Claude Legal Research MCP: How to Use Claude for US Legal Research

To use Claude for legal research, connect it to a legal research MCP server. MCP (Model Context Protocol) lets Claude call live tools instead of guessing from training data, so it reads real statutory text and returns citations you can open and check. You add the server once (a connector or a short JSON config), then ask Claude legal questions in plain English. This guide shows the exact config and a real query, end to end.

Reviewed and corrected on 6 October 2026. This is general information, not legal advice; check the cited statute or opinion before relying on it.

Anthropic launched Claude for the legal industry on May 12, 2026, with 20+ new MCP connectors and 12 new plugins (Anthropic, May 12, 2026). Legal research is one of the headline use cases. The rest of this post is how to wire it up and what it looks like once it works.

Why Claude Hallucinates Citations Without MCP

Ask Claude what the Securities Exchange Act says about manipulative trading and you'll get a clean textbook answer. Ask it for the operative text of 17 C.F.R. § 240.10b5-1, subsection by subsection, with the affirmative-defense conditions in the order the rule lists them, and it falls apart.

It will hallucinate a section number, quote language from a version the agency superseded years ago, or attribute a state code section to the wrong state. The paraphrase is usually close. The citation under it is the part that gets you sanctioned.

This isn't Claude's fault. LLMs are trained on general web data. They don't have access to structured legal databases, and they certainly don't have access to the US Code, the CFR, and the state codes as addressable, current text.

But what if they could?

A Claude legal research MCP fixes this. You give Claude (or Cursor, or VS Code Copilot) an MCP server that exposes US primary-law tools, and you can use Claude for legal research without crossing your fingers on every cite.

When you ask what a provision says, Claude doesn't guess. It resolves the citation, pulls the published text, and hands back the government URL that text came from.

One clarification before we go further, because it shapes everything below. The public REST API and the vaquill-mcp server are statutes, regulations, and codes: the U.S. Code, the CFR, the statutory codes of the states and territories, the U.S. Constitution and state constitutions, the Federal Rules and state court rules, state administrative regulations, the Federal Register, federal and state agency guidance, Executive Orders, the Sentencing Guidelines, and US tax treaties. Plus a change-monitoring layer over all of it.

It is built for statutes and regulations by citation. For court opinions, pair it with a case-law connector; the comparison table below covers the options.

I'll walk you through the setup and show you what this looks like in practice. Five minutes, and you'll have Claude reading real law for you.

TL;DR

• Use Claude for legal research by connecting a legal research MCP server. LLMs invent citations because they have no real legal database behind them. MCP gives Claude live tools that read from one.
• Since the May 12, 2026 Claude for Legal launch, you can add many legal MCP connectors from Claude's built-in directory; for a self-hosted server, you edit one JSON config block (about two minutes).
• Connect the statutes server once and Claude can read more than 5M sections of US primary law on demand: the U.S. Code, the CFR, state statutory codes, constitutions, court rules, state regulations, the Federal Register, agency guidance, and Executive Orders.
• The tool list is generated from the live API spec, so it grows with the API. On 16 October 2026 the hosted server lists 26 tools, and every one of them is read-only: search, resolve a Bluebook citation, section text, neighboring sections, defined terms, browsing the hierarchy, coverage, and cross-state comparison.
• Every section comes back with the government URL it was published at, so you verify against the publisher rather than against us.
• Works in Claude Desktop, Claude Code, Cursor, and VS Code (Copilot).
• Built for statutes and regulations. For court opinions, add a case-law connector such as the CourtListener connector from Free Law Project.

Part of our MCP and developer guide series.

For related MCP / API / developer coverage, see Legal Research from Inside Cursor and Claude Code: The MCP Way and Adding Legal Research to Your AI Agent with MCP.

Why Use Claude for Legal Research (and Where It Breaks)

Claude is a strong reasoning engine, but on its own it has no idea whether the section it just quoted is real, current, or from the right jurisdiction. The fix is not a better prompt. It is giving Claude a tool that reads from an actual legal database.

The rest of this post is how to do that, and what it looks like once it works.

What is MCP?

MCP stands for Model Context Protocol. Anthropic released the spec in late 2024, and it has since been adopted across most major AI coding tools.

