AI agents call speed_test to retrieve information from Keel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a network diagnostic measurement that reads/retrieves latency and speed metrics from the network without side effects. It is analogous to the sibling tools like 'ping' and 'http_check' which are also passive diagnostic reads. The most severe risk is if an attacker uses it to probe network characteristics, but this is reconnaissance-level and presents no destructive or execution capability.
From the tool's definition Tool name 'speed_test' and description 'Measure network download speed and latency' indicate data retrieval only. No modification, execution of arbitrary code, deletion, or financial operations occur.
Attacks that exploit this kind of access
Measure network download speed and latency. It is categorised as a Read tool in the Keel MCP Server, which means it retrieves data without modifying state.
Register the Keel MCP server in PolicyLayer and add a rule for speed_test: 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 Keel. Nothing to install.
speed_test is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the speed_test 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.
Set action: deny in the PolicyLayer policy for speed_test. 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.
speed_test is provided by the Keel MCP server (seayniclabs/keel). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →