Should my agent depend on the MCP server io.github.Vaquill-AI/courtlistener-mcp?

Verdict: allow — rich-shared — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

CourtListener

io.github.Vaquill-AI/courtlistener-mcp

MCP for CourtListener: US federal and state opinions, dockets, judges, plus eCFR regulations.

— the operator's own registry description reported

Publisher io.github.Vaquill-AI · first seen 2026-08-12 · endpoint https://courtlistener-mcp.vaquill.ai/mcp/

allow

verdict

rich-shared

cluster

ok_tools

answers

tools served

Dependency rating derived

allow — rich-shared — safe to depend on

Cluster rich-shared · distinctiveness 0.623 (unusual). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency241 ms

vs populationtypical

protocolcurrent

authopen

Use — can it use it?

tools34

vs populationhigh

capabilities6

harnessA

Trust — can it rely on it?

identityshared

servers on its host1

servers on its domain3

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_9449fc866c2312ae4f4c190d · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

citation_batch_lookup_citations citation_enhanced_citation_lookup citation_extract_citations_from_text citation_lookup_citation citation_parse_citation_with_citeurl citation_verify_citation_format ecfr_get_ancestry ecfr_get_daily_search_counts ecfr_get_hierarchy_search_counts ecfr_get_search_count ecfr_get_search_suggestions ecfr_get_search_summary ecfr_get_source_xml ecfr_get_title_search_counts ecfr_get_title_structure ecfr_get_title_versions ecfr_list_agencies ecfr_list_all_corrections ecfr_list_corrections_by_title ecfr_list_titles ecfr_search_regulations get_audio get_cluster get_court get_docket get_opinion get_person search_audio search_dockets search_dockets_with_documents search_opinions search_people search_recap_documents status

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility check	tools passing	ok
name is clear & specific	34/34	✓
has a description	34/34	✓
description is substantive	34/34	✓
parameters are typed	34/34	✓
parameters are described	34/34	✓

34 of 34 tools graded · 34 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18

protocol version

—

session model

3.4.3

server version CourtListener MCP Server

Capabilities: experimental extensions logging prompts resources tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:59:18Z	ok_tools	200	241	2025-06-18
2026-08-12T05:34:30Z	ok_tools	200	254	2025-06-18

Watch or embed this verdict

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.Vaquill-AI/courtlistener-mcp.svg)](https://robinsaige.com/s/io.github.Vaquill-AI/courtlistener-mcp)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview