[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_134":135},"routes/modules.$creator.$moduleId",{"_14":15,"_16":17,"_18":19,"_20":21},"routes/modules.$creator.$moduleId.endpoints",{"_11":12,"_13":-5},"error","Module not found","tools","module",{"_20":22,"_23":24,"_25":26,"_27":28,"_29":30,"_31":32,"_33":34,"_35":26,"_36":37,"_38":-5,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":53,"_54":55,"_56":-5,"_57":49,"_58":59,"_60":61,"_62":63,"_64":65,"_66":67,"_68":69,"_70":71,"_72":73,"_74":75,"_76":77,"_78":79,"_80":-5,"_81":-5,"_82":-5,"_83":49,"_84":-5,"_85":86,"_87":88,"_89":90,"_91":92,"_93":94,"_95":96,"_97":98},"apiUrl","https://odel.app/api","creator","cyanheads","moduleId","courtlistener-mcp-server","@cyanheads/courtlistener-mcp-server","displayName","courtlistener mcp server","tagline","Search US court opinions, federal dockets, judges, citations, and oral arguments via CourtListener.","iconKey","https://avatars.githubusercontent.com/u/10339515?v=4","category","remote","status","published","visibility","public","metaDescription","deploymentType","external","workerName","bindingName","mcpConfig","{\"url\":\"https://courtlistener.caseyjhand.com/mcp\",\"transport\":\"streamable-http\",\"authType\":\"none\"}","pricingModel","free","creatorUserId","system:external-import","createdAt",1781363414000,"updatedAt",1788329526000,"sourceRegistry","official-mcp-registry","sourceUrl","https://registry.modelcontextprotocol.io/v0/servers?search=io.github.cyanheads%2Fcourtlistener-mcp-server","sourceVerified",true,"sourceMissingSince","importedAt","upstreamStars",2,"upstreamUpdatedAt",1787636478000,"detectedTransport","streamable-http","detectedAuthType","none","probeStatus","ok","lastProbedAt",1787476968000,"githubRepoUrl","https://github.com/cyanheads/courtlistener-mcp-server","githubRepoFullName","cyanheads/courtlistener-mcp-server","releaseId","ext-cyanheads-courtlistener-mcp-server","version","0.7.1","descriptionMarkdown","

@cyanheads/courtlistener-mcp-server

Search and retrieve US court opinions, federal dockets, judge records, citation networks, and oral arguments from CourtListener's 9M+ opinion corpus via MCP. STDIO or Streamable HTTP.\n

14 Tools

\n\n

\n\n[![Version](https://img.shields.io/badge/Version-0.7.1-blue.svg?style=flat-square)](./CHANGELOG.md) [![License](https://img.shields.io/badge/License-Apache%202.0-orange.svg?style=flat-square)](./LICENSE) [![Docker](https://img.shields.io/badge/Docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white)](https://github.com/users/cyanheads/packages/container/package/courtlistener-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^2.0.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/courtlistener-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/courtlistener-mcp-server) [![TypeScript](https://img.shields.io/badge/TypeScript-^7.0.2-3178C6.svg?style=flat-square)](https://www.typescriptlang.org/) [![Bun](https://img.shields.io/badge/Bun-v1.4.0-blueviolet.svg?style=flat-square)](https://bun.sh/)\n\n

\n\n

\n\n[![Install in Claude Desktop](https://img.shields.io/badge/Install_in-Claude_Desktop-D97757?style=for-the-badge&logo=anthropic&logoColor=white)](https://github.com/cyanheads/courtlistener-mcp-server/releases/latest/download/courtlistener-mcp-server.mcpb) [![Install in Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=courtlistener-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvY291cnRsaXN0ZW5lci1tY3Atc2VydmVyIl19) [![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_Server-0098FF?style=for-the-badge&logo=visualstudiocode&logoColor=white)](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22courtlistener-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fcourtlistener-mcp-server%22%5D%7D)\n\n[![Framework](https://img.shields.io/badge/Built%20on-@cyanheads/mcp--ts--core-67E8F9?style=flat-square)](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)\n\n

\n\n

\n\n**Public Hosted Server:** [https://courtlistener.caseyjhand.com/mcp](https://courtlistener.caseyjhand.com/mcp)\n\n

\n\n---\n\n## Tools\n\n14 tools spanning the full CourtListener dataset — opinion search and retrieval, citation network traversal, federal docket lookup, party and attorney lookup, judge biography, judicial financial disclosure search and detail, court discovery, and oral argument search and detail:\n\n| Tool | Description |\n|:---|:---|\n| `courtlistener_search_opinions` | Full-text search across 9M+ written court opinions with field-level filtering, date ranges, status, and sort |\n| `courtlistener_get_opinion` | Fetch full text and metadata for an opinion cluster — returns all opinion variants (majority, concurrence, dissent) |\n| `courtlistener_get_citations` | Retrieve the citation network for an opinion: opinions cited by it (`citing`) or that cite it (`cited_by`) |\n| `courtlistener_lookup_citation` | Resolve legal citations (e.g., \"410 U.S. 113\") to cluster IDs and case metadata — one entry per citation found in the input |\n| `courtlistener_search_dockets` | Search RECAP federal court dockets by party name, attorney, court, and date |\n| `courtlistener_get_docket` | Fetch docket metadata and entry list for a single federal case |\n| `courtlistener_get_parties` | Fetch all parties and attorneys of record for a RECAP federal docket by docket ID |\n| `courtlistener_search_judges` | Search judge records by name, appointing president, court, and political affiliation |\n| `courtlistener_get_judge` | Fetch full biographical profile, appointment history, and education for a single judge |\n| `courtlistener_lookup_courts` | List courts filtered by jurisdiction type, active/inactive status, and scraper coverage |\n| `courtlistener_search_oral_arguments` | Search appellate oral argument audio recordings by case name, court, and date argued |\n| `courtlistener_get_oral_argument` | Fetch full detail for a single oral argument — panel, duration, MP3 link, and speech-to-text transcript |\n| `courtlistener_search_financial_disclosures` | Search federal judicial financial disclosure filings by judge and year — category counts, itemized gifts, and source PDF |\n| `courtlistener_get_financial_disclosure` | Fetch one disclosure's parsed line items — investments, debts, positions, income, gifts — with coded values decoded to dollar ranges; selectable by category |\n\n### `courtlistener_search_opinions`\n\nSearch the 9M+ opinion corpus. Returns opinion cluster summaries with matched text excerpts.\n\n- Free-text queries with field syntax: `caseName:`, `court_id:`, `judge:`, `docketNumber:`, `cites:(id)`, boolean `AND / OR / NOT`\n- Filter by court ID, date range, publication status (Published / Unpublished / In-chambers, etc.)\n- Sort by relevance score, filing date (asc/desc), or citation count\n- Cursor-based pagination; up to 20 results per call\n- Results include `cluster_id` (for `courtlistener_get_opinion`) and `docket_id` (for `courtlistener_get_docket`) for chaining\n- Each cluster carries its `opinions[]` variants — per-variant opinion ID, type, author, outbound cites, and a CourtListener-hosted `local_path` copy of the source document\n- `snippet` is the matched excerpt from the first variant that carries one; CourtListener does not mark which variant the search matched\n\n---\n\n### `courtlistener_get_opinion`\n\nFetch full text and metadata for an opinion cluster.\n\n- A cluster groups all opinions filed in a case: majority, concurrence, dissent, per curiam\n- Returns `html_text` and `plain_text` for each opinion variant; surfaces `download_url` when local text is absent\n- Each variant carries `type_label` — the same value `courtlistener_search_opinions` reports (`lead-opinion`, `concurrence-opinion`, `dissent`) — beside the stored `type` code, whose numeric prefix is a sort key\n- Includes `cites[]` (outbound citation IDs), `cite_count`, syllabus, posture, and docket link\n- Three upstream requests — the cluster, its opinion variants, and the linked docket for court and docket number — kept within the tight free-tier rate limit\n\n---\n\n### `courtlistener_get_citations`\n\nRetrieve the citation network for an opinion cluster in either direction.\n\n- `cited_by` (default): opinions that cite this one — measures precedential influence and downstream adoption\n- `citing`: opinions this one cites — reveals the authority chain the court relied on\n- Optional court and date filters; up to 20 results per call\n- Pagination differs by direction: `cited_by` follows CourtListener's own cursor with the filters applied, so its total and its pages describe the same set; `citing` walks the cited-opinion list and filters each page as it goes, so a filtered page can come back empty with matches still ahead — the response distinguishes that from an exhausted network\n- Results include `snippet`, the matched excerpt from the related opinion — a relevance preview for the cluster, not necessarily the text surrounding the citation\n- Rate-limit note: three upstream requests per call in either direction; the free tier supports 1–2 hops on a single case, and deep multi-hop traversal exhausts the daily budget quickly\n\n---\n\n### `courtlistener_lookup_citation`\n\nResolve legal citations to opinion cluster IDs.\n\n- Accepts standard reporter formats: \"410 U.S. 113\", \"347 U.S. 483\", \"93 S. Ct. 705\"\n- Returns `matches`, one entry per citation CourtListener extracted from the input — pass a passage and every citation in it resolves, each with its own `status` (200 one case, 300 several candidates, 400 unrecognized reporter, 404 no match) and decoded `status_label`\n- Each match carries the cases it resolved to: `cluster_id`, `case_name`, `court` / `court_id`, `court_resolution`, `docket_id`, `date_filed`, all known citation strings, `cite_count`, `precedential_status`, and `judges`\n- An unresolved or ambiguous citation comes back inside `matches`, not as an error — only text carrying no parseable citation at all fails\n- `court` is absent from the citation-lookup payload (the court lives on the linked docket), so it is resolved from `docket_id` — one extra request per distinct docket, bounded by `max_court_lookups` (default 4, up to 20; 0 skips court resolution). `court_resolution` (`resolved` / `no_docket` / `lookup_failed` / `over_budget`) says why a court is or isn't populated — only `over_budget` is worth retrying with a larger budget\n- One upstream POST to `/citation-lookup/` plus those court lookups, issued sequentially and stopped early on the first rate-limited response. The endpoint requires authentication and has no unauthenticated path\n\n---\n\n### `courtlistener_search_dockets`\n\nSearch RECAP federal court dockets.\n\n- Query matched against case name, docket number, party names, and attorney names\n- `party_name` filter applies in addition to (AND with) the `q` query — more precise than embedding party names in the query\n- Returns the docket's `parties`, `attorneys`, and `firms`, plus nature of suit, jurisdiction type, and the referred magistrate judge\n- Returns up to 3 sample document entries per docket — a search excerpt, not the full filing list — each with `is_available` status, page count, and a fully-qualified RECAP storage URL when a copy is stored\n- `coverage_note` in every response — RECAP is crowd-sourced from PACER; completeness varies by court\n\n---\n\n### `courtlistener_get_docket`\n\nFetch full docket metadata and entry list for a single federal case.\n\n- Returns all available docket entries with document availability, page count, and RECAP file path\n- `entries_page_size` controls how many entries are returned (1–50); large cases have hundreds\n- Documents with `is_available: false` require a PACER account or CourtListener RECAP filing — document retrieval is not exposed\n\n---\n\n### `courtlistener_get_parties`\n\nFetch all parties and attorneys of record for a RECAP federal docket.