CourtListener

io.github.Vaquill-AI由 GitHub 账号 Vaquill-AI 发布v0.1.0更新于 Oct 24, 2026

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

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆

概览

AI 生成的概览

远程 MCP 服务器,让助手以只读方式访问 CourtListener 的判例、案卷、法官与口头辩论,以及 eCFR 联邦法规。

可以做什么
检索并获取 CourtListener 判例资料:意见书、意见书集群、案卷、RECAP/PACER 文件、口头辩论音频、法官与法院,搜索支持游标分页,各类记录可按 ID 查询。查询、批量查询、校验、解析法律引注,并从文本中提取引注,可结合 CourtListener 案件数据增强。浏览与搜索 eCFR:列出标题、机构与更正,查看标题结构与层级,获取源 XML,并进行法规全文检索及计数、摘要与建议。查看服务器状态与指标。
适用场景
适合法律研究工作流:查找美国联邦与州判例、查看案卷与提交文件、校验或提取引注、阅读联邦法规。当助手需要无需 OAuth 的 CourtListener 数据,或在判例之外还需要 eCFR 法规工具时值得添加。
运行要求
远程 streamable HTTP 端点,无需本地安装。需要免费的 CourtListener API 令牌,通过 X-CourtListener-Token 请求头发送。需要能访问托管端点、CourtListener 与 eCFR API 的网络。也可用 Python/uv 或 Docker 自托管,并可选设置 COURT_LISTENER_API_KEY。
安装前请注意
CourtListener 令牌属于凭据,会随每次请求发送;README 称服务器仅转发而不存储,但它仍会离开本机。所有工具均说明为只读,不会写入或修改数据。查询内容与令牌会发送给第三方服务(CourtListener、eCFR)。

安装

在 SourceWeft 中

  1. 打开 控制台中的 CourtListener,将其添加到工作区。
  2. 连接 X-CourtListener-Token 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.Vaquill-AI%2Fcourtlistener-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "courtlistener": {
      "type": "http",
      "url": "https://courtlistener-mcp.vaquill.ai/mcp/",
      "headers": {
        "X-CourtListener-Token": "<YOUR_API_KEY>"
      }
    }
  }
}

README

CourtListener MCP Server

A Model Context Protocol server that gives AI assistants access to the CourtListener legal database (US federal + state court opinions, dockets, RECAP filings, PACER data, oral arguments, judges) and the Electronic Code of Federal Regulations via the official CourtListener API v4.

Use it with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, ChatGPT Desktop, or any MCP-compatible client.

Forked from Travis-Prall/court-listener-mcp. This fork adds a hosted endpoint, bring-your-own-key (BYOK) auth, a /health route, Dockerfile hardening, a full eCFR (federal regulations) tool suite, cursor pagination, per-client rate limiting, and read-only tool annotations. See the changelog for details.

When to use this vs. the official server

Free Law Project (who run CourtListener) host an official MCP at https://mcp.courtlistener.com/ (OAuth, free with any CourtListener account) - see their announcement. Prefer it if you want OAuth and the broadest CourtListener coverage. Use this server if you want: eCFR federal-regulations tools (the official server has none), simple BYOK header auth (no OAuth dance), or a self-hosted/embeddable Python server. The two are complementary.

[Discord]

Use the hosted endpoint (no install)

The Vaquill team runs a public instance for the community:

https://courtlistener-mcp.vaquill.ai/mcp/

You bring your own free CourtListener token from courtlistener.com/help/api/rest/, the server forwards it. We never see or store your key.

Claude Desktop / Claude Code

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "courtlistener": {      "url": "https://courtlistener-mcp.vaquill.ai/mcp/",      "headers": {        "X-CourtListener-Token": "YOUR_COURTLISTENER_TOKEN"      }    }  }}

Cursor

.cursor/mcp.json:

json
{  "mcpServers": {    "courtlistener": {      "url": "https://courtlistener-mcp.vaquill.ai/mcp/",      "headers": { "X-CourtListener-Token": "YOUR_COURTLISTENER_TOKEN" }    }  }}

VS Code (GitHub Copilot Chat)

.vscode/mcp.json:

json
{  "servers": {    "courtlistener": {      "type": "http",      "url": "https://courtlistener-mcp.vaquill.ai/mcp/",      "headers": { "X-CourtListener-Token": "YOUR_COURTLISTENER_TOKEN" }    }  }}

Claude Web (custom connector)

Settings → Connectors → Add custom connector → paste the URL and add X-CourtListener-Token as a header. Workspace owners only.

