Macaulay Library MCP. Query millions of wildlife records by species and region.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Macaulay Library MCP Server connects your AI client directly to Cornell Lab of Ornithology's scientific media database. You can search millions of photos, audio recordings, and videos by species, location, or contributor.
It retrieves deep metadata for specific assets using ML Catalog Numbers, tracks the latest global wildlife uploads, and filters massive datasets for ornithological research.
What your AI agents can do
Get asset
Retrieves all scientific and technical metadata for one specific media asset using its ML Catalog Number.
Get recent media
Fetches the most recently uploaded wildlife content, optionally filtered by a country or region code.
Search media
Searches the library for assets based on criteria like species name, location, contributor, or media type.
You specify criteria—like a species name or region—and the server returns relevant photo, audio, or video assets.
By providing a unique ML Catalog Number, you get all the scientific and technical data associated with that single piece of media.
The server fetches the most recently uploaded wildlife content, allowing you to monitor global or regional activity feeds.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Macaulay Library: 3 Tools for Scientific Media Retrieval
These three tools let your AI client search vast archives, pull specific assets, and track the latest global wildlife uploads.
019e5d32get asset
Retrieves all scientific and technical metadata for one specific media asset using its ML Catalog Number.
019e5d32get recent media
Fetches the most recently uploaded wildlife content, optionally filtered by a country or region code.
019e5d32search media
Searches the library for assets based on criteria like species name, location, contributor, or media type.
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 Macaulay Library, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Macaulay Library MCP Server connects your AI client straight into Cornell Lab of Ornithology's massive scientific media archive. You're looking at millions of photos, audio recordings, and videos covering global wildlife—from birds to other creatures. This isn't just a search index; it's deep, structured scientific data that lets you do some serious research work with your agent.
Searching the Archive: search_media
Need to pull assets based on specific criteria? You tell the server what you need—it handles the filtering. You can search across species names (using taxon codes), pinpoint locations, track a particular contributor, or filter by media type like photo, audio, or video. If your project requires tracking all footage of one bird family from South America over the last decade, this tool is how you pull that massive dataset together.
Getting Deep Details: get_asset
When you find an asset—a perfect recording or a crucial photo—you don't just want to know it exists; you need all its technical and scientific background. By providing the unique ML Catalog Number, this tool retrieves every piece of metadata attached to that single media file. You get deep details on how it was captured, what taxonomists analyzed it, and any specific technical measurements associated with it.
It’s your way to verifying the provenance and context for critical research assets.
Tracking Global Changes: get_recent_media
Monitoring global wildlife activity is a whole other ballgame. This tool lets you pull the absolute newest content that's been uploaded into the archive. You can track this feed globally, or you can narrow it down to just one country or specific region code if your research is hyper-focused. You get real-time insight into what scientists are submitting right now, letting you monitor global or regional activity feeds as they happen.
How These Tools Work Together
Your AI client uses these tools to make sense of the sheer volume of data. If you're working on a project comparing migratory patterns, your agent might first use search_media to find all relevant videos from a specific region and species over a ten-year span. Then, for each promising video found that meets those criteria, it uses get_asset to pull the detailed scientific metadata—checking out everything from recording equipment specs to associated research notes.
If you suspect there's new data coming in on a particular coast, your agent can use get_recent_media, filtering by the appropriate country code, pulling the latest uploads for immediate review.
This setup lets you build complex query chains. You don't just get a list of files; you get structured, actionable intelligence about wildlife media. It’s built for serious ornithological research, giving your agent access to one of the most comprehensive scientific archives in the world. Don't settle for simple keyword searches—you're getting full-stack metadata retrieval across millions of assets.
How Macaulay Library MCP Works
- 1 Subscribe to the Macaulay Library MCP Server and input your eBird API Token.
- 2 Your AI client constructs a specific query (e.g., 'Show recent videos from Brazil').
- 3 The server executes the tool, querying millions of records and returning structured media data directly to your agent.
The bottom line is you get direct, programmatic access to scientific wildlife datasets without leaving your coding environment.
Who Is Macaulay Library MCP For?
Bioacousticians and academic researchers who need massive amounts of structured data. Think of the ornithologist staring at a pile of raw field notes, needing to cross-reference species codes with media assets from specific regions. This server gives them instant access to millions of validated records.
Needs to compare local sightings against global archives, using the search_media tool by location and species code.
Uses get_asset with a known ML Catalog Number to pull audio metadata for comparison in research models.
Needs a quick feed of the most current, high-quality footage, running get_recent_media filtered by geography.
What Changes When You Connect
- Find specific assets fast. Instead of browsing folders, you use
search_mediato filter by taxon code, location, or media type (photo/audio). - Verify data quality with deep metadata. The
get_assettool pulls scientific details for any given ML Catalog Number—you know exactly what you're using. - Stay current on field discoveries. Run
get_recent_mediato pull the latest uploads from specific countries, tracking global biodiversity changes in real-time. - Saves hours of manual data collection. The server handles complex filtering (species + location + type) that used to require multiple database queries.
- Supports scientific rigor. You can build pipelines that feed structured bioacoustics and image metadata directly into your analysis models.
Real-World Use Cases
Cross-referencing species vocalizations
A student needs to compare a new recording of the Saffron Toucanet. They use search_media with the species code, then run get_asset on several returned IDs to pull metadata, verifying capture location and date for comparison.