\n\n- Returns each party's name, docket-scoped role (Plaintiff, Defendant, Petitioner, Respondent, etc.), and the attorneys of record on this docket with contact information\n- Attorney roles are decoded to labels (`Lead attorney`, `Terminated`, …) alongside the raw code, with the date a relationship ended\n- Attorney names and contact details are resolved from the docket's attorney roster — 2 upstream requests per invocation, plus one for each extra roster page on a docket with a large attorney list\n- Paginate large party lists by passing a response's `next_cursor` back as `cursor` — this endpoint is cursor-paginated, so there is no page number to increment; `page_size` (max 10) is a request only, and CourtListener paginates at a fixed size that can return more parties than asked for\n- Obtain docket IDs from `courtlistener_search_dockets` or `courtlistener_get_docket`\n\n---\n\n### `courtlistener_search_judges`\n\nSearch judge and person records across the federal and state bench.\n\n- Filter by appointing president's last name, court ID, or political affiliation (`d/r/i/l/g/u`)\n- Returns `person_id` for chaining to `courtlistener_get_judge`, plus a `current_position` summary — court, position type, appointer, selection method, and start date — selected as the position with no termination date, or the latest-starting one when several or none qualify\n- Political affiliations and ABA ratings come back as expanded labels (\"Democratic\", \"Well Qualified\"), not the codes the `political_affiliation` filter takes\n- Court IDs from `courtlistener_lookup_courts` can be passed directly\n\n---\n\n### `courtlistener_get_judge`\n\nFetch a judge's full biographical profile.\n\n- Position history: all courts served, position type, appointer, nomination date, confirmation date, termination reason — plus non-judicial roles, which carry no court and describe themselves in `job_title` and `organization_name`. `/positions/` is cursor-walked under a page bound; a `truncated` notice and `positionsShown`/`truncated` fields report when a long career ran past it\n- Position type, termination reason, and degree level come back decoded (`position_type_label`, `termination_reason_label`, `degree_label`) alongside the raw codes CourtListener's own filters take\n- Birth, death, and position dates carry the precision CourtListener recorded — `dob_granularity` and the per-position `date_start_granularity` read `year`, `month`, or `day`, and a year-only record renders as the year rather than the stored `YYYY-01-01` placeholder\n- Education records with school, degree, and year\n- Political affiliations with date ranges; ABA ratings; Federal Judicial Center ID for cross-referencing\n\n---\n\n### `courtlistener_lookup_courts`\n\nList courts with optional jurisdiction and scraper filters.\n\n- Jurisdiction codes mirror CourtListener's own `Court.JURISDICTIONS` — federal appellate (`F`), federal district (`FD`), federal bankruptcy (`FB`), state supreme (`S`), state appellate (`SA`), plus the tribal, territory, and military benches. The full table is in the `courtlistener://reference/courts` resource\n- `status` selects which bench to return: `active` (the default) only the courts CourtListener still scrapes, `inactive` only the historical and defunct ones, `any` both. Upstream filters these as disjoint sets, so `any` is the only value that reaches the whole list\n- `has_opinion_scraper` filter useful for planning opinion searches — courts without scrapers have sparse coverage\n- Returns `id` (the `court_id` string for use in all search and filter parameters), citation string (e.g., \"9th Cir.\"), and jurisdiction code\n- Page-number paginated at a **fixed 20 rows per page** — `/courts/` ignores any requested page size, so there is no way to pull a larger page. Enumerating a whole bench costs one call per 20 courts against a rate-limited free tier, and the inactive bench is several times larger than the active one: `status: 'any'` makes the full set reachable, not cheap. Filter by `jurisdiction` to answer a question in one call; pass a response's `next_cursor` back as `page` when you genuinely need to walk\n- `all_matching_court_ids` returns the complete filtered id set from a bundled snapshot of every CourtListener court, at no request cost — covers the default bench and every jurisdiction filter. Empty (not a truncated prefix) when more than 1,000 courts match; check `all_matching_court_ids_complete` before reading emptiness as \"no courts match\". The live `courts` page stays authoritative for full records\n\n---\n\n### `courtlistener_search_oral_arguments`\n\nSearch appellate oral argument audio recordings — the largest public collection of oral argument audio.