OpenProject

Exposes OpenProject CRUD tools via MCP for remote agents and AI workflows using Netlify Functions.
  • typescript

3

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You deploy and run a single MCP (Model Context Protocol) server that bridges your OpenProject instance with AI agents. This server exposes a defined set of OpenProject CRUD tools and can be accessed by MCP clients to perform actions remotely while keeping your OpenProject credentials secure and centralized.

How to use

You connect MCP clients to the OpenProject MCP server to create, read, update, and delete projects and tasks. Use the available tools to manage projects and work packages from your AI workflows or remote agents. Start from a live endpoint to test capabilities, then integrate with your preferred MCP client (for example, Langflow or other agents) to issue tool calls and receive results in structured responses.

How to install

Prerequisites and setup steps help you get the MCP server ready for use with Netlify Functions and OpenProject.

# 1. Install Netlify CLI globally
npm install -g netlify-cli

# 2. Clone the project (if you are starting from a template)
git clone git@github.com:jessebautista/mcp-openproject.git
cd mcp-openproject

# 3. Install Node dependencies
npm install

# 4. Install Python mcp-proxy (for SSE bridging tests)
# Ensure Python 3.10+ is active
python3.10 -m pip install mcp-proxy

Configure environment variables in a local .env file to point to your OpenProject instance.

OPENPROJECT_API_KEY="your_openproject_api_key_here"
OPENPROJECT_URL="https://your_openproject_instance.com"
OPENPROJECT_API_VERSION="v3"

Run the local Netlify development server to host the MCP function locally and load environment variables from the .env file.

netlify dev

Test locally with the MCP Inspector by pointing it to your local server.

npx @modelcontextprotocol/inspector npx mcp-remote@next http://localhost:8888/mcp

Additional notes

Netlify deployment uses environment variables exposed to Functions. When you deploy, set OPENPROJECT_API_KEY, OPENPROJECT_URL, and OPENPROJECT_API_VERSION in Netlify’s environment settings so the MCP server can access OpenProject securely.

To test a deployed version, use the live Netlify endpoint for the MCP function.

For remote SSE clients, you can bridge through an mcp-proxy and a public tunnel (ngrok) during development. This setup is intended for testing; for production, deploy a persistent bridge on a public server.

Netlify Function Configuration

Redirects ensure requests to /mcp map to your Express function handler. The configuration below demonstrates the mapping.

[[redirects]]
  force = true
  from = "/mcp/*" # Use wildcard to catch all sub-paths if needed
  status = 200
  to = "/.netlify/functions/express-mcp-server"

[[redirects]]
  force = true
  from = "/mcp"
  status = 200
  to = "/.netlify/functions/express-mcp-server"

Available tools

openproject-create-project

Creates a new OpenProject project via the MCP server

openproject-get-project

Retrieves a project by ID from OpenProject

openproject-list-projects

Lists all projects with pagination support

openproject-update-project

Updates details of an existing OpenProject project

openproject-delete-project

Deletes a project in OpenProject

openproject-create-task

Creates a new task (work package) within a project in OpenProject

openproject-get-task

Retrieves a task by ID from OpenProject

openproject-list-tasks

Lists tasks, optionally filtered by project, with pagination

openproject-update-task

Updates an existing task; requires lockVersion for concurrency control

openproject-delete-task

Deletes a task in OpenProject

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational