set_sampling · Mcp Open Webresearch MCP: Risk & Policy

WHAT IT DOES

What set_sampling does on Mcp Open Webresearch

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

WHY IT NEEDS A POLICY

Why set_sampling needs a policy

This tool creates or modifies data reversibly by changing the sampling setting and writing it to the .env file. It is not destructive (the change can be undone by toggling the setting back), not financial, not execute-level code execution (it configures a feature rather than running arbitrary code), and not merely a read operation.

From the tool's definition The tool 'set_sampling' modifies configuration state by enabling or disabling LLM-based relevance filtering and 'Persists setting to .env', which means it writes to a configuration file.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_sampling Rate-limited

set_sampling 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": {
    "set_sampling": {
      "limits": [
        {
          "counter": "set_sampling_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 Mcp Open Webresearch, so you can run agents against it safely.

FAQ

Questions about set_sampling

What does the set_sampling tool do? +

Enable or disable LLM-based relevance filtering for search results. When enabled, an LLM evaluates each result for relevance to the query. Requires either: (1) IDE/client with sampling support, OR (2) LLM_BASE_URL set (LLM_API_KEY optional for local models). Persists setting to .env. It is categorised as a Write tool in the Mcp Open Webresearch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_sampling? +

Register the Mcp Open Webresearch MCP server in PolicyLayer and add a rule for set_sampling: 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 Mcp Open Webresearch. Nothing to install.

What risk level is set_sampling? +

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

Can I rate-limit set_sampling? +

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

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

set_sampling is provided by the Mcp Open Webresearch MCP server (rinaldowouterson/mcp-open-webresearch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.