Connect Vaquill and your agent gets 28 tools, among them create_watch, delete_watch, get_citation_network. It answers at https://mcp.vaquill.ai/s/_ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Search US and Indian statutes, regulations, constitutions, and court rules.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
create_watch | Subscribe to a board so a change to that source notifies you. Delivery is by webhook (HMAC-SHA256 signed) or email, fired when the source's existing refresh finds real changes -- nothing is crawled on your behalf and there is no real-time t Inputs: corpus_type, channel, state, webhook_url, email_address, act_ids |
delete_watch | Delete a watch you own. Immediate and permanent, and its delivery history goes with it. To stop notifications without losing the config or history, prefer update_watch with isActive false. Inputs: watch_id |
get_citation_network | Citation graph around a US case: both who cites it and what it relies on, with per-node citation counts and treatment hints. Depth 1 is the direct neighbourhood; depth 2 reaches citing-of-citing and costs substantially more. Use to judge wh Inputs: citation, direction, depth, limit, country_code |
get_pricing | Current API credit pricing: per-endpoint credit costs and the credit-to-currency conversion rate (1 credit = $0.01 USD). Free, and no authentication required. Use to check what a call will cost before making it. |
get_section_changes | What our refreshes have observed changing on one section over time: when it was added, amended or removed, newest first. This is our capture history, not the publisher's -- an empty list means we recorded no change, never that the section w Inputs: act_id |
get_section_cited_by | The USC and CFR sections whose text cross-references a given section: the inverse of the crossReferences already returned on a section lookup. Use to find where a definition or requirement is actually invoked, or to gauge how load-bearing a Inputs: act_id, limit |
get_section_cross_state | Provisions in OTHER states that address the same subject as a given state statute section, ranked by similarity. State statutes only. Use for fifty-state surveys, multi-jurisdiction compliance, or to check whether a client's home-state rule Inputs: act_id, limit |
get_section_definitions | The term definitions that govern a section, parsed from its chapter's definitions section. Use whenever a provision turns on a term of art ('covered entity', 'security', 'employer') and you need the statute's own definition rather than the Inputs: act_id |
get_section_neighbors | The sections immediately before and after a given section within its own chapter or code, in statutory order. Use to read a provision in context, to find a definitions or penalties sibling, or to check whether the operative language continu Inputs: act_id, limit |
get_sections_batch | Metadata for up to 50 sections in one call, by a list of act_ids. Same fields as get_us_statute_section. Use instead of looping that tool when you already hold several act_ids, for example every result of one search. Sections that are not f Inputs: act_ids |
get_us_statute_section | Metadata for one US statute, regulation or rule section by act_id: citation, title hierarchy, breadcrumb, amendment history, and links to HTML, PDF and XML. Does NOT include the section text -- use get_us_statute_section_text for that. Good Inputs: act_id |
get_us_statute_section_text | The full text of a US statute, regulation or rule section by act_id. Returns styled HTML (with cross-references and paragraph numbering as officially published) and plain text. Use when you need the actual statutory language to quote, draft Inputs: act_id |
get_watch_change_diff | The full text of a changed section BEFORE and AFTER one specific change, as whole documents ready to diff. Only meaningful where hasDiff is true on the change list. A missing side is not an error: hasBefore and hasAfter say which text is pr Inputs: watch_id, change_id |
list_boards | List every watchable board: a tracked corpus source such as the Federal Register, the CFR, or one state's statutes, with its refresh cadence. A board is identified by corpusType plus state (state is null for federal). Use to discover what c Inputs: corpus_type, state, limit, offset |
list_statute_divisions | Walk the statutory hierarchy: list the child divisions (titles, chapters, parts, or sections) under any level, in statutory order. Use to browse a code structurally when you do not yet know the section number, or to enumerate everything und Inputs: corpus_type, state, code |
list_statutes_coverage | Self-describing coverage matrix: every corpusType we hold and its per-jurisdiction section counts. Use before answering a jurisdiction question to check whether we actually cover that state and that body of law, so you can say so instead of |
list_statutes_laws | Catalog of the distinct bodies of law available (a state's statutes, a state's regulations, the US Code, the US Constitution, federal court rules, and so on), each with its corpusType and section count. Use to discover the corpusType values Inputs: state, corpus_type, limit, offset |
