Low Risk

check_relevance

Free relevance screen — checks whether an action touches any of your policy variables before running a paid check. Returns a relevance score and which variables matched. If should_check is true, run check_action. If false, the action is unrelated to your policy — skip the paid check. No credits c...

Risk signalsHandles credentials or secrets (api_key)

Part of the Icme Preflight server.

check_relevance is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE ICME PREFLIGHT →

Free to start. No card required.

AI agents call check_relevance to retrieve information from Icme Preflight without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though check_relevance only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "check_relevance": {}
  }
}

See the full Icme Preflight policy for all 14 tools.

Get this rule live on your own Icme Preflight server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY ICME PREFLIGHT →

View all 14 tools →

These attack patterns abuse exactly the kind of access check_relevance gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so check_relevance only ever does what you allow.

SECURE ICME PREFLIGHT →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the check_relevance tool do? +

Free relevance screen — checks whether an action touches any of your policy variables before running a paid check. Returns a relevance score and which variables matched. If should_check is true, run check_action. If false, the action is unrelated to your policy — skip the paid check. No credits charged. Requires api_key.. It is categorised as a Read tool in the Icme Preflight MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_relevance? +

Register the Icme Preflight MCP server in PolicyLayer and add a rule for check_relevance: 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 Icme Preflight. Nothing to install.

What risk level is check_relevance? +

check_relevance is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit check_relevance? +

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

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

check_relevance is provided by the Icme Preflight MCP server (https://api.icme.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Icme Preflight tool call.

Deterministic rules across all 14 Icme Preflight tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.