taxonomy_search
AI agents call taxonomy_search to retrieve information from Mcp Uniprot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server's stated purpose (retrieval from a knowledge base), the naming pattern (taxonomy_search suggests querying taxonomy data), and the sibling tools all being read/search operations, this tool appears to retrieve or query taxonomic information about proteins without side effects. The empty tool description prevents higher confidence, but the context strongly suggests a read operation.
From the tool's definition Tool name is 'taxonomy_search'; sibling tools include 'search', 'get', 'proteomes_search', and 'keyword', all read-only retrieval operations. Server description emphasizes 'search and retrieval' of protein data without modification capabilities.
Attacks that exploit this kind of access
taxonomy_search. It is categorised as a Read tool in the Mcp Uniprot MCP Server, which means it retrieves data without modifying state.
Register the Mcp Uniprot MCP server in PolicyLayer and add a rule for taxonomy_search: 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 Uniprot. Nothing to install.
taxonomy_search 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 taxonomy_search 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 taxonomy_search. 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.
taxonomy_search is provided by the Mcp Uniprot MCP server (pipeworx-io/mcp-uniprot). 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 →