Vaquill AI
Summary
When your attorney cites 26 U.S.C. § 6662 and your pipeline has to hand-parse that string, chase down USCode.house.gov, scrape HTML that wasn't designed for machines, and pray the section numbering matches what the CFR cross-references — that is the problem Vaquill AI was built to end.
Vaquill exposes 3.9 million US primary-law sections across all 52 jurisdictions through a single REST API and an MCP interface, covering federal statutes, the CFR, Federal Register rules, executive orders, and agency guidance from the IRS to the USPTO to state insurance department bulletins. A Bluebook citation goes in; structured section text and hierarchy metadata come out. Batch endpoints handle up to 50 sections per call, which matters when you're hydrating a document review queue rather than answering one question. The dataset is open-sourced, so teams that want to verify coverage before committing can audit what's there. The wall appears when you need case law or court-filed documents — Vaquill is strictly primary law and agency guidance, full stop.
Bottom line: Pick Vaquill when your application needs to resolve statutory citations and retrieve structured legislative or regulatory text at scale — but plan a separate data source the moment your workflow requires case law, docket filings, or secondary legal analysis.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Pros
Sign in to edit- Single schema across all 52 US jurisdictions, so your code does not branch per-jurisdiction when fetching a state statute versus a federal CFR section.
- Bluebook citation resolution built into the API, which means the string your attorney wrote in a brief goes directly into a query rather than requiring a parsing layer you maintain.
- Batch endpoint for up to 50 sections per call, so a document with dozens of statutory references hydrates in a handful of requests instead of one blocking call per citation.
- Agency guidance coverage extends to granular sources — IRS Rulings, OCC Interpretive Letters, state insurance department bulletins — that competing APIs treat as out of scope, reducing the number of scraping jobs your team writes and maintains.
- MCP interface alongside REST, so LLM-based pipelines that support the Model Context Protocol can pull statutory text without a custom integration layer.
Cons
Sign in to edit- No case law, court opinions, or citator data exists in the dataset. A pipeline that needs to verify whether a statute has been judicially interpreted or overturned hits a hard stop — teams add a Westlaw, CourtListener, or Casetext integration to cover that gap, which means maintaining credentials and schemas for two systems.
- Self-hosting is not an option. Teams at firms with data-residency policies that prohibit sending legal research queries to external APIs cannot use Vaquill without a policy exception — those teams typically evaluate on-prem or private-cloud legal data vendors instead.
- Deeper access and higher volume are behind a paid tier. Teams that prototype on the free endpoints and then push batch jobs at production scale will hit rate or access limits and need to convert before their launch date — the exact threshold is not published on the public documentation page.
About
- Platforms
- REST API, MCP API
- API Available
- Yes
- Self-Hosted
- No
- Last Updated
- 2026-08-16T11:34:59.839Z
Best For
Who it's for
- Law firms needing cited primary law
- In-house legal teams
- Legal tech builders
- Policy and research organizations
- Law schools and legal aid
What it does well
- Resolve Bluebook citations to full sections
- Retrieve statutory text and hierarchy metadata
- Batch fetch metadata for up to 50 sections
- Discover available law bodies by jurisdiction
- Access federal and state agency guidance
Add notes, reviews, and benchmarks so the next visitor gets a clearer picture.
Compare Vaquill AI
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeFrequently Asked Questions
- Is Vaquill AI free?
- Vaquill AI has a permanent free tier alongside paid upgrades. You can keep using a baseline version indefinitely without paying.
- Is Vaquill AI open source?
- No — Vaquill AI is a closed-source tool. Source code is not publicly available.
- Does Vaquill AI have an API?
- Yes. Vaquill AI exposes a developer API. See the official documentation at https://vaquill.ai for details.
- What platforms does Vaquill AI support?
- Vaquill AI is available on: REST API, MCP API.
Best Vaquill AI alternatives →
Curated lists that include this category
The citation-to-text gap
When your attorney cites 26 U.S.C. § 6662 and your pipeline has to hand-parse that string, chase down USCode.house.gov, scrape HTML that wasn’t designed for machines, and pray the section numbering matches what the CFR cross-references — that is the problem Vaquill AI was built to end.
What it does
Vaquill exposes 3.9 million US primary-law sections across all 52 jurisdictions through a single REST API and an MCP interface. It covers federal statutes, the CFR, Federal Register rules, executive orders, and agency guidance from the IRS to the USPTO to state insurance department bulletins. A Bluebook citation goes in; structured section text and hierarchy metadata come out. Batch endpoints handle up to 50 sections per call. The dataset is open-sourced.
Key limits
No case law, court opinions, or citator data exists in the dataset. Self-hosting is not an option.
Who it is for / who should skip it
Best for law firms needing cited primary law, in-house legal teams, legal tech builders, policy and research organizations, and law schools and legal aid. Teams that need judicial interpretation data or must keep queries inside their own infrastructure should look elsewhere.