ClimbCast is an MCP server with 9 tools an agent can call, among them get_access_and_permits, get_alerts, get_forecast_accuracy. It answers at https://climbcast.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 27 September 2026; the last check, on 12 November 2026, succeeded.
Conditions, trip briefs, alerts, permits, roads, hourly, areas, accuracy for WA, OR, BC. No account.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_access_and_permits | Returns the permit entry and road access shown on a route's forecast page for a covered objective: the permit status, fee, notes and official link, and the road conditions for the approach passes, with highway, temperature, restrictions, th Inputs: slug, route_id |
get_alerts | Returns the NPS park alerts and National Weather Service fire weather alerts displayed for a covered objective, with source attribution and retrieval timestamps. ClimbCast does not carry current USDA Forest Service alerts or closures. Infor Inputs: slug |
get_forecast_accuracy | Returns stored public regional forecast accuracy, including observed-station or model-proxy truth lineage, data sufficiency, and eligibility. Takes either a region_id or an objective slug, which resolves to the accuracy region of the NWAC z Inputs: region_id, slug |
get_hourly_conditions | Returns the two-hourly temperature, wind speed, and wind direction shown in the hourly view of the forecast page's weather by elevation grid, for one day in the free forecast window, with local times, ISO timestamps, the time zone, and the Inputs: slug, route_id, date, activity, elevation_band |
get_objective_conditions | Returns public conditions for a covered objective: summit weather, the objective page's route list with grade, type, and round-trip distance, source provenance, and timestamps, in JSON or markdown. Covers up to five days. Daylight and air q Inputs: slug, format |
get_route_conditions | Returns up to five days of public route conditions, anchored to the route high point, with catalog gain, source provenance, and timestamps. An optional activity input selects one of the route's activities listed by search_objectives. Days c Inputs: slug, route_id, activity, format |
get_trip_brief | Returns the signed-out forecast page sections for a route in one call, covering up to five days, or one day with the date input: forecast days, daylight, air quality, and agency alerts, each with source provenance and a freshness status. Fo Inputs: slug, route_id, activity, date, include |
list_areas | Lists the public coverage areas shown on the coverage directory, with each area's slug, name, state or province code, and visible activities. An area is a fixed geographic definition, not a distance from the caller. Its slug is the optional |
search_objectives | Searches the public coverage catalog by name or alias, with optional region and activity filters. Coverage follows the current public scope. Region filters include WA, OR, and BC. Results list each objective's slug and route IDs with their Inputs: query, area, region, activity, limit |
Every block below points at https://climbcast.io/mcp. Pick your client and copy.
claude mcp add --transport http climbcast https://climbcast.io/mcp
{
"mcpServers": {
"climbcast": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://climbcast.io/mcp"]
}
}
}{
"mcpServers": {
"climbcast": {
"url": "https://climbcast.io/mcp"
}
}
}{
"servers": {
"climbcast": {
"type": "http",
"url": "https://climbcast.io/mcp"
}
}
}{
"context_servers": {
"climbcast": {
"url": "https://climbcast.io/mcp"
}
}
}{
"mcpServers": {
"climbcast": {
"serverUrl": "https://climbcast.io/mcp"
}
}
}{
"mcpServers": {
"climbcast": {
"url": "https://climbcast.io/mcp"
}
}
}name: ClimbCast
version: 0.0.1
schema: v1
mcpServers:
- name: ClimbCast
type: streamable-http
url: https://climbcast.io/mcp{
"mcpServers": {
"climbcast": {
"httpUrl": "https://climbcast.io/mcp"
}
}
}{
"mcpServers": {
"climbcast": {
"type": "http",
"url": "https://climbcast.io/mcp"
}
}
}{
"mcpServers": {
"climbcast": {
"url": "https://climbcast.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fclimbcast.io%2Fmcp&type=streamable_http&id=climbcast&name=ClimbCast
It answered our last check on 12 November 2026 in 266 ms. Over 4 checks since 27 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by climbcast.io and served from climbcast.io, the vendor's own domain: https://climbcast.io/mcp.
9, as returned by the server's own tools/list on 16 November 2026: get_access_and_permits, get_alerts, get_forecast_accuracy, get_hourly_conditions, get_objective_conditions, get_route_conditions, get_trip_brief, list_areas, and 1 more.
It answered our last check on 12 November 2026 in 266 ms. Over 4 checks since 27 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://climbcast.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.climbcast. Endpoint host: climbcast.io. ARD identifier: urn:air:io.climbcast:mcp:climbcast.
First indexed 27 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.