save_model · Mcp Archimate MCP: Risk & Policy

WHAT IT DOES

What save_model does on Mcp Archimate

AI agents use save_model to create or update resources in Mcp Archimate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Archimate environment.

WHY IT NEEDS A POLICY

Why save_model needs a policy

The tool writes changes to disk by persisting the in-memory model back to its source file. While not irreversible if backups exist, this commits data modifications to the file system and could overwrite previous versions. This is Write rather than Destructive because the operation is reversible (prior versions can be recovered) and the intent is to persist legitimate model updates, not to erase data.

From the tool's definition Saves the current in-memory model to its source file on disk—this modifies the persisted state of the ArchiMate model file, which is a write operation that alters stored data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_model Rate-limited

save_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_model": {
      "limits": [
        {
          "counter": "save_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Archimate, so you can run agents against it safely.

FAQ

Questions about save_model

What does the save_model tool do? +

Saves the current in-memory model to its source file on disk (Open Exchange XML). It is categorised as a Write tool in the Mcp Archimate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_model? +

Register the Mcp Archimate MCP server in PolicyLayer and add a rule for save_model: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Archimate. Nothing to install.

What risk level is save_model? +

save_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_model? +

Yes. Add a rate_limit block to the save_model rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block save_model completely? +

Set action: deny in the PolicyLayer policy for save_model. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides save_model? +

save_model is provided by the Mcp Archimate MCP server (lacrif/mcp-archimate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.