AI agents call bio.gene to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns structured data about genes and proteins from public databases (NCBI, UniProt) based on symbol and organism parameters. It retrieves information only and does not create, modify, delete, execute code, or involve financial transactions. The data returned is read-only reference material from established biological databases.
From the tool's definition Tool performs 'Gene lookup' and returns 'NCBI Gene identity' and 'UniProt protein' information—purely retrieval of existing public biological reference data with 'no side effects' typical of read operations.
Attacks that exploit this kind of access
Gene lookup by symbol + organism (taxid, default 9606=human): NCBI Gene identity (description, chromosome, map location, aliases, RefSeq summary) joined with UniProt protein (accession, name, length, function). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for bio.gene: 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. Nothing to install.
bio.gene 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 bio.gene 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 bio.gene. 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.
bio.gene is provided by the MCP server (@2sio/mcp). 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 →