\n\n- Query matched against case name and transcribed argument text (where available)\n- Filters by court, argued-after, and argued-before date\n- Returns two MP3 links per recording — `download_url` at the originating court, and `local_path`, CourtListener's durable hosted copy — plus `duration_seconds`, `panel_ids` (chaining to `courtlistener_get_judge`), and transcript `snippet`\n\n---\n\n### `courtlistener_get_oral_argument`\n\nFetch the full detail record for a single oral argument by audio ID.\n\n- Returns the speech-to-text `transcript` when transcription has completed, plus `panel_ids`, `duration_seconds`, MP3 `download_url`, and the linked `docket_id`\n- Audio IDs come from `courtlistener_search_oral_arguments` results\n- The argument date is not on this record — take it from the search result or the linked docket\n\n---\n\n### `courtlistener_search_financial_disclosures`\n\nSearch federal judicial financial disclosure filings for ethics and recusal research.\n\n- Filter by `judge_id` (a `person_id` from `courtlistener_search_judges`) and/or filing `year`\n- The `year` filter is applied to the fetched page only — CourtListener has no server-side year filter, so filings for that year on later pages are not included; page through with `cursor` (the response returns `next_cursor` even when the current page has no year match)\n- Returns per-filing category counts (investments, gifts, debts, positions, reimbursements, income), itemized gifts, and a link to the source PDF\n- Line-item investments — often hundreds per filing, with coded values — are summarized as counts; the linked PDF carries the full itemization\n\n---\n\n### `courtlistener_get_financial_disclosure`\n\nFetch one disclosure's parsed line items in full — the itemized companion to the search tool.\n\n- Keyed by `disclosure_id` (from a `courtlistener_search_financial_disclosures` result); one upstream call returns every category inline\n- Returns filing metadata, per-category counts, and the requested line-item rows — investments, debts, positions, reimbursements, non-investment and spouse income, agreements, and gifts\n- Coded income/value columns are decoded to readable dollar ranges (e.g. `N` → `$250,001 - $500,000`)\n- Pass `categories: [...]` to select specific categories; omit for all. When the full itemization is too large to inline, the response returns an outline of categories by size — re-call with `categories: [...]` to pull specific ones in full\n\n## Features\n\nBuilt on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):\n\n- Declarative tool definitions — single file per tool, framework handles registration and validation\n- Unified error handling across all tools\n- Pluggable auth (`none`, `jwt`, `oauth`)\n- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`\n- Structured logging with optional OpenTelemetry tracing\n- STDIO and Streamable HTTP transports\n\nCourtListener-specific:\n\n- Complete CourtListener REST API v4 integration — opinions, dockets, judges, courts, oral arguments, citation network\n- Rate-limit-aware client: 429 responses classified by window (minute / hour / day) with actionable error messages; retry with Retry-After respect\n- Pagination matched to each endpoint's own paginator — cursor-based on the `/search/`-backed tools and on parties/attorneys, page-number on the courts and docket-entry lists — with continuation surfaced on every response\n- RECAP coverage note surfaced on every docket response — sets expectations on partial PACER mirror completeness\n- Tight upstream-call budget — most tools make 1–2 calls; opinion detail and citation traversal make three (resolving the linked docket, or the source cluster's opinion variants), plus one per extra page of variants on a case