mcp-courtwatch

MCP server for free U.S. case-law and court-docket search, over CourtListener (the Free Law Project's open legal database). Built for legal-aid orgs, tenant-defense and pro-se litigants, and public-interest lawyers who cannot afford Westlaw or PACER.

It wraps CourtListener's REST API v4, normalizing the raw JSON (caseName, dateFiled, cluster_id, docket_absolute_url, and so on) into clean, documented tool outputs.

Tools

order_by for opinion_search is one of relevance (default), newest, oldest, most_cited. Court jurisdiction codes include F (federal appellate and other), FD (federal district), FB (bankruptcy), S (state), SA (state appellate), SS (state supreme).

Related MCP server: courtlistener-mcp

Data source

• Base URL: https://www.courtlistener.com/api/rest/v4

• Auth: a free API token, sent as the header Authorization: Token <token>.

• Envelope: search and list endpoints return the DRF shape { count, next, previous, results: [...] }. /search/ paginates by opaque cursor; the list endpoints (/courts/, /people/) paginate by page number (?page=N). Detail endpoints return a bare object. POST /citation-lookup/ returns a bare JSON array (one item per citation recognized in the text).

• Access: /search/, /courts/, and /people/ answer without a token at a low rate limit, so those tools attach the token only when it is set (a token raises the limit). /clusters/{id}/, /opinions/{id}/, and POST /citation-lookup/ return HTTP 401 without a token, so case_detail and citation_lookup require one.

• Citation-lookup limits (server-side): text max 64,000 characters (enforced pre-flight here with a clear error; the tool never truncates, since a dropped tail would mean unchecked citations); the first 250 citations per call are looked up and any beyond that come back flagged per-item as not checked; rate limit 60 citations/min.

Sources:

• REST API v4 overview and auth: https://www.courtlistener.com/help/api/rest/ (redirects to https://wiki.free.law/c/courtlistener/help/api/rest/v4/overview)

• Search API (params, type enum, response fields): https://www.courtlistener.com/help/api/rest/search/ (redirects to https://wiki.free.law/c/courtlistener/help/api/rest/v4/search)

• Case Law API (clusters, opinions): https://www.courtlistener.com/help/api/rest/case-law/ (redirects to https://wiki.free.law/c/courtlistener/help/api/rest/v4/case-law)

• Citation Lookup API: https://www.courtlistener.com/help/api/rest/citation-lookup/ (redirects to https://wiki.free.law/c/courtlistener/help/api/rest/v4/citation-lookup), plus the endpoint's source in the CourtListener repo: cl/citations/api_views.py and api_serializers.py (request/response fields, per-citation status codes) and cl/settings/project/citations.py (the 250-citations-per-request cap). The endpoint returns HTTP 401 without a token.

• The live API itself, for the search / courts / people field names: /search/?type=o, /search/?type=r, /courts/, /people/ (all answer unauthenticated GETs).

Field map (CourtListener to normalized output)

Install

No build step. Runs directly on tsx.

git clone https://github.com/haksanlulz/mcp-courtwatch.git
cd mcp-courtwatch
npm install

API token

case_detail and citation_lookup need a free CourtListener token, and the other tools run faster (higher rate limit) with one. Create a free account, open Profile then the API page, and copy the token. Docs: https://www.courtlistener.com/help/api/rest/

Expose it as COURTLISTENER_API_TOKEN:

export COURTLISTENER_API_TOKEN=your-token-here   # macOS / Linux
setx COURTLISTENER_API_TOKEN your-token-here      # Windows (new shells)

Without the token, opinion_search, docket_lookup, court_list, and judge_lookup still work at CourtListener's unauthenticated rate limit. case_detail and citation_lookup return a clear error telling you to set the token. The token is never logged.

MCP client config

Point your MCP client at index.ts via tsx. Use an absolute path.

{
  "mcpServers": {
    "courtwatch": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/mcp-courtwatch/index.ts"],
      "env": { "COURTLISTENER_API_TOKEN": "your-token-here" }
    }
  }
}

Example

Call opinion_search with { "q": "warrantless search", "court": "scotus", "order_by": "most_cited", "limit": 1 }:

{
  "query": { "q": "warrantless search", "court": "scotus", "filed_after": null, "filed_before": null, "order_by": "most_cited" },
  "total_matches": 161,
  "returned": 1,
  "results": [
    {
      "case_name": "Illinois v. Gates",
      "court": "Supreme Court of the United States",
      "court_id": "scotus",
      "date_filed": "1983-06-08",
      "citations": ["76 L. Ed. 2d 527", "103 S. Ct. 2317", "462 U.S. 213", "1983 U.S. LEXIS 54", "51 U.S.L.W. 4709"],
      "docket_number": "81-430",
      "cite_count": 16741,
      "status": "Published",
      "snippet": "Justice White, concurring in the judgment. In my view, the question regarding modification of the exclusionary rule ...",
      "cluster_id": 110959,
      "docket_id": 638808,
      "absolute_url": "https://www.courtlistener.com/opinion/110959/illinois-v-gates/"
    }
  ]
}

Then pass the cluster_id to case_detail ({ "id": 110959 }) for the citations, judges, and opinion ids, or case_detail with { "id": <opinion id>, "type": "opinion" } for the full opinion text.

