Get a structured liquidation probability prediction for a specific borrower or the top candidates. Returns: health_factor, cross_probability (0–1), estimated_ev_usd, lead_time_estimate_s (how long until crossing at current oracle velocity), oracle_velocity (|Δprice|/min on collateral asset), and ...
Part of the MEV Intelligence server.
Free to start. No card required.
AI agents call predict_liquidation_probability to retrieve information from MEV Intelligence 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 predict_liquidation_probability 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.
{
"version": "1",
"default": "deny",
"tools": {
"predict_liquidation_probability": {}
}
}See the full MEV Intelligence policy for all 9 tools.
These attack patterns abuse exactly the kind of access predict_liquidation_probability gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get a structured liquidation probability prediction for a specific borrower or the top candidates. Returns: health_factor, cross_probability (0–1), estimated_ev_usd, lead_time_estimate_s (how long until crossing at current oracle velocity), oracle_velocity (|Δprice|/min on collateral asset), and a human-readable verdict. This is the core moat tool — it exposes the prediction layer that drives bundle decisions. Call this before submit_bundle to confirm the opportunity is still live and to size your bribe correctly. Full probability model with confidence intervals available at /intelligence/liquidation-waves with x402 payment ($0.50).. It is categorised as a Read tool in the MEV Intelligence MCP Server, which means it retrieves data without modifying state.
Register the MEV Intelligence MCP server in PolicyLayer and add a rule for predict_liquidation_probability: 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 MEV Intelligence. Nothing to install.
predict_liquidation_probability 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 predict_liquidation_probability 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 predict_liquidation_probability. 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.
predict_liquidation_probability is provided by the MEV Intelligence MCP server (https://mev.advalorem.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 MEV Intelligence 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.