honeycomb_query_result_create · Honeycomb MCP: Risk & Policy

WHAT IT DOES

What honeycomb_query_result_create does on Honeycomb

AI agents invoke honeycomb_query_result_create to trigger actions in Honeycomb. 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 honeycomb_query_result_create needs a policy

This tool triggers the execution of a query on the Honeycomb backend. While it doesn't delete data or move money, it initiates a computational operation whose effects depend on the query arguments. This places it in the Execute category. Severity is medium because misuse could consume significant compute resources or expose sensitive observability data, but it cannot directly modify or destroy data.

From the tool's definition "Run a previously created query and return a query result ID" — the tool actively executes/triggers a query operation rather than just reading or writing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

honeycomb_query_result_create Rate-limited

honeycomb_query_result_create 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": {
    "honeycomb_query_result_create": {
      "limits": [
        {
          "counter": "honeycomb_query_result_create_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 Honeycomb, so you can run agents against it safely.

FAQ

Questions about honeycomb_query_result_create

What does the honeycomb_query_result_create tool do? +

Run a previously created query and return a query result ID that can be used to retrieve the results. It is categorised as a Execute tool in the Honeycomb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on honeycomb_query_result_create? +

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

What risk level is honeycomb_query_result_create? +

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

Can I rate-limit honeycomb_query_result_create? +

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

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

honeycomb_query_result_create is provided by the Honeycomb MCP server (kajirita2002/honeycomb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.