OpenHerbarium MCP is designed for a downstream agent such as Hermes Agent Botaniste. It is deliberately a knowledge-access layer only: it fetches, normalizes and cites botanical evidence, then lets the client agent reason, write, format and publish.

What this MCP does

It exposes MCP tools for:

plant lookup by common or scientific name;
taxonomic information;
species information such as distribution, habitat and botanical descriptions;
horticultural care-source discovery;
image-source discovery with licence and author metadata;
targeted botanical source search through a local Firecrawl instance when configured.

Every returned data point is wrapped with provenance:

{
  "value": "Marantaceae",
  "source": "GBIF Backbone Taxonomy",
  "url": "https://www.gbif.org/species/8184122",
  "retrieved_at": "2026-08-02T12:00:00+00:00",
  "confidence": "high"
}

What this MCP does not do

OpenHerbarium MCP never:

creates final Markdown plant sheets;
writes to Outline;
manages Outline collections;
creates care calendars;
decides final horticultural recommendations;
replaces the reasoning/presentation layer of Hermes Agent.

MCP tools

`search_plant(name: str)`

Returns:

accepted scientific name;
canonical name;
common/vernacular names when available;
synonyms;
family, genus, species and rank;
external identifiers such as GBIF keys and GBIF species URL;
best-effort Kew/POWO results when accessible.

`get_taxonomy(name: str)`

Returns sourced taxonomy:

kingdom;
phylum/class/order when available;
family;
genus;
species;
scientific name;
botanical authorship;
taxonomic status;
synonyms.

Priority sources:

GBIF Backbone Taxonomy;
Plants of the World Online, Kew, best-effort.

`get_species_information(name: str)`

Returns raw evidence for:

botanical descriptions;
known distribution;
natural habitat where available;
additional source-search records when Firecrawl is configured.

`get_care_sources(name: str)`

Returns raw source candidates for:

light;
temperature;
humidity;
watering;
substrate;
fertilisation;
repotting.

It does not transform those sources into final care advice.

`get_image_sources(name: str, limit: int = 10)`

Uses Wikimedia Commons to return:

image URL;
licence;
author;
source page.

`search_botanical_sources(query: str, limit: int = 5)`

Uses a local Firecrawl instance if FIRECRAWL_API_URL is configured. If not configured, the tool returns source-constrained suggested queries rather than pretending to have scraped content.

Sources

Implemented/targeted sources:

GBIF
Plants of the World Online, Kew best-effort connector
Wikimedia Commons
Royal Horticultural Society source candidates / Firecrawl search
Tela Botanica source candidates / Firecrawl search
public university horticultural resources via targeted Firecrawl search

No paid API is required.

Installation

Requirements

Python 3.11+
uv recommended, or any Python package installer capable of creating a virtual environment

Simplest install: run directly with `uvx`

You do not need to clone the repository manually. Hermes can let uvx install and run the MCP server directly from Gitea:

mcp_servers:
  openherbarium:
    command: "uvx"
    args:
      - "--from"
      - "git+https://git.home-deneuville.fr/Edern/openherbarium-mcp.git"
      - "openherbarium-mcp"
    timeout: 120
    connect_timeout: 60
    env:
      FIRECRAWL_API_URL: "http://localhost:3002"
      FIRECRAWL_API_KEY: ""
      BOTANICAL_ALLOWED_DOMAINS: "gbif.org,powo.science.kew.org,missouribotanicalgarden.org,tela-botanica.org,inpn.mnhn.fr,rhs.org.uk,edu,wikimedia.org,wikipedia.org"
      OPENHERBARIUM_TIMEOUT: "20"

Restart Hermes Agent after editing ~/.hermes/config.yaml.

An equivalent ready-to-copy snippet is available at examples/hermes-openherbarium-uvx.yaml.

JSON setup examples

Some MCP clients use a JSON config file instead of YAML. Ready-to-copy JSON examples are provided in examples/:

Client / use case	Example file	Notes
Hermes-style JSON	`examples/hermes-mcp.json`	Same structure as Hermes `mcp_servers`, but JSON. Useful if you keep MCP snippets in a separate `mcp.json` before converting/merging into `config.yaml`.
Generic MCP clients	`examples/generic-mcp.json`	Uses the common `mcpServers` JSON key.
Claude Desktop / Claude Code-style configs	`examples/claude-desktop-mcp.json`	Copy the `openherbarium` entry under your existing `mcpServers`.
Cursor	`examples/cursor-mcp.json`	Copy into Cursor's MCP configuration when it expects `mcpServers`.
Windsurf	`examples/windsurf-mcp.json`	Copy into Windsurf's MCP configuration when it expects `mcpServers`.
Local development checkout	`examples/local-dev-mcp.json`	Uses `uv --directory /absolute/path/to/openherbarium-mcp run openherbarium-mcp`.

