Kirk — Unsupervised Structural Change Detection is a remote MCP server that gives an AI agent 14 tools, among them kirk_billing_checkout, kirk_billing_show, kirk_billing_usage. It answers at https://kirk-mcp.kavara.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 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
kirk_billing_checkout | Create a Stripe Checkout Session URL for buying a credit pack (starter / scale / enterprise). Purpose: Hand the caller a self-serve URL to purchase IU credits. Use when: The caller's balance is low, or you want to route to a self-serve top- Inputs: pack |
kirk_billing_show | Return the caller's account_id, IU balance, USD equivalent at list, frozen flag, and recent ledger entries. Purpose: Surface the caller's current billing state — what they can spend, whether the account is frozen, and how recent entries lan |
kirk_billing_usage | Return the caller's inference consumption over the last N days from the append-only Gate 2 events table. Purpose: Historical usage summary + per-tool breakdown for the caller's account. Use when: You need a usage report for the caller or an Inputs: days |
kirk_bulk_howto | Return a self-contained stdlib Python client for scoring at ZERO per-call LLM tokens. Purpose: Hand the caller an HTTP consumer that runs locally so bulk scoring doesn't burn LLM tokens per book. Use when: You need to score more than ~200 b |
kirk_demo_trading | Runs a curated demonstration of Kirk on a trading example. Zero arguments. Returns real Kirk output against the same sealed engine that customer callers hit. Free, rate-limited. First-time users: call this to see what Kirk does before signi |
kirk_demo_uav | Runs a curated demonstration of Kirk on a UAV example. Zero arguments. Returns real Kirk output against the same sealed engine that customer callers hit. Free, rate-limited. First-time users: call this to see what Kirk does before signing u |
kirk_infer_legacy | Score a 50-value feature vector against the legacy /v1/infer route on the sealed engine. Purpose: Backwards-compatible scoring surface for callers that were already targeting the legacy path. Use when: You have an existing client wired to / Inputs: values |
kirk_list_models | Enumerate the model_ids the sealed engine exposes, with the engine sha stamped in-response. Purpose: Discover the model catalog and record the sealed engine sha alongside your inference results. Use when: You are wiring a client for the fir |
kirk_render_book | Render an L2 order-book snapshot into the 20×20 complex128 thermometer tensor WITHOUT invoking the sealed engine. Purpose: Local tensor prep and inspection — see what shape the sealed engine will receive without paying for a scoring call. U Inputs: bid_px, ask_px |
kirk_score_book | Score one L2 order-book snapshot through the sealed single-layer path and return a scalar entropy plus engine attestation. Purpose: Score one snapshot end-to-end through the sealed engine and surface the result plus the engine sha that prod Inputs: bid_px, ask_px, model_id |
kirk_score_book_batch | Score up to 500 L2 order-book snapshots in one MCP call — returns an entropies list plus engine attestation. Purpose: Batch-score up to 500 snapshots through the sealed engine in a single MCP dispatch. Use when: You are validating batch beh Inputs: books, model_id |
kirk_score_l2_book | Score a sequence of full L2 order books as one chain and return per-book entropies plus engine attestation. Purpose: Score complete books — prices, sizes and order counts — rather than prices alone. This is the v2 book contract; it carries Inputs: books, model_id |
kirk_score_random | Synthesize N realistic-geometry L2 book snapshots and score them — convenience wrapper on kirk_score_book_batch. Purpose: Produce a live entropy series with no external data — the fastest way to confirm a new integration is wired end-to-end Inputs: n_samples, model_id, seed |
kirk_verify_engine | Verify sealed engine identity — returns the sha256 of the running scoring binary. Also serves as a liveness probe against the sealed backend. Purpose: Attest which Kirk build is currently serving scoring calls. Response carries the HOST DEF |
Every block below points at https://kirk-mcp.kavara.ai/mcp. Pick your client and copy.
claude mcp add --transport http kirk-unsupervised-structural-cha https://kirk-mcp.kavara.ai/mcp
{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://kirk-mcp.kavara.ai/mcp"]
}
}
}{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"servers": {
"kirk-unsupervised-structural-cha": {
"type": "http",
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"context_servers": {
"kirk-unsupervised-structural-cha": {
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"serverUrl": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}name: Kirk — Unsupervised Structural Change Detection
version: 0.0.1
schema: v1
mcpServers:
- name: Kirk — Unsupervised Structural Change Detection
type: streamable-http
url: https://kirk-mcp.kavara.ai/mcp{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"httpUrl": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"type": "http",
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}{
"mcpServers": {
"kirk-unsupervised-structural-cha": {
"url": "https://kirk-mcp.kavara.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fkirk-mcp.kavara.ai%2Fmcp&type=streamable_http&id=kirk-unsupervised-structural-cha&name=Kirk%20%E2%80%94%20Unsupervised%20Structural%20Change%20Detection
It answered our last check on 21 October 2026 in 469 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
14, as returned by the server's own tools/list on 13 September 2026: kirk_billing_checkout, kirk_billing_show, kirk_billing_usage, kirk_bulk_howto, kirk_demo_trading, kirk_demo_uav, kirk_infer_legacy, kirk_list_models, and 6 more.
It answered our last check on 21 October 2026 in 469 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://kirk-mcp.kavara.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: io.github.ulyssesmodel. Endpoint host: kirk-mcp.kavara.ai. ARD identifier: urn:air:io.github.ulyssesmodel:mcp:kirk-mcp.
First indexed 10 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.