline variance, and S-curves from P6 XER and MS Project files.