Ocean data for any coast or sea, Australian marine park facts and Marxan reserve design.
Connect Remote server
claude mcp add --transport http biohotspot https://biohotspot.ai4wa.com/mcp{
"mcpServers": {
"biohotspot": {
"url": "https://biohotspot.ai4wa.com/mcp"
}
}
}{
"servers": {
"biohotspot": {
"type": "http",
"url": "https://biohotspot.ai4wa.com/mcp"
}
}
}Settings > Connectors > Add custom connector
URL: https://biohotspot.ai4wa.com/mcpTools 31 found in our last check
look_hereList every Biohotspot map layer with data within `km` of a point on the sea (a place being studied, not the user's location): habitats, wildlife, human uses, protected areas and world ocean maps, with its nearest few items each. Read-only. Use it to learn what a place holds; giv…
look_in_areaList every Biohotspot map layer with data inside a polygon on the sea, with its nearest few items each. Read-only. Give `layer` (an id from the answer) for that layer in full.
understand_areaCheck an area against its protection targets: which habitats it holds, how much of each, what is already protected, and how far each habitat is from its target. Give a polygon, or a point and radius_km. Outside Biohotspot's local planning data the answer comes from world maps an…
simulateRun the Marxan optimiser on Biohotspot's planning data (Exmouth Gulf, Western Australia, for now): the cheapest set of planning squares that meets every habitat target. `polygon` protects the squares mostly inside it (unless `protect` is given); the other settings change targets…
list_scenariosList the scenarios saved by you and by the teams of your projects (or one project's, with project_id): name, project, who saved it and its last run's headline numbers. Read-only.
save_scenarioSave a scenario in one of your projects, where its team sees it on the website: a name, an area (a GeoJSON polygon, optional) and Marxan settings that run_scenario then uses. Side effect: adds a scenario; nothing is overwritten or deleted. Needs a verified sign-in and a place on…
run_scenarioRun Marxan for one of your saved scenarios with its saved settings (any setting given here replaces the saved one for this run) and keep the run with the scenario, as the website does. Takes a few seconds to a minute; returns the run's summary and each habitat's result. Side eff…
delete_scenarioPermanently delete one of your own saved scenarios and the runs kept with it, as the website's delete does. It cannot be undone. Only the person who saved a scenario can delete it; projects and their data cannot be deleted with these tools. Tell the user the scenario's name and…
compare_runsCompare a scenario's kept runs (up to 50, newest first): for each, the targets met, area and cost of the best solution and its settings, ranked best first (most targets met, then lowest cost, then smallest area), with why each other run ranks lower. Read-only.
find_layersFind Biohotspot map layers by words (e.g. 'seagrass', 'coral bleaching') among its 1,600+ world layers. Returns ids, names and categories (25 by default), and whether each can be read with get_features: only layers whose licence lets Biohotspot share their features are (the othe…
get_featuresGet a vector layer's features as GeoJSON from Biohotspot's OGC API, optionally inside a bounding box [west, south, east, north]; up to `limit` features (500 by default, 5,000 at most). Give an id that find_layers marks get_features: true. Read-only.
get_marine_parkGet the facts about an Australian marine park from its Biohotspot page: area, IUCN categories and named zones (CAPAD 2024), habitats, blue carbon and pressures measured inside it, each with its source and licence, and the page's address. Give part of the park's name; `state` (wa…
search_papersSearch Biohotspot's research library (more than 5,200 papers and reports on coasts and marine habitats) for the words; returns titles, years and DOI links where known (10 by default, 50 at most). Read-only.
list_projectsList your Biohotspot projects and the ones shared with you: name, area, your role and how complete their data is. Read-only.
get_projectGet one of your projects: its area's bounding box and size, its data check (each data type covered, partial or missing, with the best layer found) and your role. full=true adds the boundary as GeoJSON and every layer found. Read-only.
list_project_dataList the data a project's team added, with each file's status (receiving, checked, ready, failed). Read-only.
add_project_dataAdd data to a project from a public download link (GeoPackage, zipped Shapefile, GeoJSON, KML, CSV with coordinates or GeoTIFF, up to 200 MB): your own model's output, a survey, a map. Side effect: the file is downloaded, stored and added to the project, where its team can see i…
look_in_project_dataWhat a project team's own data (their accepted uploads) holds at a point on the sea within `km` (default 1), or inside a polygon: per upload, how many features are there and a few of their names, or a grid's value at the point. Only the data you may see on that project. Read-onl…
list_habitatsList the habitats Biohotspot measures across Australia's marine parks (mangroves, the modelled kelp forest biome and tidal marshes, for now): each one's id, name, how many parks hold it and whether it has a page. Read-only.
get_habitatGet one habitat across Australia's marine parks, as its Biohotspot page shows it: the parks that hold it with their figures, sources and the page's address. Give its id from list_habitats or part of its name. Read-only.
get_layer_yearsHow many features of a world map layer fall in each year (for layers with dates, such as sightings or bleaching surveys): the series the map's year slider draws. Give a find_layers id. Read-only.
read_paperRead a research library document's text, page by page (pages `from_page` to `to_page`, at most 30 at once; default the first 5). Give a document id from search_papers. Documents without a PDF in the library have no pages. Read-only.
list_public_projectsList Biohotspot's public projects, the worked examples first: name, area and how complete their data is, and whether each is already in your list. Read-only.
create_projectCreate a Biohotspot project of yours for an area on the sea: a name and a GeoJSON polygon. Biohotspot then runs its data check (what data covers the area). Side effect: adds a project you own; nothing else changes. Needs a verified sign-in.
update_projectRename one of your projects or replace its area (a GeoJSON polygon; the data check runs again). Overwrites the old name or area. Needs owner or editor rights; who can see the project is changed on the website only.
finish_uploadFinish a file added to a project (list_project_data shows those waiting): say what it is (title, source, year, licence: cc-by, cc0, cc-by-nc, other-open, restricted or unsure; item = the data-check item it fills), match its columns (`mapping`, {field: column}, e.g. {"scientificN…
load_public_projectAdd a public project (list_public_projects) to your list, view only, to look at and plan in it. Side effect: it appears in your project list; nothing else changes.
remove_project_from_listTake a project off your list: a public project you loaded, or a project shared with you, which you then leave (its team must add you again for you to see its team-only data). Your own projects cannot be removed this way. Ask the user before calling it for a shared project.
share_projectShare one of your projects with a person by email, as an editor or a viewer: Biohotspot emails them a link in your name. Side effect: an email is sent and they join the project's team. Only adds people: someone already on the team keeps their role (change roles on the website).…
make_reportMake a PDF report and get a link to it, good for a day: give project_id for the project's data report (what data covers the area, what is missing, the team's files and scenarios) or scenario_id for a scenario report (its habitats against their targets, its kept Marxan runs compa…
email_reportEmail a scenario's PDF report to up to 10 people with a link to the scenario, in your name (replies reach you), as the website's Share report does. Side effect: an email is sent. Confirm the addresses with the user first.
Details
| Endpoint | https://biohotspot.ai4wa.com/mcp (Streamable HTTP) |
| First published | 13 Nov 2026 |
| Last updated | 13 Nov 2026 |
| Registry name | io.github.PascalSun/biohotspot |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.