view_save · THOUGHT MCP: Risk & Policy

WHAT IT DOES

What view_save does on THOUGHT

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

WHY IT NEEDS A POLICY

Why view_save needs a policy

This tool creates/stores a named view by saving a Cypher query definition. It is a write operation (creating a persistent named object in the memory store) that is reversible — views can typically be deleted or overwritten.

From the tool's definition Save a Cypher query as a named view

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

view_save Rate-limited

view_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "view_save": {
      "limits": [
        {
          "counter": "view_save_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 THOUGHT, so you can run agents against it safely.

FAQ

Questions about view_save

What does the view_save tool do? +

Save a Cypher query as a named view (re-evaluates on each call). It is categorised as a Write tool in the THOUGHT MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on view_save? +

Register the THOUGHT MCP server in PolicyLayer and add a rule for view_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 THOUGHT. Nothing to install.

What risk level is view_save? +

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

Can I rate-limit view_save? +

Yes. Add a rate_limit block to the view_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.

How do I block view_save completely? +

Set action: deny in the PolicyLayer policy for view_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.

What MCP server provides view_save? +

view_save is provided by the THOUGHT MCP server (rnbbarrett/thought-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.