Connect Shreddy and your agent gets 4 tools, among them get_clip, get_venue, list_venues. It answers at https://api.shreddy.ai/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 28 September 2026; the last check, on 14 November 2026, succeeded.
Measured mountain bike jumps and speeds at bike parks: public clips, read-only.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_clip | One public clip by id: where and when it was recorded (day and clock time at the venue), the rider if named, every measurement (jump height, speed, lap times, plus airtime), how it was calibrated, and for a group clip (a train of riders) ea Inputs: id |
get_venue | Everything about one bike park in one call: its runs and their features (with clip counts), how many public clips and measured rides it has, its records (the top 3 public rides for jump height, speed and airtime, biggest first; no lap recor Inputs: venue |
list_venues | List the bike parks (venues) that have public Shreddy clips: name, city, state, how many clips and how many measured rides, the runs and features there, and a link. Filter by `query` (matches name, city or state) or sort nearest first with Inputs: query, near, limit |
search_clips | Search public clips. Newest first by default; sort "biggest" or "smallest" with a `metric` for the biggest jumps, most airtime or fastest runs (ranked results list each rider of a group clip on their own, and leave out rides with no value f Inputs: venue, feature, rider, when, since, until |
Every block below points at https://api.shreddy.ai/mcp. Pick your client and copy.
claude mcp add --transport http shreddy https://api.shreddy.ai/mcp
{
"mcpServers": {
"shreddy": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.shreddy.ai/mcp"]
}
}
}{
"mcpServers": {
"shreddy": {
"url": "https://api.shreddy.ai/mcp"
}
}
}{
"servers": {
"shreddy": {
"type": "http",
"url": "https://api.shreddy.ai/mcp"
}
}
}{
"context_servers": {
"shreddy": {
"url": "https://api.shreddy.ai/mcp"
}
}
}{
"mcpServers": {
"shreddy": {
"serverUrl": "https://api.shreddy.ai/mcp"
}
}
}{
"mcpServers": {
"shreddy": {
"url": "https://api.shreddy.ai/mcp"
}
}
}name: Shreddy
version: 0.0.1
schema: v1
mcpServers:
- name: Shreddy
type: streamable-http
url: https://api.shreddy.ai/mcp{
"mcpServers": {
"shreddy": {
"httpUrl": "https://api.shreddy.ai/mcp"
}
}
}{
"mcpServers": {
"shreddy": {
"type": "http",
"url": "https://api.shreddy.ai/mcp"
}
}
}{
"mcpServers": {
"shreddy": {
"url": "https://api.shreddy.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.shreddy.ai%2Fmcp&type=streamable_http&id=shreddy&name=Shreddy
It answered our last check on 14 November 2026 in 652 ms. Over 4 checks since 28 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by shreddy.ai and served from api.shreddy.ai, the vendor's own domain: https://api.shreddy.ai/mcp.
4, as returned by the server's own tools/list on 17 November 2026: get_clip, get_venue, list_venues, search_clips.
It answered our last check on 14 November 2026 in 652 ms. Over 4 checks since 28 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.shreddy.ai/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: ai.shreddy. Endpoint host: api.shreddy.ai. ARD identifier: urn:air:ai.shreddy:mcp:shreddy.
First indexed 28 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.