mcpField
P
Plantnet Mcp

Plantnet Mcp

Local
github.com/OrHavraPerryScience & Education0Updated 35w ago

About Plantnet Mcp

An MCP server that connects Claude to the Pl@ntNet API for identifying plants from photos. It returns ranked species matches and taxonomic details, with tools for regional flora projects and usage quotas.

Key features

  1. 01Identify plants from 1–5 image URLs
  2. 02Return ranked matches and confidence scores
  3. 03Include scientific and common names
  4. 04Select regional flora databases
  5. 05Check daily API usage

Use cases

  1. 01Identify a plant from leaf or flower photos
  2. 02Search against a region-specific flora database
  3. 03Check remaining daily identification quota

MCP support

Exposes plant identification, available flora project listing, and API quota checking as tools for MCP clients. Identification results include ranked species matches and taxonomic data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

plantnet-mcp

An MCP server for the Pl@ntNet plant identification API — identify plants from photos directly within Claude.

MCP TypeScript License: MIT


Overview

plantnet-mcp connects Claude to the Pl@ntNet API, enabling plant identification from images with scientific accuracy. Submit 1–5 photos of a plant and get back ranked species matches with confidence scores, taxonomic data, and regional flora support.

Tools Provided
ToolDescription
identify_plantIdentify a plant from 1–5 image URLs. Returns ranked species matches with confidence scores, scientific/common names, and taxonomic data (genus, family, GBIF/POWO IDs).
list_projectsList available regional flora databases (e.g., world flora, Europe, Africa, Americas). Useful for targeting location-specific identification.
check_quotaCheck your daily API usage against your quota limit (500 identifications/day on the free tier).

Requirements


Installation

git clone https://github.com/OrHavraPerry/plantnet-mcp
cd plantnet-mcp
npm install
npm run build

Configuration

1. Set your API key

Copy .env.example to .env and add your key:

cp .env.example .env
PLANTNET_API_KEY=your_api_key_here
2. Add to Claude Desktop

Edit your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "plantnet": {
      "command": "node",
      "args": ["/absolute/path/to/plantnet-mcp/dist/index.js"],
      "env": {
        "PLANTNET_API_KEY": "your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop after saving.


Usage Examples

Identify a plant from a photo URL:

Identify this plant: https://example.com/plant.jpg

Multi-photo identification for better accuracy:

Identify this plant using these photos — leaf: [url1], flower: [url2]

Region-specific search:

List available plant projects, then identify this plant [url] using the Europe flora

Check API usage:

How many plant identifications do I have left today?

Tool Reference

identify_plant
ParameterTypeRequiredDescription
imagesstring[]Yes1–5 image URLs (JPG or PNG)
organsstring[]NoPlant organ per image: leaf, flower, fruit, bark, habit, auto, other
projectstringNoFlora database to search (default: all)
langstringNoLanguage for common names (default: en)
nb_resultsnumberNoNumber of results to return, 1–25 (default: 5)
list_projects

No parameters. Returns all available regional flora databases.

check_quota

No parameters. Returns current daily usage and limit.


Limits

  • Free tier: 500 identifications/day per API key
  • Max images per request: 5
  • Supported formats: JPG, PNG

Development

npm run dev      # Run with ts-node (no build needed)
npm run build    # Compile TypeScript to dist/
npm test         # Run test suite

License

MIT — see LICENSE

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.