keyword
AI agents call keyword 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 naming convention and sibling tools that are all Read operations (search, get, taxonomy_search), 'keyword' almost certainly retrieves or queries protein data without side effects. The empty description introduces some uncertainty, but the context strongly suggests a read-only search function. Classified as Read with low severity since it merely queries a public knowledge base.
From the tool's definition Tool named 'keyword' with empty description; context from sibling tools (search, get, proteomes_search, taxonomy_search) and server purpose (knowledge base access) indicates this performs keyword-based search/retrieval of UniProt data.
Attacks that exploit this kind of access
keyword. 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 keyword: 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.
keyword 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 keyword 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 keyword. 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.
keyword 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 →