Compute Tanimoto similarity between two molecules using Morgan fingerprints (ECFP4). Score ranges 0-1, where >0.7 suggests similar bioactivity.
AI agents call molecular_similarity 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 is a pure analytical function that queries molecular properties and returns a calculated metric. It has no side effects—it does not modify molecules, execute arbitrary code, delete data, or trigger external operations. The tool is read-only in nature: it takes molecular inputs and returns a similarity assessment.
From the tool's definition Tool computes and returns a similarity score between two molecules using established cheminformatics metrics (Morgan fingerprints, Tanimoto similarity). The description explicitly states it 'computes' and returns a numerical score (0-1 range).
Documented attack patterns abuse exactly the kind of access molecular_similarity 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 molecular_similarity:
{
"version": "1",
"default": "deny",
"tools": {
"molecular_similarity": {}
}
}molecular_similarity 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.
Compute Tanimoto similarity between two molecules using Morgan fingerprints (ECFP4). Score ranges 0-1, where >0.7 suggests similar bioactivity. 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 molecular_similarity: 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.
molecular_similarity 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 molecular_similarity 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 molecular_similarity. 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.
molecular_similarity 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.