Think of MCP as a plugin system for LLMs. Instead of an AI assistant being limited to its training data and whatever you paste into the chat window, MCP lets it call external tools, fetch live data, and take actions on your behalf.

The AI sees a list of available tools with descriptions, decides which ones to call based on your question, and folds the results into its response.

It's the difference between an AI that knows about legal research and an AI that can actually do legal research.

Here is the loop, end to end. Claude reads your question, picks a tool, the MCP server queries a real legal database, and the citations flow back into the answer before Claude ever writes a word:

Two Ways to Connect a Legal Research MCP to Claude

There are two paths, and the launch in May 2026 added the first one.

1. The Claude connector directory (point and click). On May 12, 2026, Anthropic launched Claude for the legal industry with more than 20 MCP connectors, including legal-research providers (Anthropic, May 12, 2026). In Claude, open Customize > Connectors (Anthropic's docs call it the Connectors Directory), pick the provider, and authorize it. No config file. Some connectors need a paid account with that provider (for example, the CoCounsel Legal connector needs a Thomson Reuters subscription).

2. A custom connector or a local MCP server. Any MCP server, listed in the directory or not, can be added to Claude by its URL or wired into Claude Desktop, Claude Code, Cursor, or VS Code with a short config block. This is the path the rest of this guide uses, because the same server works in every client and you control the API key.

Which Legal Research MCP Connector Should You Use?

The May 12, 2026 launch put several legal research providers into Claude at once. They are not interchangeable. Some hand Claude raw API access to a database, some ride on a paid subscription you already have, and some cover statutes and regulations by citation. Pick by what you already pay for and what you need to read. Every row below comes from the provider's own page or Anthropic's announcement.

Anthropic's announcement also lists Descrybe (search cases by concept or citation, check treatment status, find citing authorities, verify quoted language), Harvey, Solve Intelligence and Lawve AI among the connectors.

How to choose: if you want free case law and dockets, start with the CourtListener connector. If your firm already runs on Westlaw, ask Thomson Reuters about CoCounsel Legal. If you need statutes and regulations by citation, with section-level text and change monitoring, that is what the Vaquill AI server is built for. MCP lets you attach several and let Claude choose. We wrote up how to run three of them side by side.

Case Law, Citations and "Is It Still Good Law?"

Can Claude search US court opinions? Yes, through a case-law connector. Anthropic's directory includes CourtListener, Midpage, Descrybe, CoCounsel Legal and others, and our CourtListener MCP guide walks through one. A statutes server reads statutes and regulations by citation, so for opinions use a connector built for them.

Can Claude tell me whether a case is still good law? Only as well as the source it is connected to. Free Law Project's connector offers citation verification and says a free citator is on its roadmap. Descrybe is described by Anthropic as able to "check treatment status". Anthropic describes CoCounsel Legal as grounded in Westlaw primary law, Practical Law guidance and KeyCite. Midpage describes a citator (Midpage, July 23, 2026) and its docs state that its treatment data is not a complete good-law check. Whichever you use, read the later history yourself before you cite a case. Our guide to using Claude for legal research covers the verification steps.

What You Get: The Research Tools

When you connect the MCP server, your AI assistant gets tools that read the corpus. Every one is read-only. You don't need to memorize any of this; Claude picks the tool from how you phrase the question.

But it helps to know what's available so you can ask better questions.

The list is not hardcoded in the package. The server fetches the live API spec at startup and generates its tools from it, so a new endpoint shows up without a package upgrade. On 16 October 2026 the hosted US server lists 26 tools, all read-only. Read the list your client shows rather than trusting a number in a blog post. The server also appends each tool's current credit cost to that tool's own description, pulled from the pricing endpoint, so what Claude sees is what you're charged.

The tools that read the corpus

Search US primary law (search_us_statutes): Hybrid semantic and keyword search across everything at once, or narrowed with corpusType and state. The corpora are the U.S. Code, the CFR, the statutory codes of the states and territories, the U.S. Constitution and the state constitutions, the Federal Rules and state court rules, state administrative regulations, the Federal Register, federal and state agency guidance, Executive Orders and other Presidential documents, the Sentencing Guidelines, and US income tax treaties. Results carry the citation, the title hierarchy, and a link to the official source document.