Windsurf, Continue, etc.

Any client that supports MCP streamable HTTP with custom headers works. For stdio-only clients, run the server locally (see below) or proxy with mcp-remote.

Tools

34 tools across 4 groups (each group is namespaced). All are read-only.

GroupTools
Search (CourtListener)search_opinions, search_dockets, search_dockets_with_documents, search_recap_documents, search_audio, search_people
Get (CourtListener)get_opinion, get_docket, get_audio, get_court, get_person, get_cluster
Citationcitation_lookup_citation, citation_batch_lookup_citations, citation_verify_citation_format, citation_parse_citation_with_citeurl, citation_extract_citations_from_text, citation_enhanced_citation_lookup
eCFR (federal regulations)ecfr_list_titles, ecfr_get_title_versions, ecfr_get_title_structure, ecfr_get_ancestry, ecfr_get_source_xml, ecfr_list_agencies, ecfr_list_all_corrections, ecfr_list_corrections_by_title, ecfr_search_regulations, ecfr_get_search_count, ecfr_get_search_summary, ecfr_get_title_search_counts, ecfr_get_daily_search_counts, ecfr_get_hierarchy_search_counts, ecfr_get_search_suggestions
Systemstatus

Search tools accept a cursor param and return a next_cursor for pagination. See app/README.md for full parameter details.

Authentication

Two modes, in priority order:

  1. Per-request header (BYOK) — preferred for hosted / shared deployments. Send the user's CourtListener key on every MCP request:
    • X-CourtListener-Token: <key> (preferred), or
    • Authorization: Token <key> (CourtListener's native scheme — only works if the MCP server itself isn't already gated by Authorization).
  2. Server env fallback — set COURT_LISTENER_API_KEY on the server. Used when no per-request header is supplied. Leave unset on public instances to force BYOK and avoid burning the operator's quota.

If neither is provided, tools return a ValueError with a clear message.

Self-host

Docker

bash
git clone https://github.com/Vaquill-AI/courtlistener-mcp.gitcd courtlistener-mcpcp .env.example .env  # optionally set COURT_LISTENER_API_KEY for single-tenantdocker compose up -d# server at http://localhost:8000/mcp/

Python (uv)

bash
uv syncuv run python -m app --transport http

Stdio (local CLI integration)

bash
uv run python -m app --transport stdio

Add to Claude Desktop:

json
{  "mcpServers": {    "courtlistener-local": {      "command": "uv",      "args": ["run", "--directory", "/abs/path/to/courtlistener-mcp", "python", "-m", "app", "--transport", "stdio"],      "env": { "COURT_LISTENER_API_KEY": "your_token" }    }  }}

Configuration

VarRequiredDefaultNotes
COURT_LISTENER_API_KEYOptional*—Fallback when no per-request header. Leave unset on public servers.
COURTLISTENER_BASE_URLNohttps://www.courtlistener.com/api/rest/v4/
COURTLISTENER_TIMEOUTNo30seconds
MCP_TRANSPORTNostdiostdio | http | sse
MCP_PORTNo8000http/sse only
HOSTNo0.0.0.0http/sse only
ECFR_BASE_URLNohttps://www.ecfr.goveCFR API base (no key required)
RATE_LIMIT_ENABLEDNotruePer-client MCP rate limiting
RATE_LIMIT_RPSNo15Max requests/sec per client
RATE_LIMIT_BURSTNo40Burst capacity per client

* Required only if running in single-tenant mode without BYOK.