that filed many. Citation lookup is the ceiling at five, resolving up to four distinct dockets for their courts\n\nAgent-friendly output:\n\n- Chaining IDs on every response — `cluster_id`, `docket_id`, and `person_id` fields are present wherever they enable a logical follow-up call, with field-level descriptions naming which tool to pass them to\n- Discriminated rate-limit errors — minute / hour / day throttle identified in structured error so agents can reason about retry timing, not just \"try again later\"\n- Coverage caveats inline — RECAP `coverage_note` and oral argument transcript `snippet` availability explicitly signaled so agents can communicate limitations to users rather than silently omitting them\n\n## Getting started\n\n### Public Hosted Instance\n\nA public instance is available at `https://courtlistener.caseyjhand.com/mcp` — no installation required. Point any MCP client at it via Streamable HTTP:\n\n```json\n{\n \"mcpServers\": {\n \"courtlistener-mcp-server\": {\n \"type\": \"streamable-http\",\n \"url\": \"https://courtlistener.caseyjhand.com/mcp\"\n }\n }\n}\n```\n\n### Self-Hosted / Local\n\nAdd the following to your MCP client configuration file. See [CourtListener account settings](https://www.courtlistener.com/profile/settings/) to generate a free API token.\n\n```json\n{\n \"mcpServers\": {\n \"courtlistener-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"bunx\",\n \"args\": [\"@cyanheads/courtlistener-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"COURTLISTENER_API_TOKEN\": \"your-api-token\"\n }\n }\n }\n}\n```\n\nOr with npx (no Bun required):\n\n```json\n{\n \"mcpServers\": {\n \"courtlistener-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@cyanheads/courtlistener-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"COURTLISTENER_API_TOKEN\": \"your-api-token\"\n }\n }\n }\n}\n```\n\nOr with Docker:\n\n```json\n{\n \"mcpServers\": {\n \"courtlistener-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\", \"-i\", \"--rm\",\n \"-e\", \"MCP_TRANSPORT_TYPE=stdio\",\n \"-e\", \"COURTLISTENER_API_TOKEN=your-api-token\",\n \"ghcr.io/cyanheads/courtlistener-mcp-server:latest\"\n ]\n }\n }\n}\n```\n\nFor Streamable HTTP, set the transport and start the server:\n\n```sh\nMCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 COURTLISTENER_API_TOKEN=... bun run start:http\n# Server listens at http://localhost:3010/mcp\n```\n\n### Prerequisites\n\n- [Bun v1.3.2](https://bun.sh/) or higher (or Node.js v24+).\n- A CourtListener API token — free account at [courtlistener.com](https://www.courtlistener.com/sign-in/). CourtListener publishes free-tier limits of 5 req/min, 50 req/hr, 125 req/day; actual limits vary by token tier. [Free Law Project membership](https://free.law/donate/) unlocks higher limits.\n\n### Installation\n\n1. **Clone the repository:**\n\n```sh\ngit clone https://github.com/cyanheads/courtlistener-mcp-server.git\n```\n\n2. **Navigate into the directory:**\n\n```sh\ncd courtlistener-mcp-server\n```\n\n3. **Install dependencies:**\n\n```sh\nbun install\n```\n\n4. **Configure environment:**\n\n```sh\ncp .env.example .env\n# edit .env and set COURTLISTENER_API_TOKEN\n```\n\n## Configuration\n\nAll configuration is validated at startup via Zod schemas in `src/config/server-config.ts`. Key environment variables:\n\n| Variable | Description | Default |\n|:---------|:------------|:--------|\n| `COURTLISTENER_API_TOKEN` | **Required.** API token from your CourtListener account settings. CourtListener's published free-tier limits are 5 req/min, 50/hr, 125/day; actual limits vary by token tier. | — |\n| `COURTLISTENER_BASE_URL` | API base URL override. | `https://www.courtlistener.com/api/rest/v4` |\n| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |\n| `MCP_SESSION_MODE` | HTTP session handling: `stateless`, `stateful`, or `auto` (resolves to `stateful`). The published Docker image ships `stateless`. | `auto` |\n| `MCP_HTTP_PORT` | HTTP server port. | `3010` |\n| `MCP_HTTP_ENDPOINT_PATH` | HTTP endpoint path. | `/mcp` |\n| `MCP_PUBLIC_URL` | Public