Query 2-5 models in parallel with the same prompt. Returns side-by-side comparison with latency and token metrics.
AI agents invoke compare_models to trigger actions in HydraMCP. 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.
This tool actively triggers external operations by sending prompts to multiple LLM models simultaneously. It executes API calls to cloud/local LLMs, which may consume tokens/credits across subscriptions. It's not merely reading static data — it initiates live inference jobs.
From the tool's definition Query 2-5 models in parallel with the same prompt. Returns side-by-side comparison with latency and token metrics.
Documented attack patterns abuse exactly the kind of access compare_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HydraMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for compare_models:
{
"version": "1",
"default": "deny",
"tools": {
"compare_models": {
"limits": [
{
"counter": "compare_models_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}compare_models 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.
Free to start. No card required.
Query 2-5 models in parallel with the same prompt. Returns side-by-side comparison with latency and token metrics. It is categorised as a Execute tool in the HydraMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hydra MCP server in PolicyLayer and add a rule for compare_models: 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 HydraMCP. Nothing to install.
compare_models is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the compare_models 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 compare_models. 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.
compare_models is provided by the Hydra MCP server (pickle-pixel/hydramcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from HydraMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 HydraMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.