Resolve a citation (resolve_statute_citation): Hand it a Bluebook string (42 U.S.C. 1983, 16 C.F.R. 444.1, Del. Code Ann. tit. 13, 1301) and it returns the exact section that citation names, confirmed against the corpus. A pinpoint subsection like 42 U.S.C. 1983(b)(2) resolves to the parent section and echoes the subsection back. When it cannot resolve, it says so rather than improvising, and resolved: false means unverified, not current. A batch form checks up to 50 citations in one call at the same per-citation price.

Get section metadata (get_us_statute_section): Citation, title hierarchy, breadcrumb, and links to every format the publisher offers (HTML, PDF, XML, plain text, DOCX) for a single section, addressed by its actId. Use it to preview a section before pulling the text.

Get the full text (get_us_statute_section_text): The operative language, in styled HTML and plain text, with cross-references and paragraph numbering as published in the official source. Pass structured=true and you also get the body as nested Markdown plus a subsection tree you can address by pincite, so (b)(2) is a node with its own full pinpoint citation instead of a substring you have to go find.

Get neighboring sections (get_section_neighbors): The sections immediately before and after, in statutory order. This is the one that fixes the classic mistake of reading a section without its definitions or exceptions, which the spec notes usually sit a few sections back or a few forward. Search can't answer "what comes next", because relevance ranking is not statutory order. Neighbors never cross the containing chapter, and ordering is natural rather than lexicographic: 9 before 10, 1983 before 1983a.

Batch section metadata (get_sections_batch): Metadata for up to 50 sections in one call, in the order you asked for them, with misses reported separately so you can zip results back onto the ids that produced them. Enriching a 50-result page used to be 50 round trips.

Browse the hierarchy (list_statute_divisions): Walk a code one level at a time, in statutory order. USC titles, then the chapters in Title 42, then the sections in Chapter 21. Same for CFR parts, and for a state's individual codes (corpusType=STATE&state=tx gives you the Texas codes, then drill into the Penal Code). This is how you enumerate a body of law top to bottom without searching for it.

Check coverage (list_statutes_coverage): The coverage matrix, per jurisdiction and per corpus, with document counts. It reports what is held and the date it was measured. Free.

Check pricing (get_pricing): Current per-endpoint credit costs and the credit-to-dollar rate. Free and unauthenticated.

Other read tools in the spec: get_section_cited_by (the USC and CFR sections whose text cross-references a section), get_section_definitions (the defined terms that govern a section, parsed from its chapter's definitions section), get_section_cross_state (provisions in other states on the same subject as a state statute section), get_section_enactments (which acts a state publisher lists against a section), get_section_changes (the changes a refresh has observed to one section), count_statute_sections, and a set of session-law tools for state acts as enacted. get_credit_balance shows what you can still spend.

The corpus behind these tools runs to more than 5M sections, including 60,494 in the U.S. Code and 222,311 in the CFR, plus state statutes, regulations, constitutions, court rules, and the federal document corpora.

For more on how Vaquill AI's tools work and how to query them, see our MCP and developer guide series.

Setup: Claude Desktop

The entire setup takes about two minutes. You need two things: an API key and a config file edit.

Step 1: Get Your API Key

Generate a key in the API settings of your Vaquill AI account. It will start with vq_key_. Every call is metered in credits, and the free get_pricing tool lists what each one costs.

Step 2: Edit the Config File

Claude Desktop reads its MCP configuration from a JSON file. Settings > Developer > Edit Config opens it for you (Anthropic's MCP docs list macOS and Windows). On macOS, the path is:

~/Library/Application Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%\Claude\claude_desktop_config.json

Open (or create) that file and add the server entry:

{
  "mcpServers": {
    "vaquill": {
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

That file takes stdio servers only: a command, its args, and its env. It does not take a remote url. If you would rather use the hosted server than the package, add it as a connector instead: Customize > Connectors > Add custom connector, URL https://mcp.vaquill.ai/s/_, then a Request header named Authorization with the value Bearer vq_key_your_key_here. Claude sends that value exactly as typed and adds no scheme of its own, so it reads Bearer ... and never Authorization: Bearer .... In the dialog, choose No sign-in for authentication, since the server uses an API key rather than OAuth. Request headers on a custom connector are a beta feature available to a limited set of organizations (Anthropic's docs), and on the Free plan you can add one custom connector. Keep the key out of the URL: a URL ends up in logs and browser history.

