Resolve the AlphaFoldDB cross-reference for a UniProt entry — typically
AI agents use uniprot_resolve_alphafold to create or update resources in Pypi:uniprot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pypi:uniprot environment.
An AI agent can call uniprot_resolve_alphafold faster than any human can review — one bad instruction and it creates or modifies resources in Pypi:uniprot by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Resolve the AlphaFoldDB cross-reference for a UniProt entry — typically. It is categorised as a Write tool in the Pypi:uniprot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pypi:uniprot MCP server in PolicyLayer and add a rule for uniprot_resolve_alphafold: 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 Pypi:uniprot. Nothing to install.
uniprot_resolve_alphafold is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the uniprot_resolve_alphafold 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 uniprot_resolve_alphafold. 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.
uniprot_resolve_alphafold is provided by the Pypi:uniprot MCP server (pypi:uniprot-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.