update_experiment · NeuronSearchLab MCP: Risk & Policy

WHAT IT DOES

What update_experiment does on NeuronSearchLab

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

WHY IT NEEDS A POLICY

Why update_experiment needs a policy

This tool creates or modifies data (an experiment record) in a reversible way, which fits the Write category. It is not Read (no retrieval only), Execute (no code/command execution indicated), Destructive (limited to draft status, suggests controlled modifications), or Financial.

From the tool's definition Tool name 'update_experiment' and description 'Update an experiment that is in draft status' indicate modification of existing data in a reversible manner.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_experiment Rate-limited

update_experiment 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": {
    "update_experiment": {
      "limits": [
        {
          "counter": "update_experiment_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 NeuronSearchLab, so you can run agents against it safely.

FAQ

Questions about update_experiment

What does the update_experiment tool do? +

Update an experiment that is in draft status. It is categorised as a Write tool in the NeuronSearchLab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_experiment? +

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

What risk level is update_experiment? +

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

Can I rate-limit update_experiment? +

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

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

update_experiment is provided by the NeuronSearchLab MCP server (neuronsearchlab/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.