Find novel, statistically validated patterns in tabular data — hypothesis-free.
Otherv1.0.1streamable-httpdisco.leap-labs.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 2160ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo Disco@1.26.0 |
| tooling | 35 / 35 | tools/list OK: 14 tools e.g. "discovery_list_plans"; 14/14 described, 14/14 fully-typed schemas, median description 581 chars |
| latency | 4 / 10 | initialize round-trip 2160ms |
| provenance | 15 / 15 | description present; repository linked; version 1.0.1; namespace com.leap-labs matches endpoint/repo |
Score 94/100 · latency 2160ms · 14 tools · auth: open
Claude Code:
claude mcp add --transport http discovery-engine https://disco.leap-labs.com/mcp
Generic MCP client config:
{ "mcpServers": { "discovery-engine": { "type": "http", "url": "https://disco.leap-labs.com/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/com.leap-labs/discovery-engine · referral link https://mcpqueen.com/go/com.leap-labs/discovery-engine (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.leap-labs/discovery-engine)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 03:30 | A | 94 | 2160ms |