Predict ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for a molecule. Returns AI-predicted risk assessments for key safety endpoints including BBB penetration, intestinal absorption, hERG inhibition, CYP3A4 inhibition, Ames mutagenicity, and DILI risk.
AI agents call predict_admet to retrieve information from MedSci Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs computational analysis of molecular properties and generates predictions about safety endpoints. It retrieves or derives information about a molecule without creating, modifying, deleting, or executing anything irreversible. The output is informational (risk assessments) used to inform research decisions, not to take actions.
From the tool's definition Tool description states it 'Predict[s] ADMET properties' and 'Returns AI-predicted risk assessments'—pure analysis and prediction with no modification of data, creation of entities, code execution, deletion, or financial transactions.
Documented attack patterns abuse exactly the kind of access predict_admet gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MedSci Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for predict_admet:
{
"version": "1",
"default": "deny",
"tools": {
"predict_admet": {}
}
}predict_admet is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Predict ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for a molecule. Returns AI-predicted risk assessments for key safety endpoints including BBB penetration, intestinal absorption, hERG inhibition, CYP3A4 inhibition, Ames mutagenicity, and DILI risk. It is categorised as a Read tool in the MedSci Agent MCP Server, which means it retrieves data without modifying state.
Register the MedSci Agent MCP server in PolicyLayer and add a rule for predict_admet: 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 MedSci Agent. Nothing to install.
predict_admet 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_admet 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_admet. 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_admet is provided by the MedSci Agent MCP server (omar-a-hassan/medsci-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MedSci Agent, 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.
28 MedSci Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.