Xeno-canto MCP for AI. Query 800k+ global wildlife audio records.
Works with every AI agent you already use
…and any MCP-compatible client








How this MCP server connects to your AI agent
Search recordings with the search_recordings tool. Connect directly to the world’s largest open database of bird sounds, giving your agent access to over 800,000 global wildlife audio recordings.
Filter results by species, country, genus, or quality grade for bioacoustics research and identification.
What AI agents can do with Xeno-canto Automation
Search recordings
Searches the Xeno-canto database to find specific bird sound recordings using filters like genus, species, or location.
Search for recordings using filters like genus or species name to pinpoint exact bird vocalizations.
Restrict searches based on the country, location, or date of recording to narrow down global datasets.
Query results specifically for certain sound types (song vs. call) or filter by recorded audio clarity/grade.
Navigate through thousands of records using built-in pagination support without losing track of your search progress.
Ask an AI about this
Waiting for input…
What AI agents can do with Xeno-canto: Explore Audio Search (1 Tool)
Use this single tool to query massive global databases of wildlife sound recordings, allowing you to filter results by specific criteria like genus and location.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Xeno-canto on VinkiusSearch Recordings
Searches the Xeno-canto database to find specific bird sound recordings using filters like genus, species, or location.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Xeno-canto, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Xeno-canto. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 1 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Sifting through global wildlife audio recordings is a nightmare of tabs and spreadsheets., Solved with Vinkius AI Gateway
Right now, finding specific bioacoustic data means opening multiple databases or running complex filters across dozens of pages. You're manually cross-referencing country names with species lists, copying metadata from one tab into another, all just to build a manageable research sample.
With this MCP, you simply ask your agent for the recordings—for example, 'Give me high-quality songs of *Turdus* in France.' You get structured results instantly, complete with location and date data. It's a massive time saver.
The search_recordings MCP delivers precise, filtered bioacoustic datasets.
You eliminate the manual steps of geographic filtering, quality grading, and type classification. Your agent handles all that complex logic internally using the search_recordings tool.
What's different now is control. You don't just get a list; you get a structured data flow that lets you analyze patterns across continents without ever leaving your chat window.
What your AI can actually do with this
This MCP gives your AI client direct access to the Xeno-canto database, a massive collection of bird sounds from around the globe. Instead of manually navigating complex websites, your agent can query this data using natural language or advanced filters. You can search across every continent for specific species, retrieve metadata like recording date and location, or narrow down results by quality grade.
This is crucial for ornithologists and researchers who need to analyze large bioacoustic datasets quickly.
The power comes from combining searches; you might run one query for the genus Turdus in France, then another query for a specific call type, all through your agent. Because every tool call runs inside Vinkius's secure environment, you get full visibility into what data flowed and how many tokens were used by checking the AI Analytics dashboard—nothing happens in the dark.
019e5d68-0393-7005-82ec-46cc6b00f280 Here's how it actually works
The bottom line is you get structured access to millions of audio data points without touching a web browser or API key.
Ask your agent to perform a bioacoustic query, specifying parameters like species name and country.
The MCP executes the request, querying the massive Xeno-canto dataset against those filters.
You receive paginated results containing recordings, metadata (location, date), and classification details.
Who is this actually for?
Ornithologists, bioacoustics researchers, and environmental data scientists use this. They need to analyze massive amounts of global wildlife recordings fast, eliminating hours spent on manual database queries.
Collects large datasets of audio metadata for machine learning models or comparative species analysis.
Gathers specific, high-quality sound recordings from defined geographic regions to support identification projects.
Presents and retrieves diverse examples of bird songs and calls for educational programs globally.
What Changes When You Connect
Pinpoint species vocalizations: Use search_recordings to filter recordings by specific genus, ensuring you only get the data relevant to your research.
Global coverage in one query: Access sound data from every continent and thousands of subspecies without geographic limitations. This is key for comparative studies.
Deep metadata retrieval: Get more than just audio files; retrieve critical details like location, date, recordist, and specific sound type (call vs. song) immediately.
Efficient large-scale analysis: The built-in pagination support means you can process massive result sets page by page without running into data limits.
Targeted research filtering: Limit your search to only 'A' quality grade recordings or specific sound types, cutting through noise and focusing on usable audio.
See it in action
Comparing subspecies calls
An ornithologist needs to compare the vocalizations of two closely related bird species across three different continents. They use their agent to repeatedly run search_recordings, filtering by both species name and country/continent, building a comparative dataset rapidly.
Verifying historical recordings
A researcher is checking data from 1950s expeditions. They use the MCP to query search_recordings, applying date filters and specific location metadata to ensure only historically accurate files are retrieved for a paper.
Identifying unknown calls
A nature enthusiast records an unknown bird call in their backyard. They feed the agent details about the potential region and use search_recordings, refining filters by genus until they find a match with high certainty.
The honest tradeoffs
Searching only by species name
Asking for 'Blackbird recordings' will give you thousands of results from every country, forcing manual filtering just to check the UK data.
Use search_recordings and specify both the species and the desired country (e.g., 'Turdus merula in England') to immediately narrow down your scope.
Assuming all metadata is available
Thinking that just because a recording exists, its precise location and sound type are always fully tagged.
Always verify the returned metadata fields. Use search_recordings to confirm if you can filter by specific attributes like 'song' or 'call' in addition to species.
Ignoring pagination limits
Running a wide search and expecting all 10,000 results to return in one go, causing the agent to fail halfway through.
Use the built-in page management capabilities. Process the data in manageable chunks by requesting the next set of records after each successful call.
When It Fits, When It Doesn't
You use this MCP if your job requires analyzing large, diverse datasets of bioacoustic recordings from multiple global locations. If you just need to look up one sound or verify a single species, standard web search is fine. But if you're doing comparative research—say, comparing the quality grade 'A' songs of the same genus across five different countries—you need this MCP. Don't use it if your only goal is general background knowledge; you need structured data retrieval. Always remember that running multiple searches via this MCP allows you to build complex automations that span datasets and locations using a single AI agent.
Questions you might have
How can I find recordings of a specific bird species? +
Use the search_recordings tool with the species name or scientific name (e.g., 'Common Blackbird' or 'Turdus merula'). You can combine this with other filters like country or quality.
Can I filter results by recording quality or location? +
Yes! The search_recordings tool supports Xeno-canto syntax. Use cnt:france for location or q:A for the highest quality recordings within your query string.
Is there a limit to the number of results I can retrieve? +
The search_recordings tool returns results in pages. You can use the page parameter to navigate through the database, with each page containing up to 500 recordings.
What is the setup process for using the `search_recordings` tool? +
You don't need to worry about credentials. Because this MCP accesses the public Xeno-canto database, no API key or special authentication is needed to run search_recordings. Just connect your agent and start querying.
Beyond the audio file, what metadata does `search_recordings` retrieve? +
The tool returns detailed metadata for every match. You get location data, the recording date, who recorded it (the recordist), and even whether the sound is classified as a song or a call.
How can I use advanced query syntax with `search_recordings`? +
You can absolutely use complex filters. The tool accepts queries specifying criteria like genus, country, and quality grade (e.g., 'gen:Turdus cnt:france q:A'). This lets you narrow down results dramatically.
If my query using `search_recordings` returns nothing, what should I do? +
It won't throw an error; it will simply return an empty set. If that happens, try widening your search parameters or simplifying the filters you passed to the tool.
Does `search_recordings` handle massive datasets and pagination? +
Yes, it's built for large scale data. The MCP includes native page management support, letting you navigate through huge result sets without hitting artificial limits.
We've already built the connector for Xeno-canto. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 1 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.