Lr Labs is a remote MCP server that gives an AI agent 5 tools, among them analyze_cross_border_tax, list_compiled_corridors, lookup_compiled_rule. It answers at https://lrlabs.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 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
Deterministic cross-border tax engine: PE, GAAR, Indian TP, rule-level lookup. Compiled law, no LLM.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
analyze_cross_border_tax | Compute the tax position of a cross-border arrangement between a treaty pair (permanent-establishment exposure and Indian tax liability) from structured facts. Returns a determinate legal position: the answer, the condition tree it stands o Inputs: treaty, facts, question, posture, detail |
list_compiled_corridors | List which treaty pairs, PE families, and compiled-rule counts the LR Labs engine covers, plus the structured-fact schema. Call this to decide whether analyze_cross_border_tax can answer a question; outside the compiled corridors the engine |
lookup_compiled_rule | Answer a RULE-LEVEL question directly from compiled law: thresholds and day counts, WITHHOLDING TAX rates on royalty and fees for technical services (treaty and domestic), the 1961→2025 Income-tax Act section renumbering (s.195→s.393(2), s. Inputs: query, treaty |
screen_transfer_pricing | Screen an Indian transfer-pricing position deterministically: safe-harbour eligibility against the Rule 10TD floors (17%/18% software-ITES, 18-24% KPO), documentation obligations under Rule 10D, which transfer-pricing METHODS are eligible o Inputs: transactionType, transactionValueCr, serviceMarkupPct, alrPercentile, hasInternalCup, hasExternalCup |
verify_tax_research_note | Deterministically verify a piece of tax analysis (yours or anyone's): every citation is resolved against the compiled corpus, quotes and thresholds are checked against compiled law, temporal claims against validity windows — INCLUDING claim Inputs: text, as_of |
Every block below points at https://lrlabs.ai/mcp. Pick your client and copy.
claude mcp add --transport http lr-labs https://lrlabs.ai/mcp
{
"mcpServers": {
"lr-labs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lrlabs.ai/mcp"]
}
}
}{
"mcpServers": {
"lr-labs": {
"url": "https://lrlabs.ai/mcp"
}
}
}{
"servers": {
"lr-labs": {
"type": "http",
"url": "https://lrlabs.ai/mcp"
}
}
}{
"context_servers": {
"lr-labs": {
"url": "https://lrlabs.ai/mcp"
}
}
}{
"mcpServers": {
"lr-labs": {
"serverUrl": "https://lrlabs.ai/mcp"
}
}
}{
"mcpServers": {
"lr-labs": {
"url": "https://lrlabs.ai/mcp"
}
}
}name: Lr Labs
version: 0.0.1
schema: v1
mcpServers:
- name: Lr Labs
type: streamable-http
url: https://lrlabs.ai/mcp{
"mcpServers": {
"lr-labs": {
"httpUrl": "https://lrlabs.ai/mcp"
}
}
}{
"mcpServers": {
"lr-labs": {
"type": "http",
"url": "https://lrlabs.ai/mcp"
}
}
}{
"mcpServers": {
"lr-labs": {
"url": "https://lrlabs.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Flrlabs.ai%2Fmcp&type=streamable_http&id=lr-labs&name=Lr%20Labs
It answered our last check on 21 October 2026 in 470 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
5, as returned by the server's own tools/list on 13 September 2026: analyze_cross_border_tax, list_compiled_corridors, lookup_compiled_rule, screen_transfer_pricing, verify_tax_research_note.
It answered our last check on 21 October 2026 in 470 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lrlabs.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: io.github.abhinandansethi. Endpoint host: lrlabs.ai. ARD identifier: urn:air:io.github.abhinandansethi:mcp:lr-labs.
First indexed 10 September 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.