paid mcp · sandbox preview
Multi-LLM, structured,
in your terminal.
crosscheck is an MCP server that runs five patterns — confer, debate, audit, plan, panel-pick — across Anthropic, OpenAI, Gemini, and Grok. Your machine, your keys, content-free telemetry.
$20/seat/month · first month free with WELCOME100
https://crosscheckagent.com/cli/device
Or type this code:
AAAA-BBBB-CCCC
Waiting for authorization.....
five patterns
Stop reinventing the prompt. Pick the pattern.
confer
Ask the panel the same question in parallel. Fast, low-coordination, surface diverging views.
debate
Bounded multi-round back-and-forth. The moderator synthesizes. Early-stop when convergence hits.
audit
One model proposes, others review. Catches errors the proposer can't see in its own output.
plan
Collaborative planning across models. Each contributes; the synthesis is structured for execution.
panel-pick
Smart router picks the right panel by purpose + historical reliability. Lower cost, equivalent answers.
trust posture
Three invariants we won't break.
01
Server never sees prompts
Telemetry schema rejects prompt-shaped keys at the boundary. CI enforces it in every PR.
02
Server never sees keys
Upstream LLM API keys live in your OS keychain. There's no server route that accepts them.
03
Activation is privacy-preserving
Per-machine fingerprint is an Argon2 hash. Not a serial, not a MAC, not reversible.
pricing
One price. Your LLM bill stays yours.
You pay us for the orchestration, dashboard, analyzer, and activation. You pay Anthropic, OpenAI, Gemini, and Grok directly for your model usage — through your own accounts, with keys we never see.
- · cancel anytime in the stripe billing portal
- · per-seat, single-machine activation, self-serve re-activation
- · first month free with code WELCOME100
crosscheck — single seat
usd, billed monthly. add seats anytime; we prorate through stripe.
staging. crosscheckagent.com pointing here soon.
faq
Questions worth answering.
Do you see my prompts or model responses?
No. crosscheck's telemetry contains only token counts, cost estimates, latency, and the pattern name. The Zod schema at the ingest boundary rejects any prompt-shaped key (prompt, messages, content, input, text, completion, response, output). CI enforces it on every PR.
Do you store my LLM API keys?
No. Your upstream keys live in your machine's OS keychain (Keychain on macOS, Credential Manager on Windows, libsecret on Linux). There is no server route that accepts them. The crosscheck CLI loads them from the keychain into the engine subprocess's environment — that's the only place they exist outside your keychain.
What does the $20/month cover?
The orchestration engine, the dashboard, the better-use analyzer, single-machine activation, and the server-side infrastructure that issues activation JWTs and accepts content-free telemetry. It does not cover your spend with Anthropic, OpenAI, Google, or xAI — those are your own provider accounts.
Which providers are tested?
Anthropic, OpenAI, Google (Gemini), and xAI (Grok) are tested integrations. DeepSeek, Groq, and Mistral are experimental and provided as-is — we don't ship breaking changes around them but coverage is lighter.
Can I cancel anytime?
Yes. Self-serve cancellation from the Stripe billing portal. Takes effect at the end of your current billing period; no pro-rata refunds outside what applicable law requires.
Try it on us for thirty days.
Apply WELCOME100 at checkout. Cancel before the first renewal and you owe us nothing.