Example: verifying citations before filing

Courts have sanctioned filings built on citations that do not exist. A legal-aid worker or a pro-se litigant can run a draft's citations through citation_lookup before anything reaches a judge:

Call citation_lookup with { "text": "Tenants are protected here. See Roe v. Wade, 410 U.S. 113 (1973); Smith v. Imaginary, 999 U.S. 9999 (2099)." }:

{
  "query": { "text_chars": 107 },
  "citations_checked": 2,
  "found": 1,
  "not_found": 1,
  "invalid": 0,
  "not_checked": 0,
  "all_verified": false,
  "warning": "1 of 2 citation(s) did NOT verify: 1 not found in CourtListener (likely fabricated or mis-cited). Do not cite unverified authorities — check them by hand before filing.",
  "results": [
    {
      "citation": "410 U.S. 113",
      "verified": true,
      "verdict": "FOUND",
      "status": 200,
      "error_message": null,
      "normalized_citations": ["410 U.S. 113"],
      "start_index": 45,
      "end_index": 57,
      "matches": [
        {
          "cluster_id": 108713,
          "case_name": "Roe v. Wade",
          "date_filed": "1973-01-22",
          "citations": ["410 U.S. 113", "93 S. Ct. 705", "35 L. Ed. 2d 147"],
          "precedential_status": "Published",
          "citation_count": 12030,
          "judges": "Blackmun",
          "docket_id": 4463,
          "absolute_url": "https://www.courtlistener.com/opinion/108713/roe-v-wade/"
        }
      ]
    },
    {
      "citation": "999 U.S. 9999",
      "verified": false,
      "verdict": "NOT_FOUND",
      "status": 404,
      "error_message": "Citation not found: '999 U.S. 9999'",
      "normalized_citations": ["999 U.S. 9999"],
      "start_index": 86,
      "end_index": 99,
      "matches": []
    }
  ]
}

The fabricated citation comes back NOT_FOUND with a top-level warning. Per-citation status mirrors the API's own codes: 200 found, 300 found with multiple matching clusters (FOUND_MULTIPLE — a real citation, ambiguous mapping), 400 unknown reporter, 404 not found, 429 past the 250-citations-per-call cap (NOT_CHECKED_OVER_CAP — split the text and re-run the rest). A lookup that recognizes zero citations says so in a note instead of pretending to have verified anything.

Caveats

Built without a token, so:

• The case_detail field names (cluster and opinion objects) come from the Case Law API docs plus the search-result shape, not from a live authenticated GET (the /clusters/ and /opinions/ endpoints return HTTP 401 without a token). The normalizer is defensive: unknown or missing values coerce to null (or empty arrays) rather than throwing, and citations accept either string or object form. Run npm run smoke with a real token to confirm these end to end.

• The citation_lookup response shape (per-citation fields, the 200/300/400/404/429 status codes, the serializer-level 64,000-char text cap, the 250-citation per-request cap) comes from the CourtListener source (cl/citations/api_views.py, api_serializers.py, cl/settings/project/citations.py) and the Citation Lookup docs, not from a live authenticated POST (the endpoint returns HTTP 401 without a token). The normalizer is defensive like the rest. Run npm run smoke with a token: it checks one real citation (410 U.S. 113, Roe v. Wade) plus one fabricated one and fails unless the real one resolves and the fake comes back NOT_FOUND.

• The clusters returned by citation_lookup do not include the court (in CourtListener's model the court hangs off the docket, not the cluster). For the court, follow the match's absolute_url or pass its cluster_id to case_detail and the docket_id onward. Deliberately not auto-fetched here: a 250-citation brief would fan out into hundreds of extra docket calls.

• docket_number is folded into the free-text q term rather than sent as a dedicated field, so matching is best-effort. If a known docket number under-returns, also pass the case name in q.

• court_list applies its q name filter across the full courts table, walked one page at a time server-side (the /courts/ endpoint ignores page_size, so the ~3,400 courts span ~170 pages of ~20 up to a safety cap). Scope by jurisdiction to page less; a token is recommended for the unfiltered full-table scan.

• opinion_search and docket_lookup return one fixed /search/ page of ~20 results; for more, pass the response's next_cursor back as the cursor argument. The endpoint ignores page_size, so limit cannot exceed one page (it is capped at 20 rather than advertising an unreachable number).

• The order_by values, the court / filed_after / filed_before filters, and the search / courts / people field names match the live API, as does the fixed ~20-row page size of /search/ and /courts/ (both ignore page_size). The token-gated behavior of case_detail is the main thing the keyed smoke should confirm.

Develop

npm test         # vitest, fetch mocked with the documented response shapes (no token needed)
npm run smoke    # one live call per tool (needs COURTLISTENER_API_TOKEN; skips cleanly without)
npm run typecheck

License

MIT. See LICENSE. Data from CourtListener / the Free Law Project (public court records and openly licensed legal data). Unofficial, not affiliated with CourtListener or the Free Law Project.