This server connects Claude and other MCP clients to the FaultKey CausalLayer engine, which runs deterministic fault attribution for multi-party AI incidents. It exposes four tools: submit_incident analyzes liability and returns a signed certificate with per-agent fault allocation anchored to Bitcoin via OpenTimestamps, verify_certificate checks signatures and Merkle integrity independently, get_anchor_status retrieves batch proofs, and query_issuer_registry lists trusted public keys. The math is closed-form graph theory, not LLM scoring, so two adversarial parties get byte-identical results. Runs on Cloudflare Workers with regex PII filtering at the edge. Reach for it when you need auditable, reproducible liability allocation that insurers or regulators will accept, or when building compliance tooling around AI incident response.
Deterministic fault math for multi-party AI incidents. When an AI causes harm and three parties argue over who pays, FaultKey returns a signed, Bitcoin-anchored certificate of fault allocation in under 200 ms — no LLM, no probabilistic scoring, no vendor cooperation needed for a third party to verify.
This is the official Model Context Protocol (MCP) server for the CausalLayer engine, packaged as a Cloudflare Worker. It lets AI agents (Claude Desktop, Cursor, Cline, Continue, Windsurf) call the four core liability-attribution tools without writing a single line of integration code.
If this saves you time, give it a star — it helps others find it and tells us people care.
🎮 Try the Interactive Demo — No setup required. Pick a scenario, click "Run Analysis", see real-time liability attribution.
The public Worker is deployed on Cloudflare's global edge network and is fully functional in standalone demo mode (deterministic responses, watermarked, rate-limited 5 calls / IP / day):
https://mcp.faultkey.com/mcp (live, custom domain)https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp/healthz/stats (public, aggregated, no PII)Add this to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"faultkey": {
"command": "npx",
"args": ["-y", "causallayer-mcp"]
}
}
}
Restart Claude. Type "List the FaultKey tools."
Settings → MCP Servers → Add new:
faultkeynpx -y causallayer-mcp{
"name": "faultkey",
"command": "npx",
"args": ["-y", "causallayer-mcp"]
}
curl -X POST https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":0,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0"}}}'
The response includes a Mcp-Session-Id header that you reuse for subsequent calls.
| Tool | Description | Demo limit | Paid cost |
|---|---|---|---|
submit_incident | Submit an AI incident for deterministic liability attribution. Returns a signed CausalCertificateV1 with per-agent fault allocation, evidence-chain completeness, and Bitcoin-anchored proof. | 5 / IP / day | 50 credits |
verify_certificate | Independently verify a certificate (signature, Merkle integrity, issuer status) without calling FaultKey. | 50 / IP / day | 1 credit |
get_anchor_status | Return the index of all Tessera anchor batches or one batch's full JSON (signed Merkle root, OpenTimestamps proof reference). | Unlimited | Free |
query_issuer_registry | List all trusted CausalLayer issuer public-key fingerprints, status, and validity windows. | Unlimited | Free |
Insurers, banks, and APRA-regulated entities cannot accept LLM-based fault attribution because the same prompt produces different answers on different days. FaultKey uses a closed-form causal scoring algorithm (graph-theoretic, version-pinned, byte-identical reproducible across runs) so two adversarial parties get the same number — that's the whole point.
The math is published as an Australian Standards-aligned paper. The signed certificate, issuer registry, and Merkle anchor log are all independently verifiable by a third party using only Node's built-in crypto and the causallayer-verifier tool — no network calls back to the vendor.
pii_acknowledged: true (which is logged in the certificate as a compliance acknowledgement).deterministic_only: true. This is the agent's binding acknowledgement that FaultKey output is closed-form, not probabilistic.400 evidence_insufficient.You can deploy your own copy to your own Cloudflare account if you want to enforce a corporate firewall, custom rate limits, or bring your own KV namespace:
git clone https://github.com/smq9sn5jck-coder/causallayer-mcp.git
cd causallayer-mcp
pnpm install
pnpm wrangler kv namespace create LEDGER
# paste the returned id into wrangler.jsonc
pnpm wrangler deploy
The CausalLayer engine itself (the closed-form fault math) runs upstream and is available via API key. For self-hosted demos without an upstream, set STANDALONE_DEMO=true in wrangler.jsonc to short-circuit upstream calls and return deterministic, watermarked responses.
[Claude/Cursor/Cline] ←→ [npx causallayer-mcp] ←→ [Cloudflare Worker] ←→ [CausalLayer engine]
(mcp-remote proxy) (this repo) (Fly.io Sydney)
↓
[KV: credit ledger]
[DO: per-session state]
[KV: telemetry buffer]
CausalLayerMCP), SQLite-backed[DEMO] watermark| Tier | Credits | $AUD | Notes |
|---|---|---|---|
| Demo | 5 incidents / IP / day | Free | Watermarked responses |
| Starter | 1,000 | $99 | Stripe Checkout, no SLA |
| Growth | 10,000 | $749 | + 50 verify, 99.5% SLA |
| Enterprise | Unmetered | Contact | + dedicated namespace, 99.95% SLA, audit log access |
For enterprise tenants email sales@faultkey.com (or open a GitHub issue with subject "enterprise inquiry").
Score any AI incident in seconds — faultkey.com/score — describe what happened, get a deterministic liability split with dollar exposure, jurisdiction analysis, and a shareable verdict card.
Compare vendor liability profiles — faultkey.com/compare — side-by-side comparison of AI vendors (OpenAI vs Anthropic vs Google etc.) across incident types.
Public accuracy ledger — faultkey.com/track-record — 7/7 direction match on backtested cases, 3 pending predictions on active litigation.
Apache 2.0. See LICENSE.
If FaultKey helped you understand AI liability, saved you research time, or you just think deterministic fault attribution should exist:
FaultKey is built in Brisbane, Australia, with data residency in Sydney for APRA-regulated buyers. The team can be reached at hello@faultkey.com.
io.github.shelvick/shopify-subscription-reconciliation
csoai-org/meok-stripe-acp-checkout-mcp
csoai-org/stripe-billing-mcp
ai.adramp/google-ads
co.pipeboard/google-ads-mcp
co.curie/commerce