uniprot_summary
AI agents call uniprot_summary to retrieve information from Mcp Alphafold without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries protein annotation data from UniProt without side effects. It is a read-only operation that fetches existing data. The empty description slightly reduces confidence, but the name and server context strongly indicate a data retrieval function consistent with the Read category.
From the tool's definition Tool name 'uniprot_summary' and server description indicate retrieval of UniProt protein annotations and summaries. No modification, deletion, execution, or financial operations implied.
Attacks that exploit this kind of access
uniprot_summary. It is categorised as a Read tool in the Mcp Alphafold MCP Server, which means it retrieves data without modifying state.
Register the Mcp Alphafold MCP server in PolicyLayer and add a rule for uniprot_summary: 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 Mcp Alphafold. Nothing to install.
uniprot_summary 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 uniprot_summary 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_summary. 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_summary is provided by the Mcp Alphafold MCP server (zeinab-sheikhi/mcp-alphafold). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →