Submit a multi-LLM consensus consultation to GRAEAE (PYTHIA). Modes: auto/single/all/debate/majority.
AI agents invoke graeae.consult to trigger actions in Mnemos. 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 triggers external LLM operations (potentially multiple, in debate or all modes), routing requests to one or more language models. It executes external operations whose effects depend on arguments (which LLMs are called, what prompt is sent, which mode). It does not merely read existing data but actively invokes external AI services.
From the tool's definition Submit a multi-LLM consensus consultation to GRAEAE (PYTHIA). Modes: auto/single/all/debate/majority.
Documented attack patterns abuse exactly the kind of access graeae.consult gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mnemos, and nothing reaches the server without passing your rules. This is the rule we recommend for graeae.consult:
{
"version": "1",
"default": "deny",
"tools": {
"graeae.consult": {
"limits": [
{
"counter": "graeae.consult_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}graeae.consult 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.
Submit a multi-LLM consensus consultation to GRAEAE (PYTHIA). Modes: auto/single/all/debate/majority. It is categorised as a Execute tool in the Mnemos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mnemos MCP server in PolicyLayer and add a rule for graeae.consult: 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 Mnemos. Nothing to install.
graeae.consult 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 graeae.consult 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 graeae.consult. 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.
graeae.consult is provided by the Mnemos MCP server (ncz-os/mnemos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mnemos, 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.
15 Mnemos tools catalogued and risk-classified — across an index of 43,000+ MCP servers.