Trefle MCP for AI. Access 1 Million+ Plant Records and Distributions
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Trefle connects your AI client to a massive botanical database containing over 1 million plant entries. Use Trefle tools to search for specific plants or species, trace taxonomic hierarchies (genera and sub-taxa), and check detailed geographic distribution data.
It’s the deep dive you need when manual database queries aren't cutting it.
What AI agents can do with Trefle Automation
Get distribution plants
Filters a list of plants based on their recorded establishment status (e.g., native) within a specified distribution zone.
Get genus
Retrieves detailed information for one specific genus using its identifier.
Get plant
Gets the full scientific profile and metadata for a single plant species.
Runs get_plant to fetch complete scientific data on a single, known plant.
Uses search_species to query all species and sub-taxa based on keywords or criteria.
Calls list_genera to retrieve a complete list of plant genera for browsing taxonomy.
Runs list_distributions to generate an inventory of all recognized global distribution zones.
Uses get_distribution_plants to list plants found within a specific, defined geographic zone (and filter by status like 'native').
Ask an AI about this
Waiting for input…
What AI agents can do with Trefle: 12 Tools for Plant Data Cataloging
These tools allow your AI agent to perform every function needed to query, categorize, and verify data across millions of plant species.
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 Trefle on VinkiusGet Distribution Plants
Filters a list of plants based on their recorded establishment status (e.g., native) within a specified distribution zone.
Get Genus
Retrieves detailed information for one specific genus using its identifier.
Get Plant
Gets the full scientific profile and metadata for a single plant species.
Get Species
Retrieves complete details on one specific species, including its taxonomy and notes.
List Distributions
Returns a comprehensive list of all known global distribution zones available in the...
List Genera
Lists every genus currently cataloged in the botanical database.
List Plants
Provides a list of all main plant species, excluding varieties or subspecies forms.
List Species
Lists every recorded species and sub-taxa available in the database for browsing.
Report Species Error
Allows users to submit a report detailing an inaccuracy found in existing species...
Search Plants
Performs keyword searches across all main plant species records.
Search Species
Searches for specific species or sub-taxa using natural language queries.
Submit Species Correction
Submits a structured data correction when an error is found in recorded species information.
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.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Trefle integration is available immediately — no restart needed.
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 Trefle, 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 Trefle. 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 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Checking species taxonomy shouldn't require jumping between four different databases., Solved with Vinkius AI Gateway
Right now, checking a plant involves opening one database for genus names, another for sub-taxa, and a third just to confirm the current distribution zone. You copy the name here, jump over there, cross-reference the ID, and hope everything matches up.
With Trefle, your agent handles that whole process in a single call. Give it the plant's common name, and it uses `search_plants` to pull taxonomy from all sources, giving you one clean report on the spot.
Using Trefle with get_distribution_plants: Knowing where plants actually grow.
Without this tool, figuring out if a species is native to your county requires manual comparison against regional biodiversity reports. You're cross-referencing lists that aren't always current or complete.
Now, you ask for it. The agent runs `get_distribution_plants` and tells you immediately what plants are established in that zone, along with their status (native, introduced, etc.). Period.
What your AI can actually do with this
Trefle connects your AI client directly into a massive botanical database, giving you hands-on control over over a million plant entries. You're looking for more than just surface-level data; you need the deep dive when standard queries fall short. This server lets you search specific species and genera, trace complex taxonomy, and map detailed geographic distribution patterns using twelve dedicated tools.
Finding Plants and Species Data
You can start by running search_species to query all recorded species and sub-taxa using natural language—you just tell it what you're looking for. If you need a broader search across the main plant group, use search_plants instead; this performs keyword searches against all primary plant records. For comprehensive browsing, you can pull a full list of every known species or sub-taxa by calling list_species, while list_plants gives you an inventory of only the main plant species, filtering out varieties and subspecies forms.
Retrieving Scientific Profiles
When you pinpoint what you need, Trefle lets you pull full scientific profiles. To get all the metadata for a single, known plant species, run get_species to fetch its complete details, including its taxonomy notes. If you know the specific identifier of a plant, use get_plant to retrieve its full scientific profile and associated data.
For deeper taxonomic context, calling get_genus pulls detailed information for one specific genus using just its identifier.
Mapping Taxonomy and Structure
To map out the entire botanical kingdom’s structure, you can pull a complete list of all cataloged plant genera by invoking list_genera. If you need to know what global distribution zones exist in the database at all, run list_distributions to generate that full inventory. Once you have a zone listed, you use get_distribution_plants to filter records and see which plants were established there, letting you specifically filter by status—like finding only 'native' species within that defined area.
Handling Data Corrections
The database isn't perfect. If you find something wrong with the recorded data, Trefle gives you tools to fix it. You can submit a structured correction when an error exists in species information using submit_species_correction. For general reporting on inaccuracies that need review, use report_species_error to detail the problem found within existing records.
How It Works In Practice
You're not just viewing data; you're running complex queries. You can first determine all available global distribution zones with list_distributions. Then, if you want to know what species are native only to a specific zone, you use get_distribution_plants and filter by status. If your research requires tracing the family structure back up through the taxonomy, you'll start by calling list_genera, narrow down your focus with get_genus, and then pull the final details on an individual species using get_species.
The sheer depth of this data means you never have to guess where to look; you just tell Trefle what criteria you need it to check.
019e5d62-2e37-72b7-b0b1-dc1c0debd643 
Here's how it actually works
The bottom line is: It lets your AI client run complex botanical database queries using natural language prompts.
First, you subscribe to the server and provide your Trefle API token.