Health check

bash
curl https://courtlistener-mcp.vaquill.ai/health# {"status":"healthy","service":"courtlistener-mcp","version":"..."}

Development

bash
uv sync --devuv run pytestuv run ruff format . && uv run ruff check .uv run mypy app/

Changelog

0.2.0

  • Added a full eCFR (federal regulations) tool suite (15 tools): titles, structure, versions, ancestry, source XML, agencies, corrections, and full-text regulation search + analytics. This is the differentiator over CourtListener-only servers.
  • Fixed a validation crash: optional search filters are now nullable (str | None), so clients that send explicit JSON null no longer get a ValidationError (previously broke search_dockets / search_recap_documents).
  • Real pagination: removed the no-op hit param; search tools now honor limit and expose a next_cursor token plus an input cursor.
  • Read-only tool annotations on all tools (better client UX, no write prompts).
  • Per-client rate limiting middleware (configurable, on by default).
  • Migrated import_server → mount (FastMCP 3), fixed the API-key env-var alias, refreshed project metadata, and got the test suite green (unit tests mocked; live-API tests gated behind RUN_INTEGRATION=1).

Credits & License

CourtListener data is provided by the Free Law Project under their respective terms. eCFR data is from ecfr.gov.

Community

Questions, ideas, or want to contribute? Join the Vaquill community on Discord.

来源:README.md,提交 9078d09

工具

34

status

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

无需输入参数。

search_opinions

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

输入参数q必填courtjudgelimitcursorcited_gtcited_ltorder_bycase_namefiled_afterfiled_before

search_dockets

Search federal cases (dockets) from PACER in CourtListener.

输入参数q必填courtlimitcursororder_bycase_nameparty_namedocket_numberdate_filed_afterdate_filed_before

search_dockets_with_documents

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.

输入参数q必填courtlimitcursororder_bycase_nameparty_namedocket_numberdate_filed_afterdate_filed_before

search_recap_documents

Search federal filing documents from PACER in the RECAP archive.

输入参数q必填courtlimitcursororder_bycase_nameparty_namefiled_afterfiled_beforedocket_numberdocument_numberattachment_number

search_audio

Search oral argument audio recordings in CourtListener.

输入参数q必填courtjudgelimitcursororder_bycase_nameargued_afterargued_before

search_people

Search judges and legal professionals in the CourtListener database.

输入参数q必填namelimitcursorschoolorder_byappointed_byposition_typeselection_methodpolitical_affiliation

get_opinion

Get a specific court opinion by ID from CourtListener.

输入参数opinion_id必填

get_docket

Get a specific court docket by ID from CourtListener.

输入参数docket_id必填

get_audio

Get oral argument audio information by ID from CourtListener.

输入参数audio_id必填

get_cluster

Get an opinion cluster by ID from CourtListener.

输入参数cluster_id必填

get_person

Get judge or legal professional information by ID from CourtListener.

输入参数person_id必填

get_court

Get court information by ID from CourtListener.

输入参数court_id必填

citation_lookup_citation

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

输入参数citation必填

citation_batch_lookup_citations

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.

输入参数citations必填

citation_verify_citation_format

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.

输入参数citation必填

citation_parse_citation_with_citeurl

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

输入参数broadcitation必填

citation_extract_citations_from_text

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).

输入参数text必填

citation_enhanced_citation_lookup

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.

输入参数citation必填include_courtlistener

ecfr_list_titles

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

无需输入参数。

ecfr_get_title_versions

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

输入参数title必填

ecfr_get_title_structure

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

输入参数date必填title必填

ecfr_get_ancestry

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

输入参数date必填parttitle必填section

ecfr_get_source_xml

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``.

输入参数date必填parttitle必填chaptersectionsubpartappendixsubtitlesubchapter

ecfr_list_agencies

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

无需输入参数。

ecfr_list_all_corrections

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

输入参数datetitle

ecfr_list_corrections_by_title

List all corrections for a single CFR title.

输入参数title必填

ecfr_search_regulations

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

输入参数datepageorderquery必填titleper_pageagency_slugs

ecfr_get_search_count

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

输入参数datequery必填titleagency_slugs

ecfr_get_search_summary

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

输入参数datequery必填titleagency_slugs

ecfr_get_title_search_counts

Get search result counts broken down by CFR title.

输入参数datequery必填

ecfr_get_daily_search_counts

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

输入参数datequery必填

ecfr_get_hierarchy_search_counts

Get search result counts distributed across the CFR hierarchy.

输入参数datequery必填

ecfr_get_search_suggestions

Get search-term suggestions for a partial CFR query.

输入参数query必填

版本历史

1
  1. v0.1.0最新Sep 16, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分