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 valid versions of workspaces only.

The Stages MCP server grants access to the valid versions of all workspaces the authenticated user has access to and for which the “MCP” permission is granted.

Currently it offers 10 tools to browse and search workspaces and elements. This is subject to change.

The Stages MCP server is integrated into Stages 26.2.0.0 and later.

<placeholder for authentication setup instructions>

Note: Stages 7.12.5.1 or later and Stages 26.1.0.0 or later had a beta implementation of this feature that worked quite differently.

Configuration depends on Stages version

Currently Stages MCP server supports Server-Sent Events (SSE) protocol for Tomcat 9 version. 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
}

Currently Stages MCP server supports Streamable HTTP protocol for Tomcat 10 version. The endpoint is /mcp/http, e.g.:

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

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/http",
    "--header",
    "StagesToken: ${AUTH_TOKEN}"
  ],
  "env": {
    "AUTH_TOKEN": "eyJh..."
  },
  "active": true
}