Step 3: Restart Claude Desktop

Quit and reopen Claude Desktop. Then click the "Add files, connectors, and more" indicator in the bottom-left corner of the message box, move to "Connectors", and click "Manage connectors". Select vaquill to see its tools (Anthropic's MCP docs). That's it. You're connected.

Setup: Claude Code (Terminal)

If you use Claude Code in the terminal, setup is a single command:

claude mcp add --scope user vaquill -e VAQUILL_API_KEY=vq_key_your_key_here -- uvx vaquill-mcp

--scope user registers the server for every project. The default scope is local, which registers it only for the directory you happened to run the command in.

Pass the key with -e rather than exporting it in your shell. A shell export may not be visible when Claude Code is launched from an IDE, so keeping the key with the registration is the safer choice.

For the hosted server instead of the package, register it over HTTP:

claude mcp add --transport http --scope user vaquill \
  https://mcp.vaquill.ai/s/_ \
  --header "Authorization: Bearer vq_key_your_key_here"

--header and -e are variadic, so they have to come after the name and the URL. Put them first and the URL is swallowed into the flag's value list.

Setup: Cursor

Cursor reads MCP servers from ~/.cursor/mcp.json, or from .cursor/mcp.json in a repo root when you want the config to travel with one project. Open that file (Cursor's docs say you can also install and manage MCP servers from the Customize page) and add this configuration:

{
  "mcpServers": {
    "vaquill": {
      "type": "stdio",
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

Restart Cursor, and the tools will be available in your AI chat panel. For the hosted server, drop type, command, args and env, and give it a url plus a headers object instead; Cursor takes the transport from which of those keys are present.

Setup: VS Code (GitHub Copilot)

For VS Code with GitHub Copilot, MCP servers live in their own file, .vscode/mcp.json, not in settings.json:

{
  "servers": {
    "vaquill": {
      "type": "stdio",
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

That file is per-project. To get the same server in every workspace, run the MCP: Open User Configuration command from the Command Palette and put the same servers block in the file it opens.

Real Workflows: How Lawyers and Researchers Use This

Once the MCP server is connected, you just talk to Claude normally. It figures out which tools to call on its own.

Here are five workflows to try, modeled on common lawyer research patterns.

Workflow 1: Researching a Statutory Scheme

You're advising on OSHA injury recordkeeping and need to know what the rule actually requires, where the duty sits, and which employers it exempts.

You type:

What does the CFR require for OSHA injury and illness recordkeeping? Pull the operative sections, not a summary.

Claude calls search_us_statutes with corpusType: "CFR" and gets back ranked sections with citations and official source links. It then calls get_us_statute_section_text on the ones that matter and quotes the published language rather than paraphrasing it.

Follow up:

The section you quoted refers to "recordable injury" without defining it. Get me the sections around it.

Claude calls get_section_neighbors on § 1904.4 (Recording criteria). With the default of three sections on each side, a live call on 6 October 2026 returned §§ 1904.5, 1904.6 and 1904.7 after it and nothing before it, so the partial exemptions at §§ 1904.1 and 1904.2 are not among the neighbours. The part's definitions are at the far end, § 1904.46, so Claude walks there with list_statute_divisions. This is the step that separates reading a rule from reading a rule correctly.

Then, if you want the whole thing:

Enumerate every section in that part, in order.

Claude calls list_statute_divisions with the corpus, title, and part, and walks the level below it. You get the part's table of contents, in statutory order, rather than whatever a relevance ranking happened to surface.

Workflow 2: How Current Is This Text?

You're about to quote a regulation in an advice memo. Before you do, you need to know how current the text in front of you actually is.

A statutes corpus answers that question differently than a case-law database does. It carries provenance and a clock. For whether a case is still good law, see the case-law section above.

You type:

Before I rely on this, how fresh is your CFR data, and where did this text come from?

Claude calls list_statutes_coverage, which says what is held for each jurisdiction and corpus, with document counts and the date they were measured.

The get_us_statute_section_text response carries the rest: a sourceUrl pointing at the government page that published the text. That is the link you verify against. Where a publisher states its own currency, that rides on the section as currentThrough.

