Retrieve an AlphaFold-predicted protein structure by UniProt accession. Returns confidence scores (pLDDT), predicted aligned error, and download links for PDB/mmCIF files.
AI agents call predict_structure 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 tool queries a pre-computed database of protein structure predictions and returns read-only data (structure files, metrics). There are no side effects, no code execution, no data modification, and no resource consumption beyond data transfer. The information retrieved is public scientific data from AlphaFold, making this a straightforward Read operation with low blast radius if misused.
From the tool's definition Tool retrieves AlphaFold-predicted protein structure and returns confidence scores and download links. Key verbs: 'Retrieve', 'Returns' — no modification, deletion, execution, or financial operations.
Documented attack patterns abuse exactly the kind of access predict_structure 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 predict_structure:
{
"version": "1",
"default": "deny",
"tools": {
"predict_structure": {}
}
}predict_structure 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.
Retrieve an AlphaFold-predicted protein structure by UniProt accession. Returns confidence scores (pLDDT), predicted aligned error, and download links for PDB/mmCIF files. 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 predict_structure: 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.
predict_structure 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 predict_structure 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 predict_structure. 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.
predict_structure 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.