Authority
Bind the AI agent identity, permitted action, resource, value, destination, time window and required approval.
AI AGENTS, WITHOUT UNCHECKED POWER.
The authority system
for consequential AI work.
Fidacy lets AI agents execute payments, refunds, customer operations, data workflows and production changes inside explicit, enforceable boundaries.
Define the right. Enforce it at execution. Prove the decision independently.
DEPLOYED TODAYAI AGENTS→IN DEVELOPMENTPHYSICAL AI
BUILT FOR THE AGENT STACK YOU ALREADY RUN
Native integrations where they exist. Universal enforcement through MCP, SDK and API. Private prompts, files and tool arguments stay in your environment.
Works with the AI agents and frameworks your teams already run.
Native integrationMCP hostSDK / API
Claude CodeNative plugin
OpenClawNative pluginLangChainNative · JS + Python
OpenAI AgentsNative adapter
Vercel AI SDKNative middlewareMCPFidacy MCPUniversal server
CodexMCP hostCursorMCP host
Gemini CLIMCP host
GitHub CopilotMCP host
WindsurfMCP host
Hermes AgentMCP + hooks
OpenCodeMCP host
ClineMCP host
CrewAISDK / API
PydanticAISDK / API
Cloudflare AgentsSDK / API
Strands AgentsSDK / API
Microsoft Agent FrameworkSDK / API
Google ADKSDK / API
GrokBotAPI agentANY CUSTOM AGENTSDKAPIMCPUCPAP2A2ASTRIPEBREXGITHUBBITCOINPAYMENTSREFUNDSCRMEMAILFILESINFRASTRUCTURE
Authority Firewall for AI Agents
Watch the action stop before it becomes an incident.
Select an AI agent and a consequential action. Fidacy verifies identity, mandate, policy and request integrity before the connected executor receives permission to act.
1 / CHOOSE THE AI AGENT
2 / CHOOSE THE ACTION
Representative connected-enforcement replay. The payment path is available as a live signed verdict; every surface shown uses the same executor-side grant contract.Install it in your agent →
Firewall
Require a matching signed grant at the executor. No valid grant means no payment, email, export, refund or production change.
Evidence
Sign every allow and deny, preserve the policy version and request digest, then anchor the evidence outside the operational system.
Coverage
Show which AI agent actions are gated, observed, incomplete or outside control so security, legal and insurance teams see the real exposure.
If the AI agent is compromised
What can the attacker execute with the access you already granted?
Payments, supplier changes, data exports, credentials and production systems become attack paths when AI agent intent reaches them without an independent authority check.
01 / MONEY
Redirect the payment.
Change the payee, amount, invoice or currency inside a workflow that already has payment access.
02 / DATA AND SYSTEMS
Use the AI agent as the way in.
Export records, expose credentials or call production tools through permissions the organization granted itself.
03 / BINDING ACTIONS
Act in the company’s name.
Issue refunds, send commitments or change critical records before a human sees the consequence.
Production Authority Deployment
From exposed workflow to enforced production boundary.
One production contract takes the highest-exposure AI agent actions from scope to enforcement, evidence and ongoing operation.
01 / Map
Define the action surface.
Identify AI agents, executors, actions, owners, approval thresholds and the consequences that require hard enforcement.
02 / Enforce
Connect the real executor.
Require one matching grant before the protected system acts.
03 / Operate
Monitor control and preserve proof.
Track coverage, policy versions, approvals, evidence gaps and incident records.
One boundary. The complete authority cycle.
Block. Allow. Record. Anchor.
Most products observe risk after an agent acts. Fidacy identifies the agent, verifies its mandate, enforces the boundary before execution and produces independently verifiable evidence after every decision.
IDENTIFYAUTHORIZEDECIDEENFORCERECORDANCHOR
Stop what exceeds the mandate.
Fidacy Firewall and Spend Guard refuse altered payees, excessive amounts, replayed grants and unauthorized side effects before the connected system is called.
FIREWALLSPEND GUARDHARD GATE
Inspect enforcement →
Release exactly what was authorized.
KYA binds the workload identity. A signed mandate fixes the action, resource, amount, destination and duration. One matching request receives one executable grant.
KYAMANDATESONE-TIME GRANTS
Build authority →
Preserve the decision and its coverage.