Hermes JSON-style snippet:

{
  "mcp_servers": {
    "openherbarium": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://git.home-deneuville.fr/Edern/openherbarium-mcp.git",
        "openherbarium-mcp"
      ],
      "timeout": 120,
      "connect_timeout": 60,
      "env": {
        "FIRECRAWL_API_URL": "http://localhost:3002",
        "FIRECRAWL_API_KEY": "",
        "BOTANICAL_ALLOWED_DOMAINS": "gbif.org,powo.science.kew.org,missouribotanicalgarden.org,tela-botanica.org,inpn.mnhn.fr,rhs.org.uk,edu,wikimedia.org,wikipedia.org",
        "OPENHERBARIUM_TIMEOUT": "20"
      }
    }
  }
}

Generic mcp.json snippet used by many MCP clients:

{
  "mcpServers": {
    "openherbarium": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://git.home-deneuville.fr/Edern/openherbarium-mcp.git",
        "openherbarium-mcp"
      ]
    }
  }
}

The MCP is configured through environment variables passed by the MCP client. This lets you change endpoints and timeouts directly in config.yaml, mcp.json or your client's MCP settings screen, without modifying the repository.

Available parameters:

Environment variable	Required	Default	Purpose
`FIRECRAWL_API_URL`	No	unset	Local Firecrawl base URL. Enables `search_botanical_sources` and richer source search in care/species tools.
`FIRECRAWL_API_KEY`	No	unset	Optional bearer token if your Firecrawl instance requires authentication.
`BOTANICAL_ALLOWED_DOMAINS`	No	built-in allow-list	Comma-separated source domains used to constrain targeted botanical searches.
`OPENHERBARIUM_TIMEOUT`	No	`20`	HTTP timeout in seconds for public APIs and Firecrawl calls.

Generic JSON example with all configurable parameters:

{
  "mcpServers": {
    "openherbarium": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://git.home-deneuville.fr/Edern/openherbarium-mcp.git",
        "openherbarium-mcp"
      ],
      "env": {
        "FIRECRAWL_API_URL": "http://localhost:3002",
        "FIRECRAWL_API_KEY": "",
        "BOTANICAL_ALLOWED_DOMAINS": "gbif.org,powo.science.kew.org,missouribotanicalgarden.org,tela-botanica.org,inpn.mnhn.fr,rhs.org.uk,edu,wikimedia.org,wikipedia.org",
        "OPENHERBARIUM_TIMEOUT": "20"
      }
    }
  }
}

Client-specific file locations change between applications and versions. When in doubt, use the app's MCP settings screen and paste the openherbarium server entry under its existing mcpServers object.

Development install with `uv`

git clone https://git.home-deneuville.fr/Edern/openherbarium-mcp.git
cd openherbarium-mcp
uv sync --extra dev

Run tests:

uv run pytest

Run the MCP server over stdio from the checked-out project:

uv run openherbarium-mcp

Hermes Agent configuration for local development

If you want to work on the source code locally instead of using the uvx setup, add the checked-out server to ~/.hermes/config.yaml:

mcp_servers:
  openherbarium:
    command: "uv"
    args:
      - "--directory"
      - "/absolute/path/to/openherbarium-mcp"
      - "run"
      - "openherbarium-mcp"
    timeout: 120
    connect_timeout: 60
    env:
      FIRECRAWL_API_URL: "http://localhost:3002"
      FIRECRAWL_API_KEY: ""
      BOTANICAL_ALLOWED_DOMAINS: "gbif.org,powo.science.kew.org,missouribotanicalgarden.org,tela-botanica.org,inpn.mnhn.fr,rhs.org.uk,edu,wikimedia.org,wikipedia.org"
      OPENHERBARIUM_TIMEOUT: "20"

Restart Hermes Agent. Tools will be exposed with names similar to:

mcp_openherbarium_search_plant
mcp_openherbarium_get_taxonomy
mcp_openherbarium_get_species_information
mcp_openherbarium_get_care_sources
mcp_openherbarium_get_image_sources
mcp_openherbarium_search_botanical_sources

`.env` fallback for manual/local runs

For direct local execution outside an MCP client, you can also copy .env.example to .env and set the same parameters there:

FIRECRAWL_API_URL=http://localhost:3002
FIRECRAWL_API_KEY=

If Firecrawl is not configured, source-search tools return explicit suggested queries and a not_configured status.

Development

uv sync --extra dev
uv run pytest

Project layout:

openherbarium-mcp/
├── src/
│   └── openherbarium_mcp/
│       ├── server.py
│       ├── gbif.py
│       ├── kew.py
│       ├── rhs.py
│       ├── tela_botanica.py
│       ├── wikimedia.py
│       └── firecrawl.py
├── tests/
├── README.md
├── pyproject.toml
├── LICENSE
└── .env.example

Reliability model

The server distinguishes between:

high confidence: exact/high-confidence API matches, mostly GBIF taxonomic matches;
medium confidence: sourced API records that still require interpretation;
low confidence: source candidates or search results that must be manually/agent verified.

OpenHerbarium MCP prefers returning status: unavailable, status: not_configured or empty records over inventing missing data.

License

MIT

README.md

OpenHerbarium MCP

What this MCP does

What this MCP does not do

MCP tools

search_plant(name: str)

get_taxonomy(name: str)

get_species_information(name: str)

get_care_sources(name: str)

get_image_sources(name: str, limit: int = 10)

search_botanical_sources(query: str, limit: int = 5)