Design amino acid sequences for a protein backbone using ProteinMPNN.
AI agents invoke design_sequence 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 computational process (ProteinMPNN neural network) to generate/design amino acid sequences. It executes an external computational tool and produces new sequence outputs. It is not merely reading existing data, nor is it destructive or financial. The blast radius is medium — misuse could generate unintended protein sequences, but it does not directly destroy data or move money.
From the tool's definition Design amino acid sequences for a protein backbone using ProteinMPNN
Documented attack patterns abuse exactly the kind of access design_sequence 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_sequence:
{
"version": "1",
"default": "deny",
"tools": {
"design_sequence": {
"limits": [
{
"counter": "design_sequence_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}design_sequence 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.
Design amino acid sequences for a protein backbone using ProteinMPNN. 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_sequence: 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_sequence 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_sequence 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_sequence. 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_sequence 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.