Enterprise Architect MCP Server

A read-only Model Context Protocol (MCP) server for Sparx Enterprise Architect .qea exports. Gives AI agents access to EA analysis models — search elements, navigate packages, read use case scenarios, and traverse connectors — without a running EA instance.

Works with any MCP client (VS Code / GitHub Copilot, Claude Desktop, Cursor, Windsurf). Reads the .qea SQLite export directly, never writes to it, and every response carries completeness metadata so an agent can tell a truncated answer from a complete one.

Keywords: MCP server · Sparx Enterprise Architect · .qea · UML · use case scenarios · package tree · connectors · diagrams · model search · AI agent tooling

Prerequisites

• Node.js 22+ (uses the built-in node:sqlite module)
• A .qea file exported from Sparx Enterprise Architect

Installation

VS Code / GitHub Copilot

The quickest route is the Install in VS Code badge at the top of this page. There is nothing to fill in: the server asks for your .qea path the first time an agent queries the model, and remembers the answer for next time.

To register it from a terminal instead, which is handier for scripting or a shared setup, use one CLI call:

code --add-mcp '{\"name\":\"enterprise-architect\",\"command\":\"npx\",\"args\":[\"-y\",\"enterprise-architect-mcp\"]}'

The \" sequences are for the code shim, which re-parses the argument after PowerShell has already handed it over — escaping with PowerShell's own backtick, or using --%, still arrives with the quotes stripped. The single quotes stop PowerShell from touching the string. On bash or zsh the plain form works instead:

code --add-mcp '{"name":"enterprise-architect","command":"npx","args":["-y","enterprise-architect-mcp"]}'

To configure it by hand instead, add to your project's .vscode/mcp.json:

{
  "servers": {
    "enterprise-architect": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "enterprise-architect-mcp"]
    }
  }
}

Nothing personal is in that file, so it can be committed as-is and each developer answers the prompt once on their own machine. If you would rather not be asked at all, name the path up front — as a trailing argument, in an env block, or in a gitignored .env in your workspace root:

EA_QEA_PATH=C:\EA\exports\model.qea

Claude Desktop

The same path-less configuration goes in claude_desktop_config.json (%APPDATA%\Claude\ on Windows, ~/Library/Application Support/Claude/ on macOS):

{
  "mcpServers": {
    "enterprise-architect": {
      "command": "npx",
      "args": ["-y", "enterprise-architect-mcp"]
    }
  }
}

Claude Desktop does not run the server from a workspace folder, so a .env there is not reliable. If the client cannot show the path prompt at all, the server says so instead of failing silently, and you can name the path in an env block:

"env": { "EA_QEA_PATH": "C:\\EA\\exports\\model.qea" }

To run straight from source instead of npm, use "args": ["-y", "github:mm6502/enterprise-architect-mcp"].

Example Prompts

Once connected, try prompts like:

• "Search for elements related to 'legal entity'"
• "Show me the package structure under the root"
• "What are the use case scenarios for UC_SUBMIT_APPLICATION?"
• "What elements and connectors are on diagram 0103 Application Processing?"
• "Resolve the reference {3F2A7C10-5B4D-4e8a-9C1F-27D6E8B0A4F3}"
• "What columns does t_connector have?"
• "Which diagrams does element a7680 appear on?"

Configuration

The server does not need a path to start. It looks for one when an agent first queries the model, and takes the first source that actually opens:

1. CLI argument — mcp-server-ea C:\path\to\model.qea
2. Environment variable — EA_QEA_PATH (set in an env block or system env)
3. .env file — EA_QEA_PATH=... in a .env file in the working directory
4. A remembered answer — whatever you last told the prompt
5. The prompt — the client asks, and a working answer is remembered for next time

If you would rather never see the prompt — a CI job, a shared image, or simply a preference — put the path in a gitignored .env in the working directory. Copy the template:

Copy-Item .env.example .env

Then set your local path in .env:

EA_QEA_PATH=C:\EA\exports\model.qea

If the path points to a directory instead of a file, the server automatically picks the newest .qea file in it by modification time — point it at your export folder and new exports are picked up without reconfiguring anything:

EA_QEA_PATH=C:\EA\exports\

The .env file is gitignored — each developer sets their own path without affecting the shared config. It is also never committed, which is why it is the one route every new user has to set up by hand; answering the prompt once is what makes that unnecessary.

A source naming a path that cannot be opened is skipped rather than fatal, so the next source gets its turn. The reason goes to the server log, and once some later source opens, ea_get_model_info lists it under skipped. That is deliberate — a sample value left in an env block would otherwise outrank every answer you could give, and answering the prompt would never help. The cost is that a genuine typo is demoted quietly, so check ea_get_model_info if the server opens a different model than you expected.

Skipping is only worth it when an answer can take the skipped source's place, so two cases stay fatal: a path you passed on the command line (that is this run's explicit instruction, not a stale default), and any broken source in a client that cannot show a prompt — falling through there would quietly open some other model instead of telling you.

Answers are remembered per machine, in %APPDATA%\enterprise-architect-mcp\ on Windows, ~/Library/Application Support/enterprise-architect-mcp/ on macOS, and $XDG_CONFIG_HOME (or ~/.config) elsewhere; set EA_MCP_CONFIG_DIR to keep that file somewhere else. A path that does not open is never remembered, so asking again is enough to correct a mistyped answer.

Available Tools