Score protein stability using ESM2 pseudo-log-likelihood.
AI agents call score_stability to retrieve information from Protein Design without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only evaluation using a machine learning model (ESM2) to compute a stability metric. It retrieves or computes derived information about a protein structure but does not execute arbitrary user-supplied code, modify persistent data, delete anything, or trigger financial transactions.
From the tool's definition Tool is named 'score_stability' and described as scoring protein stability using ESM2 pseudo-log-likelihood.
Documented attack patterns abuse exactly the kind of access score_stability gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Protein Design, and nothing reaches the server without passing your rules. This is the rule we recommend for score_stability:
{
"version": "1",
"default": "deny",
"tools": {
"score_stability": {}
}
}score_stability 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.
Score protein stability using ESM2 pseudo-log-likelihood. It is categorised as a Read tool in the Protein Design MCP Server, which means it retrieves data without modifying state.
Register the Protein Design MCP server in PolicyLayer and add a rule for score_stability: 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 Protein Design. Nothing to install.
score_stability 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 score_stability 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 score_stability. 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.
score_stability is provided by the Protein Design MCP server (jasonkim8652/protein-design-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Protein Design, 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.
19 Protein Design tools catalogued and risk-classified — across an index of 43,000+ MCP servers.