Get a summary count of Xeno-canto recordings for a species broken down by quality grade (A=best through E=worst). Use this ONLY after you have already presented a species list to the user and they have confirmed they want recording gap data. Do not call this speculatively. Returns total count and...
AI agents call get_recording_counts 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.
This tool queries the Xeno-canto API to fetch and aggregate recording metadata. It performs a read-only retrieval of existing data (recording counts by quality grade) and presents it for user analysis. There is no creation, modification, deletion, code execution, or financial impact.
From the tool's definition Tool returns a 'summary count' and 'per-grade breakdown' of existing recordings with no modification capability. Explicitly described as retrieving data to 'identify which species... would most benefit' — a query/analysis function with no side effects.
Attacks that exploit this kind of access
Get a summary count of Xeno-canto recordings for a species broken down by quality grade (A=best through E=worst). Use this ONLY after you have already presented a species list to the user and they have confirmed they want recording gap data. Do not call this speculatively. Returns total count and per-grade breakdown. Ideal for identifying which species in a list are underrepresented and would most benefit from new recordings. 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 get_recording_counts: 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.
get_recording_counts 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 get_recording_counts 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 get_recording_counts. 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.
get_recording_counts 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 →