CausalLayer is a remote MCP server that gives an AI agent 10 tools, among them evaluate_prospective_response, extract_incident, get_anchor_status. It answers at https://mcp.faultkey.com/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 24 October 2026, succeeded.
Deterministic AI liability attribution with Bitcoin-anchored proof certificates.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
evaluate_prospective_response | Deterministic prospective-evaluation gate (FK-METHOD-2026-006). Pass a ProposedAction BEFORE the agent delivers a response; receive one of three verdicts: 'allow', 'require_revision' (with specific factor-keyed directives), or 'block'. Uses Inputs: action, overrides |
extract_incident | Claude-powered structured extractor. Parses unstructured text (news articles, court filings, emails, PDFs, incident reports, logs) into the typed JSON schema required by submit_incident. Returns a ready-to-submit incident object with extrac Inputs: text, context_hint, jurisdiction_hint |
get_anchor_status | Return the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE. Inputs: version |
query_issuer_registry | Return the CausalLayer issuer registry, or one issuer record. The registry lists all trusted public-key fingerprints, key algorithms, validity windows, and the anchor-log repo for each active issuer. FREE — no API key required. Inputs: issuer_id |
query_jurisdiction_overlay | Multi-jurisdiction overlay (FK-METHOD-2026-004). Given a canonical attributable apportionment (party-id -> share), the union of all jurisdiction role tags on each actor, and the union of jurisdiction-specific flags, return side-by-side post Inputs: attributable, actors, flags, jurisdictions, primaryJurisdiction |
simulate_remediation | Counterfactual remediation simulator. Given a certificate's verdict + fourFactorScoring + agents and a list of remediation IDs from the FK-METHOD-2026-003 catalog, return the apportioned shares each remediation would have produced (in isola Inputs: verdict, fourFactorScoring, agents, remediations |
submit_incident | Submit an AI incident for deterministic causal liability attribution. Returns a signed CausalCertificate, per-agent liability allocation, evidence-chain completeness, regulatory mapping, and (where keys are configured) a Bitcoin-anchored pr Inputs: title, description, category, severity, jurisdiction, financial_impact_cents |
submit_otel_trace | Convert an OpenTelemetry OTLP JSON trace into a FaultKey incident and return the same deterministic CausalCertificate as submit_incident. Each span becomes an event; service.name groups spans into agents; W3C trace_id and span_id propagate Inputs: title, otlp, category, jurisdiction, financial_impact_cents, currency |
verify_certificate | Independently verify a CausalCertificate end-to-end (signature, Merkle integrity, issuer status against the registry). Cost: 1 credit. In production env, certificates from non-active issuers are rejected. Inputs: certificate |
verify_certificate_recompute | Independently re-derive a CausalCertificate from its canonical input and compare byte-for-byte against the claimed certificate. This is the strongest verification path: it requires no trust in the issuer or signing key. Cost: 1 credit (same Inputs: certificate, canonicalInput |
Every block below points at https://mcp.faultkey.com/mcp. Pick your client and copy.
claude mcp add --transport http causallayer https://mcp.faultkey.com/mcp
{
"mcpServers": {
"causallayer": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.faultkey.com/mcp"]
}
}
}{
"mcpServers": {
"causallayer": {
"url": "https://mcp.faultkey.com/mcp"
}
}
}{
"servers": {
"causallayer": {
"type": "http",
"url": "https://mcp.faultkey.com/mcp"
}
}
}{
"context_servers": {
"causallayer": {
"url": "https://mcp.faultkey.com/mcp"
}
}
}{
"mcpServers": {
"causallayer": {
"serverUrl": "https://mcp.faultkey.com/mcp"
}
}
}{
"mcpServers": {
"causallayer": {
"url": "https://mcp.faultkey.com/mcp"
}
}
}name: CausalLayer
version: 0.0.1
schema: v1
mcpServers:
- name: CausalLayer
type: streamable-http
url: https://mcp.faultkey.com/mcp{
"mcpServers": {
"causallayer": {
"httpUrl": "https://mcp.faultkey.com/mcp"
}
}
}{
"mcpServers": {
"causallayer": {
"type": "http",
"url": "https://mcp.faultkey.com/mcp"
}
}
}{
"mcpServers": {
"causallayer": {
"url": "https://mcp.faultkey.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.faultkey.com%2Fmcp&type=streamable_http&id=causallayer&name=CausalLayer
It answered our last check on 24 October 2026 in 383 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 21 September 2026: evaluate_prospective_response, extract_incident, get_anchor_status, query_issuer_registry, query_jurisdiction_overlay, simulate_remediation, submit_incident, submit_otel_trace, and 2 more.
It answered our last check on 24 October 2026 in 383 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.faultkey.com/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.smq9sn5jck-coder. Endpoint host: mcp.faultkey.com. ARD identifier: urn:air:io.github.smq9sn5jck-coder:mcp:causallayer.
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.