feature_summary
AI agents call feature_summary 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.
This tool appears to retrieve summary information about protein features from UniProt. It has no side effects—it queries and returns data. Despite the empty description, the context (knowledge base server, retrieval-oriented siblings) and naming convention indicate a Read operation with low severity and blast radius.
From the tool's definition Tool name 'feature_summary' on a UniProt knowledge base server that provides 'search and retrieval' capabilities; sibling tools include 'get', 'search', and 'taxonomy_search', all retrieval operations.
Attacks that exploit this kind of access
feature_summary. 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 feature_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 Uniprot. Nothing to install.
feature_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 feature_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 feature_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.
feature_summary 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 →