Connect Claude to Open-Meteo

Current weather and a 16-day forecast for any coordinates, plus a geocoder that turns a place name into them. No key, no sign-up. Toolspoke puts 2 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: None
Actions exposed: 2
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Open-Meteo
Open the marketplace in your workspace, add Open-Meteo to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Nothing to connect. Open-Meteo needs no credential.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Open-Meteo shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Open-Meteo asks for

Open-Meteo needs no credential. Install it and it works, and there is nothing of yours for Toolspoke to hold.

What Claude can do in Open-Meteo

2 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 2Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

geocode_search
Turn a place name into coordinates: search cities, towns and villages by name and get back latitude, longitude, country, admin region, population, elevation and timezone for each match. This is step one when you have "Berlin" and get_forecast needs 52.52/13.41 - pick a result (the first is usually right, but check `country` when the name is ambiguous: there are Springfields in thirty places) and pass its latitude and longitude on. Matching is fuzzy for names of three characters or more, so partial names work. Free, no key. Returns `{"results": [...]}`, or an empty object when nothing matched - treat a missing `results` as no match, not an error.
get_forecast
Current weather and forecast for one pair of coordinates - up to 16 days ahead and 92 days back, free, no key. Ask only for what you need: `current` for conditions right now, `daily` for day-by-day summaries, `hourly` for hour-by-hour detail; each is a list of variable names and the response carries one array per name (with a matching `_units` object). `weather_code` values are WMO codes: 0 clear, 1 - 3 partly cloudy, 45/48 fog, 51 - 67 drizzle and rain, 71 - 77 snow, 80 - 82 showers, 95 - 99 thunderstorm. Times are ISO 8601 in the requested timezone - the default here is "auto", the timezone at the coordinates, which is almost always what a person means. Units default to °C, km/h and mm; switch with temperature_unit, wind_speed_unit and precipitation_unit. A 16-day hourly request is a large payload, so prefer `daily` for anything beyond a couple of days. Coordinates come from geocode_search when you only have a place name.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 2 actions above are the whole of it. A call to any other name is refused before it reaches Open-Meteo rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in Open-Meteo.
It reaches no further than your credential: Toolspoke holds no access to Open-Meteo of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Open-Meteo: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Open-Meteo. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Open-Meteo's own rate limits. A call that Open-Meteo refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Open-Meteo?

2 named actions: 2 that only read. They include geocode_search and get_forecast. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Open-Meteo connector need?

None at all. Open-Meteo is reachable without one, so there is nothing of yours for Toolspoke to store.

Does the Open-Meteo connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 2 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Open-Meteo connector not do?

The 2 actions above are the whole of it. A call to any other name is refused before it reaches Open-Meteo rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in Open-Meteo. Toolspoke holds no access to Open-Meteo of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Open-Meteo. An agent has to ask. Toolspoke does not retry, queue or back off around Open-Meteo's own rate limits. A call that Open-Meteo refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Open-Meteo's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Open-Meteo?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More data connectors

Browse all of them