list_watch_changes | What a watched source added, amended or removed: section identifier, citation, title and detection time, newest first. Metadata only, never section text. Covers the board's whole captured history, not just since you subscribed. Safe to poll Inputs: watch_id, limit, offset |
list_watch_deliveries | Per-attempt delivery log for one watch: status code, error and attempt number, retained 90 days. Webhook watches only -- an email-only watch always returns an empty list, because email sends are not logged per attempt. Use to debug a webhoo Inputs: watch_id, limit, offset |
list_watches | List the board watches you own, with their board, channel, destination, active state and the outcome of the last delivery attempt. Use to find a watchId for the other watch tools. Inputs: limit, offset |
lookup_case | Full details for one US case: opinion text, the panel of judges, its citation list and disposition. Use after resolve_citation when you need to read or quote the opinion itself rather than just confirm it exists. Inputs: citation, country_code |
quick_search | Fast, compact US case law search returning the top few results with just the essentials: title, citation, court, year and a short excerpt. Same boolean syntax as search_legal_cases but flatter and cheaper. Best when you need a quick orienta Inputs: query, top_k, court_type, court_name, year_from, year_to |
resolve_citation | Resolve a US case citation ('603 U.S. 369', '410 U.S. 113') to its canonical record, returning the case details and cluster id. Returns found=false rather than an error when the citation cannot be resolved. Use before lookup_case or get_cit Inputs: citation, country_code |
resolve_statute_citation | Resolve a Bluebook citation string ('42 U.S.C. 1983', '16 C.F.R. 444.1', 'Cal. Code Regs. tit. 22, 76227') to the exact section, confirmed, with an official source link and the act_id. Use this whenever the user gives you a citation rather Inputs: citation |
search_legal_cases | Boolean keyword search across 8M+ US federal and state court opinions. Supports AND, OR, NOT and quoted phrases; filter by court and year range. Returns paginated results with citation, court, date, relevance score and a snippet. Present th Inputs: query, court_type, court_name, year_from, year_to, country_code |
search_us_statutes | Semantic + keyword search across US primary law: the United States Code (USC), the Code of Federal Regulations (CFR), and all 50 states' statutes, regulations, constitutions and court rules. Use for any 'what does the law say' question. Fil Inputs: query, corpus_type, state, code, title_number, limit |
test_watch | Send a synthetic notification to a watch's destination to verify signing, outbound auth and reachability before relying on it. Test deliveries are deliberately not persisted, so they never appear in list_watch_deliveries and never move the Inputs: watch_id |
update_watch | Change a watch's destination, signing secret, outbound auth, or active state. Set isActive false to pause notifications while keeping the watch's config and history. The channel itself cannot be changed. Inputs: watch_id, is_active, webhook_url, email_address |
Every block below points at https://mcp.vaquill.ai/s/_. Pick your client and copy.
claude mcp add --transport http vaquill https://mcp.vaquill.ai/s/_
{
"mcpServers": {
"vaquill": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.vaquill.ai/s/_"]
}
}
}{
"mcpServers": {
"vaquill": {
"url": "https://mcp.vaquill.ai/s/_"
}
}
}{
"servers": {
"vaquill": {
"type": "http",
"url": "https://mcp.vaquill.ai/s/_"
}
}
}{
"context_servers": {
"vaquill": {
"url": "https://mcp.vaquill.ai/s/_"
}
}
}{
"mcpServers": {
"vaquill": {
"serverUrl": "https://mcp.vaquill.ai/s/_"
}
}
}{
"mcpServers": {
"vaquill": {
"url": "https://mcp.vaquill.ai/s/_"
}
}
}name: Vaquill
version: 0.0.1
schema: v1
mcpServers:
- name: Vaquill
type: streamable-http
url: https://mcp.vaquill.ai/s/_{
"mcpServers": {
"vaquill": {
"httpUrl": "https://mcp.vaquill.ai/s/_"
}
}
}{
"mcpServers": {
"vaquill": {
"type": "http",
"url": "https://mcp.vaquill.ai/s/_"
}
}
}{
"mcpServers": {
"vaquill": {
"url": "https://mcp.vaquill.ai/s/_"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.vaquill.ai%2Fs%2F_&type=streamable_http&id=vaquill&name=Vaquill
It answered our last check on 18 October 2026 in 327 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
28, as returned by the server's own tools/list on 31 August 2026: create_watch, delete_watch, get_citation_network, get_pricing, get_section_changes, get_section_cited_by, get_section_cross_state, get_section_definitions, and 20 more.
It answered our last check on 18 October 2026 in 327 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.vaquill.ai/s/_. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.vaquill-ai. Endpoint host: mcp.vaquill.ai. ARD identifier: urn:air:io.github.vaquill-ai:mcp:vaquill-mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.