origin for TLS-terminating reverse-proxy deployments. | — |\n| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |\n| `MCP_LOG_LEVEL` | Log level (`debug`, `info`, `warning`, `error`, etc.). | `info` |\n| `MCP_GC_PRESSURE_INTERVAL_MS` | Opt-in Bun-only forced-GC pressure loop (ms). Try `60000` if RSS grows under sustained HTTP load. | `0` |\n| `LOGS_DIR` | Directory for log files (Node.js only). | `/logs` |\n| `STORAGE_PROVIDER_TYPE` | Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1`. | `in-memory` |\n| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |\n\nSee [`.env.example`](https://github.com/cyanheads/courtlistener-mcp-server/blob/main/.env.example) for the full list of optional overrides.\n\n## Running the server\n\n### Local development\n\n- **Build and run:**\n\n ```sh\n # One-time build\n bun run rebuild\n\n # Run the built server\n bun run start:stdio\n # or\n bun run start:http\n ```\n\n- **Run checks and tests:**\n\n ```sh\n bun run devcheck # Lint, format, typecheck, security\n bun run test # Vitest test suite\n bun run lint:mcp # Validate MCP definitions against spec\n ```\n\n### Docker\n\n```sh\ndocker build -t courtlistener-mcp-server .\ndocker run --rm -e COURTLISTENER_API_TOKEN=your-token -p 3010:3010 courtlistener-mcp-server\n```\n\nThe Dockerfile defaults to HTTP transport, stateless session mode, and logs to `/var/log/courtlistener-mcp-server`. OpenTelemetry peer dependencies are installed by default — build with `--build-arg OTEL_ENABLED=false` to omit them.\n\n## Project structure\n\n| Directory | Purpose |\n|:----------|:--------|\n| `src/index.ts` | `createApp()` entry point — registers tools and inits services. |\n| `src/config` | Server-specific environment variable parsing and validation with Zod. |\n| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). 14 tools across opinions, citations, dockets, parties, judges, financial disclosures, courts, and oral arguments. |\n| `src/services/courtlistener` | CourtListener REST API client — auth, retry, rate-limit error classification. |\n| `tests/` | Unit and integration tests mirroring `src/`. |\n\n## Development guide\n\nSee [`CLAUDE.md`](https://github.com/cyanheads/courtlistener-mcp-server/blob/main/CLAUDE.md) for development guidelines and architectural rules. The short version:\n\n- Handlers throw, framework catches — no `try/catch` in tool logic\n- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage\n- Register new tools by importing them in `src/index.ts` and adding to the `createApp({ tools: [...] })` array\n- Wrap CourtListener API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields\n\n## Contributing\n\nIssues and pull requests are welcome. Run checks and tests before submitting:\n\n```sh\nbun run devcheck\nbun run test\n```\n\n## License\n\nApache-2.0 — see [LICENSE](https://github.com/cyanheads/courtlistener-mcp-server/blob/main/LICENSE) for details.\n","changelogMarkdown","videoKey","requiredSecretsJson","publishedAt","priceCents","trialDays",0,"iconType","image","upstream",{"_114":115,"_116":117,"_118":119,"_120":121,"_122":123,"_124":125},"requiredSecrets",[],"tags",[101,102,103,104,105,106,19,107,108,109,110,111,112,113],"assets",[],"stats",{"_99":86,"_100":86},"ratingAvg","reviewCount","ai-agents","ai-tools","case-law","citation-network","court-opinions","courtlistener","federal-courts","judges","legal","legal-research","pacer","recap","typescript","topics",[101,102,103,104,105,106,19,107,108,109,110,131,132,133,111,112,113],"license","Apache-2.0","language","TypeScript","registryName","io.github.cyanheads/courtlistener-mcp-server","homepage","https://www.npmjs.com/package/@cyanheads/courtlistener-mcp-server","packages",[126,127],{"_128":129,"_130":22,"_76":77},{"_128":129,"_130":22,"_76":77},"registryType","npm","identifier","mcp","mcp-server","model-context-protocol","ENV",{"_136":137,"_138":139,"_140":141},"ENVIRONMENT","production","TURNSTILE_SITE_KEY","0x4AAAAAAB8-rEI2gNDf_QhU","SENTRY_DSN","https://45fd1229f78089d5c3ee78be128030e1@o4510583261757440.ingest.de.sentry.io/4510584253448272"]