Next, you tell your AI client which specific data point you need (e.g., 'What plants are native to zone X?').
The agent runs the appropriate tool (get_distribution_plants), pulls the structured data, and gives you the list of species.
Who is this actually for?
Botanists who need to confirm taxonomy quickly. Researchers tracking biodiversity across regions. Developers building apps that require accurate, structured plant data. If you spend time manually cross-referencing species against global maps, this is for you.
Uses get_species and list_genera to verify taxonomy and build comprehensive family trees.
Integrates plant data into custom applications, using tools like search_plants for structured retrieval.
Checks native status and distribution using get_distribution_plants to inform conservation efforts.
What Changes When You Connect
Find exact data fast. Instead of digging through multiple tabs, you ask your agent to run get_plant using the slug, and you get the full scientific profile immediately.
Map global biodiversity. Use list_distributions to see every zone, then use get_distribution_plants to filter that list down to only native species in a target area.
Understand taxonomy depth. You can start broad by calling list_genera, and if you need more detail later, drill down using get_genus for the specific family structure.
Handle dirty data. If you spot an error—say, the wrong year of discovery—you don't have to email a database admin; you run report_species_error or submit_species_correction directly through your agent.
Search efficiently. Use search_plants for general keywords across main species, or use search_species when you know the sub-taxa but aren't sure of the exact name.
See it in action
Verifying Native Flora
A conservation scientist needs to check if a plant is native to the Mediterranean basin. They run list_distributions to identify the correct zone, then they use get_distribution_plants and filter by 'native' establishment status. The agent returns a clean list of only local species.
Deep Taxonomic Dive
A student is researching orchids. They first run list_genera to see related groups, then they use get_genus on a promising candidate. Finally, they call search_species to pull all known sub-taxa under that genus for their paper.
Data Cleanup and Correction
A developer notices the date for 'Rosa canina' is wrong in a legacy system. Instead of manually patching it, they use submit_species_correction to formally submit the accurate data point directly from their AI client.
Identifying Unknown Species
A field biologist captures photos and knows the plant is in the Rosaceae family. They run search_plants with keywords like 'rose' or 'Rosaceae'. The agent surfaces potential matches, which they can then investigate further using get_plant.
The honest tradeoffs
Over-relying on general searches
Asking the agent, 'Tell me about plants.' This is too vague and forces the tool to guess which data set you need (genera? species?).
Be specific. If you want genera, ask the agent to run list_genera. If you know the name, use search_plants or provide a slug to get_plant.
Treating data correction as chat
Telling the agent in conversation: 'Hey, that species date looks wrong.' The agent can't act on this vague request.
You must use a structured tool. Call submit_species_correction and provide all necessary fields for the correction.
Ignoring distribution zones
Just searching 'Oak tree' without context. This might pull up data from every continent.
First, run list_distributions to pick your zone. Then use get_distribution_plants with the filter set for that specific zone.
When It Fits, When It Doesn't
Use Trefle if you need structured, verifiable biological data—specifically taxonomy, species records, or geographic distribution. You must run a tool call; chat is not enough. Use list_genera when your scope is broad (e.g., 'show me all major plant groups'). Use get_plant when you know the exact slug of what you want (high confidence). Don't use Trefle if you are doing general conceptual research or need to analyze co-occurrence data that isn't mapped via established distribution zones; for those, a dedicated ecological modeling tool would be better. If your goal is merely browsing, start with list_species; if it’s querying, go straight to the specific getter functions.
Questions you might have
How do I find all the plant genera available? Using list_genera? +
Run list_genera. This tool returns a comprehensive index of every genus in the database. It's the best place to start if you don't know which specific group you need.
What is the difference between search_plants and list_plants? +
list_plants gives a simple index of all main species, while search_plants lets you use keywords to filter that index. Use the latter if you have partial information.
Can I check the native status for a plant? Using get_distribution_plants? +
Yes. You must first run list_distributions to define your zone, then use get_distribution_plants. Make sure you include the filter criteria (e.g., {"filter[establishment]": "native"}).
How do I submit a data correction? Using submit_species_correction? +
You must use submit_species_correction. This requires structured input—you'll need to provide the species ID, the field name, and the corrected value for it to work.
How do I authenticate or connect before running a command like `get_plant`? +
You must subscribe to the server and enter your Trefle API Token into your AI client. This token authorizes your agent, allowing it to access the botanical database and execute tools like get_plant.
If I spot incorrect data for a species, which tool should I use? Is it `report_species_error`? +
Yes, use report_species_error. This tool lets you submit structured reports directly about the faulty data. You provide details on what's wrong and where to find the error.
Before filtering plants by location using `get_distribution_plants`, how do I see all possible distribution zones? +
Run list_distributions. This tool pulls a complete list of every recognized WGSRPD zone. You can then use these specific zone names to filter your searches later.
What kind of detailed scientific data does the tool give me when I run `get_species`? +
The tool returns a full profile, not just basic identification. Expect metadata like the family name, the year it was first described, and other key botanical slugs.
Can I search for plants using a simple text query? +
Yes, use the search_plants tool. It allows you to find main plant species by providing a query string like 'rose' or 'oak'.
How can I filter plants by a specific family, like Orchidaceae? +
You can use the list_plants tool and provide a JSON string in the query_params field, such as {"filter[family_name]": "Orchidaceae"}.
Is it possible to get info on sub-species and varieties? +
Absolutely. While list_plants focuses on main species, the list_species and search_species tools include all sub-taxa, varieties, and hybrids.
We've already built the connector for Trefle. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting.
You're up and running in seconds.
Gemini 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.