save_map · Ros MCP: Risk & Policy

WHAT IT DOES

What save_map does on Ros

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

WHY IT NEEDS A POLICY

Why save_map needs a policy

The tool creates or modifies persistent data by saving a map file. While the operation is reversible (maps can be resaved or deleted), it commits data to storage and is a Write operation rather than Read (which would only retrieve existing maps). It is not Destructive because saving is reversible and non-destructive.

From the tool's definition Tool name is 'save_map' and description states it 'Request a map save and wait for the result.' This persists data (the map) to storage, modifying the persistent state of the robot system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_map Rate-limited

save_map 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_map": {
      "limits": [
        {
          "counter": "save_map_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 Ros, so you can run agents against it safely.

FAQ

Questions about save_map

What does the save_map tool do? +

Request a map save and wait for the result. It is categorised as a Write tool in the Ros 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_map? +

Register the Ros MCP server in PolicyLayer and add a rule for save_map: 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 Ros. Nothing to install.

What risk level is save_map? +

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

Can I rate-limit save_map? +

Yes. Add a rate_limit block to the save_map 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_map completely? +

Set action: deny in the PolicyLayer policy for save_map. 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_map? +

save_map is provided by the Ros MCP server (reidlo5135/ros-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.