
Connects Claude to the Royal Botanic Gardens, Kew's Plants of the World Online database through the Pipeworx gateway. The source doesn't list specific tools, but this hooks into POWO's botanical data, which typically includes plant taxonomy, distributions, and nomenclature lookups. Hosted as a streamable HTTP endpoint, so no local setup required. You can use it standalone for plant queries or connect to the full Pipeworx gateway to combine botanical data with 826+ other sources. Includes an ask_pipeworx wrapper that handles natural language queries instead of direct tool calls. Reach for this when you need authoritative plant identification or taxonomic data in your AI workflows.
POWO (Plants of the World Online, by the Royal Botanic Gardens, Kew) MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_plants | Search POWO (Plants of the World Online, by Kew) — the authoritative global plant taxonomy database — for accepted plant names and synonyms by scientific or common name. Returns matching taxa with their family, rank, whether the name is accepted, and a POWO fqId you can pass to get_taxon. Keyless. Complements GBIF/iNaturalist with curated botanical taxonomy. |
get_taxon | Fetch a full POWO (Plants of the World Online, by Kew) taxon record by its fqId (e.g. "urn:lsid:ipni.org:names:304293-2", obtained from search_plants). Returns the taxon's classification, family/genus, taxonomic status, native distribution (TDWG region codes), accepted-name resolution (for synonyms), and synonym count. Keyless authoritative botanical taxonomy. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"powo": {
"url": "https://gateway.pipeworx.io/powo/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/powo/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Powo data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/powo_search_plants \
-H 'Content-Type: application/json' \
-d '{"query":"Quercus robur"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/powo_search_plants. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.