Tracking migratory patterns
A researcher suspects a bird's range expanded. They use get_recent_media, filtering by the suspected region code over the last six months. This gives them an immediate feed of new assets to analyze for shifts in biodiversity.
Building educational content
An educator needs high-quality photos and videos of local birds. They run search_media using the species name and limit results by a specific state code, gathering all vetted assets into one structured list.
Auditing media usage rights
A content creator has an asset ID (ML Catalog Number). They run get_asset to pull the full metadata sheet immediately. This confirms technical details, contributor info, and scientific context before publication.
The Tradeoffs
Asking for all bird photos
Prompting the agent with 'Get me pictures of birds.' The result is useless—too many assets, no structure, and unclear filtering parameters.
→
You must use search_media and specify at least a species taxon code or a location filter to narrow the results down. Don't rely on general searches.
Forgetting asset IDs
Trying to get details about an image using only descriptive text like 'the red bird photo from Florida.' The server can't guess the unique identifier.
→
Always use get_asset and provide the exact ML Catalog Number. That ID is the key to getting precise metadata.
Missing location context
Running a search for 'House Sparrow' without specifying a region code. You get global results, making it impossible to prove local relevance.
→
When searching, always include the desired geographic filter using search_media's parameters. This keeps your dataset geographically accurate.
When It Fits, When It Doesn't
Use this server if your work requires validated scientific data on flora or fauna, and you need to process millions of records by specific taxonomy codes or precise locations. If your goal is simple image retrieval (e.g., finding a random picture of a bird online), don't use this—it’s too detailed and academic. Only use it if you know what data point you are looking for: Is it the latest uploads? A specific ID? Or a search by defined criteria? If your question is 'Show me anything cool,' this isn't the tool. Use search_media to define the parameters first.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Macaulay Library. 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
Works with 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 server provides 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Sifting through scientific archives takes days of manual work.
Today, getting a comprehensive view of bird media means juggling multiple academic databases. You download zip files from one source for species data, then manually check another site for location context, and finally try to cross-reference everything in a spreadsheet. It's slow, error-prone, and you always miss something.
With the Macaulay Library MCP Server, your agent runs `search_media` across millions of records instantly. You specify 'Species X' and 'Region Y,' and it compiles all relevant assets—photos, audio, video—into one structured output. It saves you days of tedious API calling.
The Macaulay Library MCP Server: Get validated media insights.
Manual processes require you to track down the unique ML Catalog Number for every asset, then use a separate tool just to check its metadata. You're bottlenecked by retrieving one single piece of information at a time, slowing your research dramatically.
Now, you pass the ID to `get_asset` and instantly pull all associated data points—technical specs, recording details, scientific context—in one go. The process is immediate, reliable, and structured.
Common Questions About Macaulay Library MCP
How do I find media for a specific bird species using search_media? +
You use search_media and provide the species' taxon code as one of the required parameters. This is much more accurate than searching by common name alone.
What does get_asset need to run? +
It requires a single input: the ML Catalog Number. Once you have this unique ID, it pulls all available metadata for that specific piece of media.
Can I check new uploads from Brazil using get_recent_media? +
Yes. You pass 'BR' (or the region code) to get_recent_media. This filters the latest global feed down to just what was recently uploaded in that country.
Is search_media better than get_asset? +
search_media is for discovery—when you don't know the ID yet. get_asset is for verification and detail—when you already have the specific ML Catalog Number.
Before I run `search_media`, what kind of API token do I need to connect? +
You must use an eBird API Token. This token authenticates your request and grants your agent read access to the live Macaulay data feed, ensuring you can query all three tools successfully.
If I run `get_asset` with a Catalog Number that doesn't exist, what error should I expect? +
You will receive an HTTP 404 or similar 'Asset Not Found' status. This specific error means the ID is incorrect or the data was removed; it confirms your connection to the server works fine.
Can I use `search_media` to filter results by both species and a specific date range? +
Yes, you pass multiple filters into the search query. You specify the taxon code and provide start/end dates in the parameters, narrowing down the assets significantly for targeted research.
When I use `get_recent_media`, how do I get all results if there are thousands of uploads? +
The function supports pagination using a cursor or offset parameter. You must pass this identifier with subsequent calls to fetch the next chunk of media until the API returns an empty set.
Can I filter my media search to only show audio recordings for a specific species? +
Yes! Use the search_media tool and set the mediaType parameter to 'a' (audio) along with the taxonCode for the species you are interested in.
How do I find the most recent media uploads from a specific country like Canada? +
You can use the get_recent_media tool and provide the regionCode (e.g., 'CA' for Canada) to fetch the latest submissions from that area.
What information can I get if I have a specific ML Catalog Number? +
By using the get_asset tool with the mlCatalogNumber, you will receive detailed metadata including species identification, location, date, contributor details, and technical specifications of the media.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Docamatic
Generate professional PDFs from templates with dynamic data injection for invoices, reports, and custom documents at scale.
HeyGen
Create AI-generated videos with realistic digital avatars that speak in any language for training, marketing, and communication.
Luma AI (Generative Video & Creative)
Generate cinematic AI videos and images via Luma — use Dream Machine for text-to-video, image-to-video, and professional camera control.
You might also like
Freshdesk
Resolve customer tickets faster with omnichannel helpdesk tools, smart automation, and self-service portals your users will love.
Alchemer
Survey and feedback orchestration — manage surveys, responses, and reports via AI.
RandomDuck
Brighten your day with random duck images, GIFs, and HTTP status ducks for developers.