MCP for CourtListener: US federal and state opinions, dockets, judges, plus eCFR regulations.
Dev & Codev0.1.0streamable-httpcourtlistener-mcp.vaquill.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1201ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo CourtListener MCP Server@3.4.3 |
| tooling | 35 / 35 | tools/list OK: 34 tools e.g. "status"; 34/34 described, 34/34 fully-typed schemas, median description 69 chars |
| latency | 7 / 10 | initialize round-trip 1201ms |
| provenance | 15 / 15 | description present; repository linked; version 0.1.0; namespace io.github.Vaquill-AI matches endpoint/repo |
Score 97/100 · latency 1201ms · 34 tools · auth: open
Claude Code:
claude mcp add --transport http courtlistener-mcp https://courtlistener-mcp.vaquill.ai/mcp/
Generic MCP client config:
{ "mcpServers": { "courtlistener-mcp": { "type": "http", "url": "https://courtlistener-mcp.vaquill.ai/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/io.github.Vaquill-AI/courtlistener-mcp · referral link https://mcpqueen.com/go/io.github.Vaquill-AI/courtlistener-mcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.Vaquill-AI/courtlistener-mcp)
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 20:03 | A | 97 | 1201ms |