AI agents call get_cids_by_smiles to retrieve information from OrigeneMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data (CID identifiers) based on input (SMILES notation). It performs a read-only lookup against a biomedical database without creating, modifying, deleting, or executing any code. The blast radius of misuse is minimal—an agent could retrieve incorrect compound identifiers, but this would not alter data, execute code, or cause financial harm.
From the tool's definition Tool name 'get_cids_by_smiles' and description 'Obtain the CID corresponding to the drug smiles' indicate a lookup/retrieval operation that converts a chemical structure representation (SMILES) into a PubChem Compound ID (CID).
Documented attack patterns abuse exactly the kind of access get_cids_by_smiles gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OrigeneMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_cids_by_smiles:
{
"version": "1",
"default": "deny",
"tools": {
"get_cids_by_smiles": {}
}
}get_cids_by_smiles 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.
Obtain the CID corresponding to the drug smiles. It is categorised as a Read tool in the OrigeneMCP MCP Server, which means it retrieves data without modifying state.
Register the Origene MCP server in PolicyLayer and add a rule for get_cids_by_smiles: 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 OrigeneMCP. Nothing to install.
get_cids_by_smiles 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 get_cids_by_smiles 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 get_cids_by_smiles. 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.
get_cids_by_smiles is provided by the Origene MCP server (gentel-lab/origenemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OrigeneMCP, 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.
439 OrigeneMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.