This single check is the difference between a credible memo and a sanctions exposure.

We cover that risk in detail in our piece on AI hallucinations and legal research sanctions.

Workflow 3: Statute Lookup

You're advising on a civil rights claim and want the text of the statute plus the standard of review for a related agency action.

You type:

Pull 42 U.S.C. 1983 for me, then show me 5 U.S.C. 706 on the scope of APA review.

Claude calls resolve_statute_citation on each Bluebook string, which confirms the citation against the corpus and returns the exact section it names. It then calls get_us_statute_section_text for each. You get the operative language of the civil rights cause of action and the APA review standard, both as published, both with a link to the government source.

Then:

Give me 17 U.S.C. 107 broken out by subsection, so I can cite the four factors individually.

Claude calls the text tool with structured=true. Alongside the HTML and plain text you get a subsection tree, where each node carries its pincite path and its full pinpoint citation. Quoting factor three becomes addressing a node, not hunting through a wall of text and hand-building the cite.

Other provisions you'll reach for the same way: 28 U.S.C. 1331 (federal-question jurisdiction), 18 U.S.C. 922 (firearms), and 16 C.F.R. 444.1 (the FTC credit practices definitions).

Workflow 4: Writing a Legal Memo

You need a three-state survey memo on non-compete enforceability, and you want every proposition tied to a statute you can open.

You type:

Search California, Texas, and New York statutes for non-compete and restrictive covenant provisions. Give me the sections, then the text of the ones that state the rule.

Claude calls search_us_statutes with corpusType: "STATE" and a list of states, which returns ranked sections from all three codes in one call. It then calls get_sections_batch to enrich the whole result page in a single round trip, and get_us_statute_section_text on the handful that carry the operative rule.

You can then say:

Now draft the memo. Structure it as an introduction, the rule in each state, where they diverge, and a conclusion. Cite the section for every proposition and include the official source link.

Claude produces a structured memo where every assertion is backed by a section it actually retrieved, with the government URL attached.

Workflow 5: Quick Citation Lookup

Someone sends you a draft with three statutory cites in it, and one of them was produced by an LLM. You need to know which.

You type:

Check these three: 42 U.S.C. 1983, 16 C.F.R. 444.1, and 15 U.S.C. 7291. Which of them actually resolve?

Claude calls resolve_statute_citation on each. A real citation comes back with resolved: true and the full section metadata attached. A citation that names nothing comes back with resolved: false and a null section, which is a confident negative rather than a plausible-looking guess. That distinction is the whole reason the tool exists, and the spec says it is charged either way for exactly that reason.

Ten seconds, no browser tabs, and a definite answer on a cite you were about to file.

Tips for Getting the Best Results

A few habits that get better results:

Name the jurisdiction and the corpus. "Texas Penal Code sections on theft" produces much better results than "state law on stealing." The corpus filters are the difference between searching 5M+ sections and searching the right few thousand.

Ask for the text, not a summary. If you say "what does this section say", a model will happily paraphrase from memory. Say "pull the text" or "quote it" and it reaches for the tool. The tool is the whole point.

Chain the lookup. Resolve the citation, pull the text, then pull the neighbors. Three calls, and you have the provision with its definitions and its exceptions instead of a paragraph floating in space.

Verify against the source URL, not against us. Every text response carries the government page it came from. Open it before you file. Our copy can lag the publisher; the publisher tells you what the law is.

Use the free tools to orient first. list_statutes_coverage costs no credits and answers "is this jurisdiction even in here" before you spend anything searching it.

For opinions, name a case-law connector. If you ask "what cases interpret this section" and no case-law tool is connected, a model will answer from training data, and that is exactly the failure mode you connected an MCP server to avoid. Attach a case-law connector and tell Claude which one to use.

FAQ

Can Claude do legal research? Yes, but not reliably on its own. On its own Claude reasons well and hallucinates citations, because it has no live legal database. Connect a legal research MCP server and Claude reads real statutory text and returns citations you can open and verify.

What is an MCP connector for legal research? MCP (Model Context Protocol) is an open standard Anthropic released in late 2024 that lets Claude call external tools. A legal research MCP connector exposes tools like statute search, citation resolution, and full-text retrieval to Claude so it queries a real database instead of guessing. See the spec.

