AI agents call bio.species 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 is a straightforward read-only taxonomy lookup service. It queries an external knowledge base (GBIF) and returns structured information about organisms. No data is written, modified, deleted, or financial transactions triggered. The pay-per-call model affects billing, not the nature of the tool itself.
From the tool's definition Tool retrieves taxonomic data from GBIF backbone: 'accepted name, full lineage, vernacular names, global occurrence count, GBIF link.' Described action is 'Resolve' and 'Fuzzy-matches' — pure data lookup with no modification, creation, deletion, or external…
Attacks that exploit this kind of access
Resolve any organism (scientific or common name) to the GBIF taxonomic backbone: accepted name, full lineage (kingdom→species), vernacular names, global occurrence count, GBIF link. Fuzzy-matches misspellings. 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.species: 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.species 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.species 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.species. 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.species 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 →