FaultKey · CausalLayer

smq9sn5jck-coder/causallayer-mcp

If you're building AI systems where liability matters and need deterministic fault allocation across vendor/deployer/user, this server exposes four CausalLayer tools through MCP. The main one is submit_incident, which returns a signed, Bitcoin-anchored certificate splitting blame using closed-form math instead of LLM scoring. You also get verify_certificate for third-party proof checking, get_anchor_status for Merkle batch lookups, and query_issuer_registry for trusted key fingerprints. It runs on Cloudflare Workers with edge-enforced PII scanning and evidence requirements. The demo endpoint is rate-limited at 5 calls per IP daily, but you can self-host or connect to the paid upstream engine for production loads.

GitHub stars: 2
tools: 10
transport: HTTP
last updated: May 16, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp --name causallayer-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http causallayer-mcp https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 10 tools

Verified live against the running server on Nov 6, 2026.

submit_incidentSubmit 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 proof. Cost: 50 credits. Three guardrai...11 params

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 proof. Cost: 50 credits. Three guardrai...

Parameters* required

agents*array

categorystring

currencystring

descriptionstring

deterministic_only*boolean

G2: Must be true. Acknowledges CausalLayer is deterministic and not LLM-based.

events*array

financial_impact_centsvalue

jurisdictionstring

pii_acknowledgedboolean

G1: Set to true ONLY if caller has confirmed PII handling is permitted by their data agreement. False payloads with detected PII will be rejected.default: false

severitystring

one of low · medium · high · critical

title*string

verify_certificateIndependently 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.1 params

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.

Parameters* required

certificate*object

CausalCertificateV1 object as returned by submit_incident.certificate

verify_certificate_recomputeIndependently 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 price as verify_certificate). Return...2 params

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 price as verify_certificate). Return...

Parameters* required

canonicalInput*object

The original incident body that produced the certificate — the same JSON originally posted to submit_incident or submit_otel_trace.

certificate*object

The CausalCertificate object claimed by the issuer.

submit_otel_traceConvert 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 as evidence pointers on the causal gr...8 params

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 as evidence pointers on the causal gr...

Parameters* required

categorystring

currencystring

deterministic_only*boolean

G2: Must be true. Acknowledges CausalLayer is deterministic.

financial_impact_centsvalue

jurisdictionstring

otlp*object

OTLP JSON payload with resourceSpans[]. See https://opentelemetry.io/docs/specs/otlp/#json-protobuf-encoding

pii_acknowledgedboolean

G1: Set to true ONLY if PII handling is permitted by your data agreement. OTLP traces frequently leak user/session ids in attributes.default: false

title*string

simulate_remediationCounterfactual 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 isolation) and the composite shares if the...4 params

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 isolation) and the composite shares if the...

Parameters* required

agents*array

Agent registry (id + type) so the simulator can map remediation targetType to specific party ids.

fourFactorScoring*object

The fourFactorScoring block from the CausalCertificate.

remediations*array

List of remediation IDs from the catalog (e.g. vendor_adversarial_eval_suite, deployer_human_in_loop). Each may optionally pin appliedToParty to a specific agent id.

verdict*object

The verdict block from the CausalCertificate.

query_jurisdiction_overlayMulti-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-overlay shares for AU, EU, US, UK, C...5 params

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-overlay shares for AU, EU, US, UK, C...

Parameters* required

actors*array

All actors with the union of jurisdiction-specific role tags. EU and AU tags coexist on the same actor record.

attributable*object

Canonical pre-overlay apportionment as { party_id: share }. Sum should approximate 1.0; the function renormalises within tolerance.

flags*object

Union of jurisdiction-specific flags. AI Act / PLD flags drive the EU overlay; ACL / CPS 230 / VAISS flags drive the AU overlay.

jurisdictionsarray

Optional subset to compute. Defaults to all five.

primaryJurisdictionstring

Engine-level jurisdiction string (e.g. 'EU', 'DE', 'AU'). Used by the EU gate to decide engagement.

evaluate_prospective_responseDeterministic 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 the same four-factor engine that iss...2 params

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 the same four-factor engine that iss...

Parameters* required

action*object

The structured ProposedAction to evaluate.

overridesobject

Optional per-call threshold override. Rationale REQUIRED for audit.

get_anchor_statusReturn the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE.1 params

Return the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE.

Parameters* required

versionstring

Optional anchor version, e.g. '2026-05-16-v1.6.4-simulation-calibration'.

query_issuer_registryReturn 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.1 params

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.

Parameters* required

issuer_idstring

Optional issuer id, e.g. 'causallayer-prod-2026-q2'. If omitted, returns the full registry.

extract_incidentClaude-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 extracted agents, events, severity, jurisdi...3 params

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 extracted agents, events, severity, jurisdi...

Parameters* required

context_hintstring

Optional hint about the source type (e.g., 'court filing', 'news article', 'internal incident report') to improve extraction accuracy.

jurisdiction_hintstring

Optional ISO country code hint if the jurisdiction is known (e.g., 'AU', 'US', 'EU').

text*string

Unstructured text to extract from. Can be a news article, court filing, incident report, email, PDF text, log output, or any description of an AI incident.

Readme

FaultKey · CausalLayer MCP Server

View the full README on GitHub

Details

Repository: github.com/smq9sn5jck-coder/causallayer-mcp
Website: faultkey.com
Category: Finance & Commerce
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related Finance & Commerce MCP servers

View all

Knowmintsou0327/knowmintAI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.2stars

Paradex Tradingtradeparadex/mcp-paradex-pyMCP server for Paradex perp trading. Market data, accounts, orders, positions, and vaults.2stars

Agentfolio Mcp Server0xbrainkid/agentfolio-mcp-serverAI agent identity verification via SATP on Solana. Trust scores and on-chain attestations.1stars

Safebot Chatalexkirienko/safebot-chatEnd-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.1stars

Signaldaemonbevanding/signaldaemonNarrative & signal intelligence for AI agents: crypto/AI/macro convergence & divergence.1stars

Marginscflorczyk9/marginsUse your Claude Pro/Max subscription on your Obsidian vault. Reads markdown, proposes writes.1stars

FaultKey · CausalLayer

Install

Tools

Readme

FaultKey · CausalLayer MCP Server

Details

More from smq9sn5jck-coder

Related Finance & Commerce MCP servers