How do I connect Claude to a legal research database? Two ways. Add a connector from Claude's built-in directory (Customize > Connectors), which Anthropic expanded for legal on May 12, 2026. Or add a server by its URL as a custom connector, or wire in a local MCP server with a short JSON config that works across Claude Desktop, Claude Code, Cursor, and VS Code. This guide shows the config for desktop and terminal.

How do I add a legal research connector to Claude? In claude.ai, open Customize > Connectors, find the provider in the directory, and authorize it. For a server that is not listed, use Add custom connector and enter its URL. Anthropic's docs say you can add one custom connector on the Free plan (Anthropic).

What tools does the Vaquill AI MCP server actually expose? The list is generated from the live API spec, so it changes with the API. On 16 October 2026 the hosted server lists 26 tools, all read-only. The core ones are search_us_statutes, resolve_statute_citation, get_us_statute_section, get_us_statute_section_text, get_section_neighbors, get_sections_batch, list_statute_divisions, list_statutes_coverage and get_pricing.

Does it search case law? It is built for statutes and regulations by citation. For US opinions, use a case-law connector such as the CourtListener connector from Free Law Project; the two coexist in one setup and Claude routes between them.

Can Claude check whether a case is still good law? Only through a source that tracks later case history, and even then read the treatment yourself. See the case-law section above for what each connector says about itself.

Can it show me how a regulation has changed? Yes. get_section_changes lists the changes we have observed to one section, and get_us_statute_section_text with asOf reads a section as it stood on a past date.

Is Claude for Legal a real product? Yes. Anthropic launched Claude for the legal industry on May 12, 2026 with more than 20 MCP connectors and 12 practice-area plugins (Anthropic, May 12, 2026). Legal research is one of the headline use cases.

Is Legal Data Hunter available in Claude? Yes. Anthropic lists it among the legal research connectors, describing 31M+ documents from 160+ jurisdictions (Anthropic, May 12, 2026).

Does Claude have access to Westlaw or case law by default? No. Out of the box Claude has no access to Westlaw, Lexis, or court opinions. Access comes from a connector. Anthropic's announcement lists Thomson Reuters CoCounsel Legal, which connects Claude to Westlaw and Practical Law content for customers with a CoCounsel Legal subscription.

Will Claude still hallucinate citations with an MCP connected? The risk drops sharply for anything inside the connected corpus, because the answer is retrieved text with a government URL attached. It does not drop for anything outside it. When no connected tool covers a question, the model falls back on training data. Scope your questions to what the connected servers actually cover.

Is it free to use Claude for legal research? Claude's own plan terms apply (on the Free plan you can add one custom connector, per Anthropic's docs). The Vaquill AI server needs an API key and meters calls in credits, and get_pricing lists the cost of every call. Coverage, boards, pricing and most watch operations cost no credits; the change diff costs 4.

Is the CourtListener connector free inside Claude? Free Law Project says every CourtListener account includes free API access, with additional access available through a Free Law Project membership (Free Law Project, May 12, 2026).

Does CoCounsel Legal require a paid subscription? Thomson Reuters says you need an active Thomson Reuters account with a CoCounsel Legal subscription (Thomson Reuters connector guide).

Which AI clients support legal research MCP servers? Claude Desktop, Claude Code, Cursor, and VS Code (GitHub Copilot) all support MCP, so the same legal research server works in any of them with a per-client config.

For Developers

If you're building a legal tech product or an AI agent that needs primary law programmatically, this MCP server calls the same REST API you'd call directly. Each tool calls one REST endpoint, and the tool list is derived from the published OpenAPI spec rather than maintained by hand (spec).

For a deeper look at agent architectures, multi-step tool chaining patterns, and integration with frameworks like LangGraph and CrewAI, see our post on adding legal research to AI agents with MCP.

For the US statutes, regulations and court rules these laws sit in, see the US primary law API.

Priyansh Khodiyar

Co-Founder & CTO

Priyansh leads engineering and AI at Vaquill AI: the pipelines that pull statutes, regulations and court rules from every US jurisdiction's official publisher, and the REST API, MCP server and open dataset that serve them.