Search for proteins in the UniProt database.
AI agents call search_uniprot to retrieve information from UniProt MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches or queries protein data from a public database with no capability to create, modify, delete, or execute code. It is a standard read operation with minimal security risk, even if an AI agent misuses it by crafting unusual search queries—the worst outcome is unwanted data retrieval from a public source.
From the tool's definition Tool name and description indicate searching/querying: 'Search for proteins in the UniProt database.' This retrieves protein information without modification or side effects.
Attacks that exploit this kind of access
Search for proteins in the UniProt database. It is categorised as a Read tool in the UniProt MCP Server MCP Server, which means it retrieves data without modifying state.
Register the UniProt MCP Server MCP server in PolicyLayer and add a rule for search_uniprot: 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 UniProt MCP Server. Nothing to install.
search_uniprot 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 search_uniprot 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 search_uniprot. 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.
search_uniprot is provided by the UniProt MCP Server MCP server (vitamin3615/uniprot-mcp-server). 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 →