mindmap_prune · Mindmap MCP: Risk & Policy

WHAT IT DOES

What mindmap_prune does on Mindmap

AI agents invoke mindmap_prune to trigger actions in Mindmap. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why mindmap_prune needs a policy

The tool triggers an automated computational operation ('consolidation pass', 'recompute') that processes and modifies the memory store. This is not a simple read (which would just retrieve data) nor a simple write (which would insert/update discrete records).

From the tool's definition Tool performs a consolidation pass that 'recompute[s] every memory', which is an active computational operation with side effects that alters the state of stored memories through a non-trivial process.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mindmap_prune Rate-limited

mindmap_prune stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mindmap_prune": {
      "limits": [
        {
          "counter": "mindmap_prune_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about mindmap_prune

What does the mindmap_prune tool do? +

Run the consolidation pass that the background thread runs automatically: recompute every memory. It is categorised as a Execute tool in the Mindmap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mindmap_prune? +

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

What risk level is mindmap_prune? +

mindmap_prune is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mindmap_prune? +

Yes. Add a rate_limit block to the mindmap_prune 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 mindmap_prune completely? +

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

mindmap_prune is provided by the Mindmap MCP server (@ravi-labs/mindmap-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.