OpenProject 17.2 Adds MCP Server for Secure AI Integrations

OpenProject | Open Source Project Management

Mar 14, 2026 · Updated Apr 25, 2026

OpenProject 17.2 introduces an MCP Server that exposes project data as Model Context Protocol endpoints. Teams can now connect LLMs and AI agents to their projects while keeping authentication and access control fully managed. Available for Enterprise plans.

OpenProject, an open-source project management platform, released version 17.2 with a new MCP Server as an Enterprise add-on. The server exposes OpenProject's APIv3 resources as MCP-compatible endpoints, enabling secure, authenticated connections from LLMs and other MCP clients.

This brings AI agents into project workflows without sacrificing data control. Rather than exporting data to external AI services, teams keep project information in OpenProject while AI systems query it through the MCP interface. The Enterprise add-on includes administrative UI support for configuring and monitoring these connections.

Teams on Enterprise plans can enable the MCP Server to let AI agents access project data contextually — querying work packages, tracking progress, or generating reports while respecting existing permissions and authentication.

View the full update on openproject.org

OpenProject | Open Source Project Management

@openprojectMar 11

🚀 OpenProject 17.2 is here – bringing AI to your projects while keeping you fully in control. 🔹 Secure AI integrations with the new MCP Server 🔹 Improved Project Overview 🔹 Comment fields for project attributes ...and much more! Release notes: https://t.co/JHFW9cu8WR https://t.co/Cj2eLMOjHE

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

OpenAI Launches Secure MCP Tunnels to Connect Agents to Private Data

OpenAI released Secure MCP Tunnel, a networking tool that lets AI agents access private on-premises databases and tools through outbound-only HTTPS connections. This removes the need for inbound firewall exceptions, allowing enterprises to safely ground agents in sensitive internal data.

n8nMay 27

n8n Simplifies AI Agent Tooling With One Click MCP Authentication

n8n v2.22.4 introduces a streamlined UI for connecting AI agents to external tools via the Model Context Protocol. By replacing manual configuration with a pick and sign-in workflow, the platform removes the technical friction of wiring up specialized agent capabilities.

Ian NuttallMar 15

Keep Launches MCP Server to Chat With Your Markdown Feed

Keep now has an MCP server, letting any MCP-compatible AI client search, read, and save items in your markdown feed. A researcher or marketer can ask Claude or ChatGPT to find articles on a topic directly from their saved library.

BasedashMay 16

Basedash Integrates MCP Connectors to Enable Agentic Actions Across Business Tools

Basedash added support for the Model Context Protocol, allowing its AI agent to execute actions in external tools like Slack and GitHub directly from chat. This shift moves the platform from a passive data reader to an active operational hub that can manage workflows across a company's entire SaaS stack.