End-to-end de novo fold design pipeline: RFdiffusion (unconditional backbone) →
AI agents invoke design_fold to trigger actions in Protein Design. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a multi-step computational pipeline (RFdiffusion followed by additional steps implied by the truncated description) that executes complex protein design algorithms. It triggers external computational operations whose effects depend on input arguments, classifying it as Execute.
From the tool's definition End-to-end de novo fold design pipeline: RFdiffusion (unconditional backbone) →
Documented attack patterns abuse exactly the kind of access design_fold 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 design_fold:
{
"version": "1",
"default": "deny",
"tools": {
"design_fold": {
"limits": [
{
"counter": "design_fold_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}design_fold stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
End-to-end de novo fold design pipeline: RFdiffusion (unconditional backbone) →. It is categorised as a Execute tool in the Protein Design MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Protein Design MCP server in PolicyLayer and add a rule for design_fold: 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.
design_fold is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the design_fold 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 design_fold. 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.
design_fold 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.