Export a model to various formats (JSON, GraphML, SFILES string) - Replaces dexpi_export_json, dexpi_export_graphml, sfiles_to_string
AI agents use model_save to create or update resources in Engineering MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engineering MCP Server environment.
This tool exports/serializes engineering diagrams to persistent formats. Although export operations are typically read-like, the context shows this server is designed to 'create, modify, analyze, and persist' diagrams. The 'model_save' operation creates new external representations of models in durable formats (JSON, GraphML, SFILES), which is a write operation that modifies the external state of the system.
From the tool's definition Tool name 'model_save' and description 'Export a model to various formats (JSON, GraphML, SFILES string)' indicates data output/serialization.
Documented attack patterns abuse exactly the kind of access model_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engineering MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for model_save:
{
"version": "1",
"default": "deny",
"tools": {
"model_save": {
"limits": [
{
"counter": "model_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}model_save 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.
Free to start. No card required.
Export a model to various formats (JSON, GraphML, SFILES string) - Replaces dexpi_export_json, dexpi_export_graphml, sfiles_to_string. It is categorised as a Write tool in the Engineering MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engineering MCP Server MCP server in PolicyLayer and add a rule for model_save: 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 Engineering MCP Server. Nothing to install.
model_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the model_save 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.
Set action: deny in the PolicyLayer policy for model_save. 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.
model_save is provided by the Engineering MCP Server MCP server (puran-water/dexpi-sfiles-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engineering MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
72 Engineering MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.