Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CourtListener

REMOTE · COURTLISTENER-MCP.VAQUILL.AI · SCANNED SEP 20

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

Available components

remote · courtlistener-mcp.vaquill.ai 80
0 this week 80 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security60
Transport & Reachability100
Schema Quality & AI Usability77
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2987 tokens (~87/item across 34 items; 34 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 34 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 35 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the CourtListener MCP server?

CourtListener is a hosted endpoint at https://courtlistener-mcp.vaquill.ai/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · courtlistener-mcp.vaquill.ai

# add to Claude Code
claude mcp add --transport http vaquill-ai-courtlistener-mcp 'https://courtlistener-mcp.vaquill.ai/mcp/'
// .cursor/mcp.json
{
  "mcpServers": {
    "vaquill-ai-courtlistener-mcp": {
      "url": "https://courtlistener-mcp.vaquill.ai/mcp/"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "vaquill-ai-courtlistener-mcp": {
      "type": "http",
      "url": "https://courtlistener-mcp.vaquill.ai/mcp/"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.vaquill-ai-courtlistener-mcp]
url = "https://courtlistener-mcp.vaquill.ai/mcp/"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vaquill-ai-courtlistener-mcp": {
      "type": "remote",
      "url": "https://courtlistener-mcp.vaquill.ai/mcp/",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add vaquill-ai-courtlistener-mcp --url 'https://courtlistener-mcp.vaquill.ai/mcp/' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  vaquill-ai-courtlistener-mcp:
    url: "https://courtlistener-mcp.vaquill.ai/mcp/"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "vaquill-ai-courtlistener-mcp": {
      "Transport": "http",
      "Url": "https://courtlistener-mcp.vaquill.ai/mcp/"
    }
  }
}
# add to Vellum
assistant mcp add vaquill-ai-courtlistener-mcp -t streamable-http -u 'https://courtlistener-mcp.vaquill.ai/mcp/'
// mcp.json
{
  "mcpServers": {
    "vaquill-ai-courtlistener-mcp": {
      "type": "http",
      "url": "https://courtlistener-mcp.vaquill.ai/mcp/"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 24 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 7 Aug 26 0
    • The server no longer declares the “experimental” capability functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Jul 26 0

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://courtlistener-mcp.vaquill.ai/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=vaquill.ai CN=WE1,O=Google Trust Services,C=US 18 Sept 2026 17 Dec 2026 ECDSA 256 ECDSA-SHA256 599ec1f46b8c7e350e5aeb78219f0309
SANs: vaquill.ai, *.vaquill.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of courtlistener-mcp.vaquill.ai. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
vaquill.ai. present 2371 13 Verified
courtlistener-mcp.vaquill.ai. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://courtlistener-mcp.vaquill.ai/mcp/ Verified 200
http (plaintext) http://courtlistener-mcp.vaquill.ai/mcp/ HTTPS enforced 301 https://courtlistener-mcp.vaquill.ai/mcp/
MCP tools · 34 exposed · ~2,883 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
citation_batch_lookup_citations ~60

Look up multiple legal citations in a single request. This is more efficient than making individual requests for each citation. Accepts up to 100 citations at once.

NameTypeReqDescription
citationsarrayyesList of citations to look up (max 100)

Structured output declared, but exposes no named fields.

No examples provided.

citation_enhanced_citation_lookup ~83

Enhanced citation lookup combining citeurl parsing with CourtListener data. This tool first uses citeurl to parse and validate the citation format, then optionally queries the CourtListener API for additional case information.

NameTypeReqDescription
citationstringyesThe citation to look up and analyze
include_courtlistenerboolean–Whether to also perform CourtListener API lookup

Structured output declared, but exposes no named fields.

No examples provided.

citation_extract_citations_from_text ~66

Extract all legal citations from a block of text using citeurl. This tool finds and parses all legal citations within a given text, including both long-form and short-form citations (like 'id.' references).

NameTypeReqDescription
textstringyesText containing legal citations to extract

Structured output declared, but exposes no named fields.

