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.

The Stages MCP server uses the Stages Collector Data API. Data that should be provided via MCP can be precisely defined and precalculated. The MCP server then connects the AI systems with the collected data. The MCP server adds context by providing the AI systems with domain-specific instructions.

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.

• 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
• Stop Stages
• Activate API tokens in Stages and restart 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

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

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)

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
}