Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-trefle search for sunflower species"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Trefle MCP — global plant database (1M+ species)
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
Tool | Description |
| Full plant record by Trefle ID. Returns scientific/common names, family, status, image, year, main species. |
| Search species (the rank below plants — some plants have multiple species). Returns Trefle species ID + scientific name. |
Related MCP server: Aurora-MCP
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"trefle": {
"url": "https://gateway.pipeworx.io/trefle/mcp"
}
}
}Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Trefle data" })The gateway picks the right tool and fills the arguments automatically.
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search GBIF species taxonomy, occurrence records, datasets, and publishers.
Search GBIF species taxonomy, occurrence records, datasets, and publishers.
iNaturalist MCP — citizen-science species observations (free, no auth for read-only)
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pipeworx-io/mcp-trefle'
If you have feedback or need assistance with the MCP directory API, please join our Discord server