Connect LegalSearch and your agent gets 6 tools, among them roop.public.corpus.status, roop.public.judgments.get_packet, roop.public.judgments.get_segment. It answers at https://mcp.roopslaw.ai/mcp 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 4 September 2026; the last check, on 17 October 2026, succeeded.
Public Indian legal search MCP for Roop judgments, statutes, and corpus grounding.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
roop.public.corpus.status | Report the public corpus surfaces exposed through this DMZ MCP. |
roop.public.judgments.get_packet | Fetch a bounded public judgment or appellate tribunal packet by ROOP judgment id. Inputs: roop_id |
roop.public.judgments.get_segment | Fetch one bounded, continuable segment of an exact public judgment by ROOP judgment id. Inputs: roop_id, offset, max_chars |
roop.public.judgments.search | Search public Indian judgment and appellate tribunal metadata plus public snippets. Inputs: query, court, limit |
roop.public.statutes.get_packet | Fetch a bounded public statute packet using the public statutes search surface. Inputs: query, limit |
roop.public.statutes.search | Search public statutes and subordinate legislation metadata. Inputs: query, jurisdiction_scope, state_code, doc_kind, instrument_type, instrumentType |
Every block below points at https://mcp.roopslaw.ai/mcp. Pick your client and copy.
claude mcp add --transport http legalsearch https://mcp.roopslaw.ai/mcp
{
"mcpServers": {
"legalsearch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.roopslaw.ai/mcp"]
}
}
}{
"mcpServers": {
"legalsearch": {
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"servers": {
"legalsearch": {
"type": "http",
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"context_servers": {
"legalsearch": {
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"mcpServers": {
"legalsearch": {
"serverUrl": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"mcpServers": {
"legalsearch": {
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}name: LegalSearch
version: 0.0.1
schema: v1
mcpServers:
- name: LegalSearch
type: streamable-http
url: https://mcp.roopslaw.ai/mcp{
"mcpServers": {
"legalsearch": {
"httpUrl": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"mcpServers": {
"legalsearch": {
"type": "http",
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}{
"mcpServers": {
"legalsearch": {
"url": "https://mcp.roopslaw.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.roopslaw.ai%2Fmcp&type=streamable_http&id=legalsearch&name=LegalSearch
It answered our last check on 17 October 2026 in 566 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by roopslaw.ai and served from mcp.roopslaw.ai, the vendor's own domain: https://mcp.roopslaw.ai/mcp.
6, as returned by the server's own tools/list on 8 September 2026: roop.public.corpus.status, roop.public.judgments.get_packet, roop.public.judgments.get_segment, roop.public.judgments.search, roop.public.statutes.get_packet, roop.public.statutes.search.
It answered our last check on 17 October 2026 in 566 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.roopslaw.ai/mcp. 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: ai.roopslaw. Endpoint host: mcp.roopslaw.ai. ARD identifier: urn:air:ai.roopslaw:mcp:legalsearch.
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.