Append Xeno-canto recording counts and quality grades to an array of species. Call this ONLY after presenting a species list to the user AND receiving explicit confirmation that they want to see recording gap data. This tool makes one API call per species and can be slow for large lists — warn th...
AI agents call enrich_species_list to retrieve information from Birding Buddy MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
enrich_species_list performs a read-only enrichment operation that queries external APIs (Xeno-canto) to augment existing data with recording statistics and returns a reorganized view. No data is created, modified, deleted, or executed. The operation is deterministic, safe, and informational in nature. The only side effect is API rate consumption, which is a normal constraint of read operations.
From the tool's definition Tool description states it 'Append[s] Xeno-canto recording counts and quality grades' and 'Returns the input list sorted by fewest A-grade recordings first' — this is purely data retrieval and transformation with no modifications to underlying data.
Attacks that exploit this kind of access
Append Xeno-canto recording counts and quality grades to an array of species. Call this ONLY after presenting a species list to the user AND receiving explicit confirmation that they want to see recording gap data. This tool makes one API call per species and can be slow for large lists — warn the user if the list exceeds 20 species. For 50 species expect ~10 seconds. Returns the input list sorted by fewest A-grade recordings first, so the highest-priority recording targets appear at the top. It is categorised as a Read tool in the Birding Buddy MCP MCP Server, which means it retrieves data without modifying state.
Register the Birding Buddy MCP server in PolicyLayer and add a rule for enrich_species_list: 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 Birding Buddy MCP. Nothing to install.
enrich_species_list 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 enrich_species_list 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 enrich_species_list. 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.
enrich_species_list is provided by the Birding Buddy MCP server (woodcreeper/birding-buddy-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 →