No examples provided.

citation_lookup_citation ~120

Look up a legal citation to find the opinion it references in CourtListener. This tool accepts various citation formats including: - U.S. Reporter citations (e.g., "410 U.S. 113") - Federal Reporter citations (e.g., "123 F.3d 456") - WestLaw citations (e.g., "2023 WL 12345") - State reporter citations

NameTypeReqDescription
citationstringyesThe citation to look up (e.g., '410 U.S. 113', '2023 WL 12345')

Structured output declared, but exposes no named fields.

No examples provided.

citation_parse_citation_with_citeurl ~137

Parse a legal citation using citeurl's advanced citation recognition. This tool uses the citeurl library to parse legal citations and extract structured information including tokens, normalized format, and URL generation. Returns detailed information about the citation including: - Recognized citation format and source - Extracted tokens (volume, reporter, page, etc.) - Generated URL if available - Normalized citation text

NameTypeReqDescription
broadboolean–Use broad matching for more flexible parsing
citationstringyesThe citation to parse (e.g., '410 U.S. 113', '42 USC § 1988')

Structured output declared, but exposes no named fields.

No examples provided.

citation_verify_citation_format ~87

Verify if a citation string is in a valid format using citeurl's advanced parsing. This tool performs validation using citeurl's comprehensive citation templates to check if a citation appears to be in a recognized legal citation format. This is much more accurate than simple regex matching. Returns information about the citation format and any detected issues.

NameTypeReqDescription
citationstringyesThe citation to verify

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_ancestry ~92

Get the ancestry chain (title -> ... -> node) for a CFR node on a date.

NameTypeReqDescription
datestringyesSnapshot date (YYYY-MM-DD)
part––Restrict to a part, e.g. '75'
section––Restrict to a section, e.g. '75.1'
titleintegeryesCFR title number (1-50)

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_daily_search_counts ~50

Get search result counts broken down by date (daily histogram).

NameTypeReqDescription
date––As-of date (YYYY-MM-DD)
querystringyesFull-text search query over the CFR

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_hierarchy_search_counts ~49

Get search result counts distributed across the CFR hierarchy.

NameTypeReqDescription
date––As-of date (YYYY-MM-DD)
querystringyesFull-text search query over the CFR

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_search_count ~72

Get the total number of CFR sections matching a search query.

NameTypeReqDescription
agency_slugs––Restrict to agency slugs
date––As-of date (YYYY-MM-DD)
querystringyesFull-text search query over the CFR
title––Restrict to a title

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_search_suggestions ~35

Get search-term suggestions for a partial CFR query.

NameTypeReqDescription
querystringyesPartial query to get suggestions for

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_search_summary ~74

Get summary details (counts + metadata) for a CFR search query.

NameTypeReqDescription
agency_slugs––Restrict to agency slugs
date––As-of date (YYYY-MM-DD)
querystringyesFull-text search query over the CFR
title––Restrict to a title

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_source_xml ~201

Fetch the source regulation TEXT (XML) for a CFR node on a snapshot date. Pass a part or section to scope the request. Fetching an entire large title at once can time out on the eCFR side, so narrowing is strongly recommended. Returns the raw XML under ``content_xml``.

NameTypeReqDescription
appendix––Appendix identifier
chapter––Chapter, e.g. 'I'
datestringyesSnapshot date (YYYY-MM-DD)
part––Part to fetch, e.g. '75'. STRONGLY recommended: whole-title fetches can time out.
section––Section, e.g. '75.1'
subchapter––Subchapter, e.g. 'B'
subpart––Subpart, e.g. 'C'
subtitle––Subtitle, e.g. 'A'
titleintegeryesCFR title number (1-50)

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_title_search_counts ~48

Get search result counts broken down by CFR title.

NameTypeReqDescription
date––As-of date (YYYY-MM-DD)
querystringyesFull-text search query over the CFR

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_title_structure ~56

Get the full hierarchical structure (title -> section) of a CFR title on a date.

