io.github.Pak209/alphalabs-intelligence is a remote MCP server that gives an AI agent 6 tools, among them alphalabs_calibration_report, alphalabs_evaluate_signal, alphalabs_explain_decision. It answers at https://api.pak-labs.com/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 20 October 2026, succeeded.
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
alphalabs_calibration_report | Live paper-trading pipeline calibration telemetry: stage funnel, gate failures, near-misses. Derived analytics only — no positions, orders, or account data exist on this surface. |
alphalabs_evaluate_signal | Score YOUR trade idea through the live AlphaLabs deterministic engine: composite score, tier, per-component sub-signals, floors. Price/volume confirmation is not evaluated (no vendor market data). Returns an evaluation_id for alphalabs_expl Inputs: ticker, bias, confidence, catalyst, thesis, catalyst_type |
alphalabs_explain_decision | Glass-box breakdown of a prior evaluation by evaluation_id: every sub-signal, weight, floor, and the composite reasoning. Inputs: evaluation_id |
alphalabs_feature_attribution | Which engine inputs actually predict outcomes, measured on recorded live results: Spearman rankings, median-split deltas, dead inputs. |
alphalabs_get_catalog | Free: list AlphaLabs Intelligence products, prices, and auth model. |
alphalabs_outcome_report | Recorded outcomes of the live pipeline's own decisions: hit rates, score-band tables, accepted-vs-rejected edge, gate near-miss regret. Aggregated engine telemetry — percent moves and counts only. |
Every block below points at https://api.pak-labs.com/mcp. Pick your client and copy.
claude mcp add --transport http io-github-pak209-alphalabs-intel https://api.pak-labs.com/mcp
{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.pak-labs.com/mcp"]
}
}
}{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"url": "https://api.pak-labs.com/mcp"
}
}
}{
"servers": {
"io-github-pak209-alphalabs-intel": {
"type": "http",
"url": "https://api.pak-labs.com/mcp"
}
}
}{
"context_servers": {
"io-github-pak209-alphalabs-intel": {
"url": "https://api.pak-labs.com/mcp"
}
}
}{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"serverUrl": "https://api.pak-labs.com/mcp"
}
}
}{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"url": "https://api.pak-labs.com/mcp"
}
}
}name: io.github.Pak209/alphalabs-intelligence
version: 0.0.1
schema: v1
mcpServers:
- name: io.github.Pak209/alphalabs-intelligence
type: streamable-http
url: https://api.pak-labs.com/mcp{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"httpUrl": "https://api.pak-labs.com/mcp"
}
}
}{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"type": "http",
"url": "https://api.pak-labs.com/mcp"
}
}
}{
"mcpServers": {
"io-github-pak209-alphalabs-intel": {
"url": "https://api.pak-labs.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.pak-labs.com%2Fmcp&type=streamable_http&id=io-github-pak209-alphalabs-intel&name=io.github.Pak209/alphalabs-intelligence
It answered our last check on 20 October 2026 in 729 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 12 September 2026: alphalabs_calibration_report, alphalabs_evaluate_signal, alphalabs_explain_decision, alphalabs_feature_attribution, alphalabs_get_catalog, alphalabs_outcome_report.
It answered our last check on 20 October 2026 in 729 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.pak-labs.com/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.pak209. Endpoint host: api.pak-labs.com. ARD identifier: urn:air:io.github.pak209:mcp:alphalabs-intelligence.
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.