Stages MCP Server (Beta)

MCP (Model Context Protocol) has established itself as the universal way to connect LLMs (Large Language Models) and other AI systems with data sources.

Through our MCP server, AI systems can access process data managed in Stages for various purposes and use cases.

In the currently provided MCP solution Stages provides access to a single workspace only. In future versions of MCP support this limitation is going to be eliminated.

How it works

The Stages MCP server uses the Stages Collector Data API. Data that should be provided via MCP need to be provided by one or multiple Stages Collector jobs. The MCP server then provides the AI-systems with the collected data.

How to get started

This feature is currently in beta. It requires Stages 7.12.5.1 or later, or Stages 26.1.0.0 or later.

Please request the current version of the MCP package from Stages support. You will receive an MCP server, script, and configuration suitable for processes based on the unified configuration metamodel.

Installation

  • Stop Stages
  • Add mcp-server.properties to the Stages conf folder
  • Choose the right WAR file:
    • Stages 7.12: mcp-web-tomcat-9-*.war
    • Stages 26.1: mcp-web-tomcat-10-*.war
    • Extract the WAR file to stages/tomcat/webapps/mcp. Ensue that the folders META-INF and WEB-INF are directly in the mcp folder
  • Start Stages
  • Go to the Company workspace and add the workspace variable mcpDefaultWorkspace. Set the value to the ID of the workspace that you want to access.
  • In Stages go to Administration → Jobs and create a job for MCP (e.g. “mcp”)
  • Upload the mcp.js file to MCP job
  • Run the job once
  • Specify a cron expression to keep the data updated

If Stages is running, you can check the path /mcp/status on your Stages server to see if the MCP server is running. For example: https://stages.example.com/mcp/status

Configure credentials

Access to the MCP server and Stages data is protected. A personal Stages API token is required to access the REST API. The user must have the following privileges:

  • Process Modeler
  • CollectorData Read and Create permission
  • Permission according to the data collector (e.g. Process Read)

Configure AI system

Currently Stages MCP server supports Server-Sent Events (SSE) protocol. The endpoint is /mcp/sse, e.g.:

https://stages.example.com/mcp/sse

The API token that was created must be provided to the MCP server via the header StagesToken.

An example MCP configuration:

{
  "command": "npx",
  "args": [
    "mcp-remote",
    "https://stages.example.com/mcp/sse",
    "--header",
    "StagesToken: ${AUTH_TOKEN}"
  ],
  "env": {
    "AUTH_TOKEN": "eyJh..."
  },
  "active": true
}