NameTypeReqDescription
datestringyesSnapshot date (YYYY-MM-DD)
titleintegeryesCFR title number (1-50)

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_get_title_versions ~39

List the available content versions (issue dates) for one CFR title.

NameTypeReqDescription
titleintegeryesCFR title number (1-50)

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_list_agencies ~27

List all agencies that appear in the CFR, with their title/chapter references.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_list_all_corrections ~54

List CFR corrections, optionally filtered by title and/or effective date.

NameTypeReqDescription
date––Corrections in effect on this date (YYYY-MM-DD)
title––Restrict to a CFR title number

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_list_corrections_by_title ~37

List all corrections for a single CFR title.

NameTypeReqDescription
titleintegeryesCFR title number (1-50)

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_list_titles ~26

List all 50 CFR titles with their latest amended/issue dates and status.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

ecfr_search_regulations ~136

Full-text search over federal regulations, returning matching sections with hierarchy.

NameTypeReqDescription
agency_slugs––Restrict to one or more agency slugs (from list_agencies)
date––Search the CFR as of this date (YYYY-MM-DD)
order––Sort order: 'relevance', 'hierarchy', 'newest_first', 'oldest_first'
pageinteger–Page number
per_pageinteger–Results per page (max 20)
querystringyesFull-text search query over the CFR
title––Restrict to a CFR title number

Structured output declared, but exposes no named fields.

No examples provided.

get_audio ~33

Get oral argument audio information by ID from CourtListener.

NameTypeReqDescription
audio_idstringyesThe audio recording ID to retrieve

Structured output declared, but exposes no named fields.

No examples provided.

get_cluster ~32

Get an opinion cluster by ID from CourtListener.

NameTypeReqDescription
cluster_idstringyesThe opinion cluster ID to retrieve

Structured output declared, but exposes no named fields.

No examples provided.

get_court ~42

Get court information by ID from CourtListener.

NameTypeReqDescription
court_idstringyesThe court ID to retrieve (e.g., 'scotus', 'ca9')

Structured output declared, but exposes no named fields.

No examples provided.

get_docket ~33

Get a specific court docket by ID from CourtListener.

NameTypeReqDescription
docket_idstringyesThe docket ID to retrieve

Structured output declared, but exposes no named fields.

No examples provided.

get_opinion ~33

Get a specific court opinion by ID from CourtListener.

NameTypeReqDescription
opinion_idstringyesThe opinion ID to retrieve

Structured output declared, but exposes no named fields.

No examples provided.

get_person ~36

Get judge or legal professional information by ID from CourtListener.

NameTypeReqDescription
person_idstringyesThe person (judge) ID to retrieve

Structured output declared, but exposes no named fields.

No examples provided.

search_audio ~158

Search oral argument audio recordings in CourtListener.

NameTypeReqDescription
argued_after––Filter arguments after this date (YYYY-MM-DD)
argued_before––Filter arguments before this date (YYYY-MM-DD)
case_name––Filter by case name
court––Court ID filter (e.g., 'scotus', 'ca9')
cursor––Pagination cursor from a prior response's next_cursor
judge––Filter by judge name
limitinteger–Max results from this page (upper bound; CL pages ~20)
order_bystring–Sort by 'score desc', 'dateArgued desc', or 'dateArgued asc'
qstringyesSearch query for oral argument audio

Structured output declared, but exposes no named fields.

No examples provided.

search_dockets ~182

Search federal cases (dockets) from PACER in CourtListener.

NameTypeReqDescription
case_name––Filter by case name
court––Court ID filter (e.g., 'scotus', 'ca9')
cursor––Pagination cursor from a prior response's next_cursor
date_filed_after––Filter dockets filed after this date (YYYY-MM-DD)
date_filed_before––Filter dockets filed before this date (YYYY-MM-DD)
docket_number––Specific docket number to search for
limitinteger–Max results from this page (upper bound; CL pages ~20)
order_bystring–Sort by 'score desc', 'dateFiled desc', or 'dateFiled asc'
party_name––Filter by party name
qstringyesSearch query for docket text

Structured output declared, but exposes no named fields.

