LMbox
Vos données restent chez vous. Book a demo
← Back to the Box Integration · Cursor

Cursor, without the per-seat bill

Cursor speaks the Anthropic Messages API when you pick a Claude model. The LMbox Box intercepts those calls, routes to whichever tier is enough (local or Bedrock EU), and exposes internal connectors via MCP. You keep Cursor; you stop paying $20/dev/month on top of the Anthropic API.

The problem

Cursor at team scale: double bill, code leaks to Anthropic

$20/dev/month for Cursor

Cursor Pro is $20/seat/month, $40 for Business. A 30-developer team is $7,200/year before the first API call.

+ the API bill on top

The Cursor seat only covers a fast-mode quota. Beyond that, and especially for Claude Sonnet, your card is charged on every chat. No clear ceiling for the IT team.

Your repos go to Anthropic

Cursor ships open-file context + selections + @-searches to the chosen model's API. For a confidential repo, that's a deal-breaker without a network gate in front.

Three patterns

How Cursor plugs into the Box

Cursor accepts an Anthropic-compatible endpoint and a custom MCP server. The Box covers both. Pick what matches your sovereignty bar.

Pattern A

Pure local proxy

Cursor points at the Box for Claude models. Zero internet egress. Great for short sessions and inline completion via Mistral / Codestral; limited on 20+ turn agentic chats.

Cursor → Settings → Models → Override OpenAI/Anthropic Base URL → https://lmbox.local. The Box answers /v1/messages with Mistral Large 2.

Pour qui
Law firms · OIV · health · air-gap
★ Recommandé
Pattern B

Cascade routing (recommended)

The lmbox router scores each request (turns, tokens, keywords, tools) and picks fast / medium / frontier. Cursor only sees one URL; the router records its scoring in the audit log. ~75% of traffic stays local.

Same as Pattern B for Claude Code. The lmbox-router is protocol-agnostic, regardless of whether the client is Claude Code or Cursor.

Pour qui
Tech mid-market · industry · Mistral/Anthropic partners
Pattern C

MCP @ over internal connectors

Cursor supports MCP natively. Drop lmbox-mcp into .cursor/mcp.json and the 4 tools (search / read_doc / list_sources / find_similar) appear. Type @LMbox in a session to query SharePoint, Confluence, Jira — content never leaves the Box.

Streamable HTTP transport. Master-key auth in v1 (OIDC on the roadmap). Only the ranked top-K hits the model; raw doc bodies never leave the appliance.

Pour qui
Any team with an internal documentation base
The math

30-developer team, three scenarios

Assumptions: 30 developers on Cursor Pro ($20/seat), heavy agentic use, observed cascade ratio 65/25/10 (fast/medium/frontier). Bedrock EU pricing as of May 6, 2026, € ≈ $1.08.

Scenario Cursor seats Anthropic API LMbox cost Monthly total
Cursor Pro direct (no LMbox) ≈ €555 ≈ €6,000 ≈ €6,555 · €78,660/year
LMbox cascade (75% local) ≈ €555 ≈ €1,200 Box amortised over 36 months ≈ €1,850 · €22,200/year
100% local (Mistral) — Cursor frontier disabled ≈ €555 €0 Box amortised over 36 months ≈ €600 · €7,200/year
3-year savings, team of 30
≈ €170,000

The Cursor seat still buys you the IDE features (inline autocomplete, agent-mode, multi-cursor edit). What gets cut is the API bill on top, not the editor subscription itself.

Quickstart · LLM

Point Cursor at the Box

1. Override the Anthropic base URL

In Cursor → Settings → Models → Override Anthropic API. The key can be any non-empty value — the Box authenticates internally on X-LMbox-* headers.

Anthropic Base URL: https://lmbox.local
Anthropic API Key:  $(lmbox vault get cursor_passthrough_key)

2. Pick a Claude model in Cursor

Choose 'claude-sonnet-4.5' in Cursor. The Box rewrites the model name based on the tier the router picked (Mistral / Qwen / Sonnet).

$ lmbox router test "Cross-file refactor of the billing module"
{ "tier": "frontier", "score": 18, "would_route_to": "bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0" }

3. Audit costs at week's end

After a week the audit log shows who routed where — useful to recalibrate the scoring if the team feels a local model gets too many hard requests.

$ lmbox router stats 7
TIER          REQ   ERR  TIN/M  TOUT/M  P50ms  P95ms   COST€
fast        4,230     1   2.84    0.51     78    142    0.00
medium      1,102     0   5.71    1.42   1,430  2,810   0.00
frontier      303     2   4.21    1.32    340    980   58.74
TOTAL       5,635                                       58.74
Quickstart · MCP

Plug Cursor into the LMbox connectors

Pattern C — Cursor has supported MCP natively since 0.49. Three steps to expose SharePoint / Confluence / Jira / GitLab as @LMbox inside the Cursor chat.

1. Declare the MCP server in Cursor

Create .cursor/mcp.json at the project root (per-project) or ~/.cursor/mcp.json (global). The key comes from the age-encrypted vault.

{
  "mcpServers": {
    "LMbox": {
      "url": "https://lmbox.local/mcp",
      "headers": {
        "x-lmbox-mcp-key": "${LMBOX_MCP_KEY}"
      }
    }
  }
}

2. Verify the tools on the Box side

The server exposes 4 tools. Cursor picks them up after a window reload.

$ lmbox mcp tools
• search        args=(query, source, top_k)
• read_doc      args=(doc_id, source)
• list_sources  args=()
• find_similar  args=(text, source, top_k)

3. Use @LMbox inside Cursor's chat

Type @LMbox followed by a query. Cursor calls the search tool; the query runs in the Box; only the top-K reaches the model.

> @LMbox find anything in Confluence about our Azure AD SSO flow

[tool] LMbox.search confluence "Azure AD SSO flow" → 8 hits
[model] The SSO flow is documented across 3 pages…

Cursor + MCP: zero exfiltration on the editor side

Cursor calls MCP tools client-side itself — the request goes from your machine to the Box, never through Anthropic. Combined with the LLM proxy, that means no byte of Confluence or SharePoint touches Cursor or Anthropic servers.

What CISOs and lead devs ask

Questions teams raise before signing

+ Does Cursor still send data home?
Inline autocomplete and local repo indexing — yes, that's their core feature and it stays on their servers (you can disable cloud indexing under privacy settings). Chat / agent-mode, with the Base URL override, hit the Box. The most defensible mix for a law firm: cloud autocomplete disabled + chat routed via LMbox.
+ Which Cursor models can be routed?
All "Claude" models (Cursor uses the Anthropic Messages API for them). GPT-* models hit OpenAI directly today and don't traverse the LMbox router — on the roadmap. For now, default the team to Claude on sensitive sessions.
+ How do I cut off the Anthropic passthrough during an incident?
lmbox router config --frontier=disabled forces all frontier traffic down to medium or fast. The Cursor team keeps a working chat on Mistral / Qwen, with no outbound calls. Reversible without restart.
+ Does Cursor accept a non-Anthropic base URL?
Yes — the "Override OpenAI/Anthropic Base URL" field is explicitly there under Settings → Models. It was added for enterprise and self-hosted proxies. No jailbreak.
+ Since when does Cursor support MCP?
Cursor 0.49 (April 2025). Streamable HTTP is supported; legacy SSE too. MCP tools surface as @-suggestions and can be invoked programmatically by agent-mode.

We install the Box, we connect Cursor

30-day on-site POC with a team of 10 to 30 developers. We measure the actual local/frontier ratio + disable Cursor's cloud telemetry where we can. If the team complains, we pack up.