No examples provided.

search_dockets_with_documents ~201

Search federal cases (dockets) with up to three nested documents. If there are more than three matching documents, the more_docs field will be true.

NameTypeReqDescription
case_name––Filter by case name
court––Court ID filter (e.g., 'scotus', 'ca9')
cursor––Pagination cursor from a prior response's next_cursor
date_filed_after––Filter dockets filed after this date (YYYY-MM-DD)
date_filed_before––Filter dockets filed before this date (YYYY-MM-DD)
docket_number––Specific docket number to search for
limitinteger–Max results from this page (upper bound; CL pages ~20)
order_bystring–Sort by 'score desc', 'dateFiled desc', or 'dateFiled asc'
party_name––Filter by party name
qstringyesSearch query for federal cases

Structured output declared, but exposes no named fields.

No examples provided.

search_opinions ~195

Search case law opinion clusters with nested Opinion documents in CourtListener.

NameTypeReqDescription
case_name––Filter by case name
cited_gt––Minimum number of times opinion has been cited
cited_lt––Maximum number of times opinion has been cited
court––Court ID filter (e.g., 'scotus', 'ca9')
cursor––Pagination cursor from a prior response's next_cursor
filed_after––Only show opinions filed after this date (YYYY-MM-DD)
filed_before––Only show opinions filed before this date (YYYY-MM-DD)
judge––Filter by judge name
limitinteger–Max results from this page (upper bound; CL pages ~20)
order_bystring–Sort by 'score desc', 'dateFiled desc', or 'dateFiled asc'
qstringyesSearch query for full text of opinions

Structured output declared, but exposes no named fields.

No examples provided.

search_people ~154

Search judges and legal professionals in the CourtListener database.

NameTypeReqDescription
appointed_by––Filter by appointing authority
cursor––Pagination cursor from a prior response's next_cursor
limitinteger–Max results from this page (upper bound; CL pages ~20)
name––Filter by person's name
order_bystring–Sort by 'score desc' or 'name asc'
political_affiliation––Filter by political affiliation
position_type––Filter by position type (e.g., 'jud' for judge)
qstringyesSearch query for judges and legal professionals
school––Filter by school attended
selection_method––Filter by selection method

Structured output declared, but exposes no named fields.

No examples provided.

search_recap_documents ~202

Search federal filing documents from PACER in the RECAP archive.

NameTypeReqDescription
attachment_number––Specific attachment number to search for
case_name––Filter by case name
court––Court ID filter (e.g., 'scotus', 'ca9')
cursor––Pagination cursor from a prior response's next_cursor
docket_number––Specific docket number to search for
document_number––Specific document number to search for
filed_after––Filter documents filed after this date (YYYY-MM-DD)
filed_before––Filter documents filed before this date (YYYY-MM-DD)
limitinteger–Max results from this page (upper bound; CL pages ~20)
order_bystring–Sort by 'score desc', 'dateFiled desc', or 'dateFiled asc'
party_name––Filter by party name
qstringyesSearch query for RECAP filing documents

Structured output declared, but exposes no named fields.

No examples provided.

status ~33

Check the status of the CourtListener MCP server. Returns: A dictionary containing server status, system metrics, and service information.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the CourtListener MCP server?

CourtListener is an MCP server listed in the public MCP registry as io.github.Vaquill-AI/courtlistener-mcp. MCP for CourtListener: US federal and state opinions, dockets, judges, plus eCFR regulations. This page covers its hosted endpoint (https://courtlistener-mcp.vaquill.ai/mcp/).

Is the CourtListener MCP server safe to use?

CourtListener scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CourtListener MCP server expose?

CourtListener exposes 34 tools: status, search_opinions, search_dockets, search_dockets_with_documents, search_recap_documents, and 29 more. Their descriptions and schemas cost roughly 2,883 tokens of context every time the server is loaded.

Does the CourtListener MCP server require authentication?

No. We connected to CourtListener without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the CourtListener MCP server still maintained?

CourtListener is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.