Every ALLOW and DENY is signed. Continuous Control Monitoring shows whether the path was gated, merely observed, incomplete or outside current evidence.
SIGNED JWSCONTROL COVERAGEINCIDENT PACK
See Control Coverage →
Put the evidence outside the argument.
Signed records enter append-only history, become Merkle checkpoints and receive an external Bitcoin timestamp that any third party can verify.
HASH CHAINMERKLEBITCOIN
Verify the proof →Three consequences. Three verifiable records.
Prove the money, the message and the document.
The action is only half the risk. Fidacy preserves neutral evidence of what moved, what was said and which exact artifact existed, without taking custody of the payment, transcript or file.
01 / PAYMENT AUTHORITYHARD GATE
No valid grant.
No money moves.
Bind payee, amount, invoice, currency and expiry. Where the payment rail is connected through Fidacy, an altered, excessive or replayed request is refused before settlement.
REQUESTUS$4,280
MANDATEPAYEE + CAP MATCH
ALLOW · ONE USE02 / CONVERSATION RECEIPTSLOCAL HASHING
Prove exactly what the chatbot said.
Hash each message locally, anchor the final session digest through Fidacy and give both sides a receipt they can verify. The transcript stays inside your infrastructure.
CUSTOMER
My card was charged twice. Can you refund the second US$900 payment?
ACME SUPPORT
Yes. I approved the full US$900 refund. You’ll see it within two business days.
SESSION DIGEST SEALED
2 verifiable receipts issuedTranscript retained by Acme03 / ARTIFACT RECEIPTSBITCOIN CHECKPOINT
Prove the file has not changed.
Anchor the hash of a prescription, insurance claim, contract, invoice, image or recording. Fidacy receives the digest, never the source file.
MEDICAL PRESCRIPTIONSHA-2568d8c3f…a217
VERIFIED
Insurance infrastructure
The evidence layer that makes AI agent risk insurable.
Fidacy does not price risk or issue policies. It gives underwriters a defensible view of which controls were operating, which actions were hard-gated, where coverage stopped and what happened in a specific incident.
01UNDERWRITEControl Coverage
Current boundaries, policy versions, connector state and evidence gaps.
02CONDITIONVerified controls
Require hard-gated actions and current evidence for protected workflows.
03ADJUDICATEIncident Pack
Identity, mandate, signed decision, receipt, chain position and checkpoint.
Primary sources, not predictions
The liability is not a thesis anymore. It is on the record.
Courts and regulators in four jurisdictions reached the same practical conclusion: an organization remains responsible for the automated action it deploys.
THE VERIFIABLE RECORD4 CONTROL LAYERS
ONE EVENT · FOUR LAYERSChange the record and the public verification fails.
CONTROL COVERAGE · LIVE BOUNDARIESContinuous control monitoring
Know where the control is real, and where the evidence stops.
Fidacy separates a hard gate from a heartbeat, current coverage from historical proof and a complete trail from a telemetry gap.
GATEDA verified execution boundary enforced the grant.
OBSERVEDA current authenticated connector is reporting.
LIMITEDThe latest evidence trail is incomplete.
NO EVIDENCEFidacy will not claim protection it cannot prove.
Independent by design
The party inside the transaction should not certify itself.
Fidacy is neutral to the model, agent framework, payment rail and system of record. The proof can be checked without calling us.
FIDACY INCIDENT PACK
One event. Every fact a third party needs.
Decision, agent identity, governing mandate, policy version, receipt, chain position and external checkpoint in one portable package for the owner, auditor, insurer or regulator.
See the evidence package →SIGNEDBoth ALLOW and DENY carry a public-key verifiable JWS.
CHAINEDEach append-only record commits to the record before it.
ANCHOREDMerkle checkpoints are externally timestamped against Bitcoin.
PORTABLEIncident Packs package one decision for audit, insurance or dispute review.
Agent-agnostic by design
The Authority Firewall for AI Agents. Simple to deploy. Difficult to bypass.
Start through an SDK, MCP host or API. One compact layer fits the stack you already run while private prompts, files and tool arguments remain inside your environment.
Claude, Cursor, Codex and more
One local server for agent tools and action boundaries.
npx -y @fidacy/mcpJavaScript and Python
Wrap the tool so a denied call never executes.
@fidacy/langchainGate the tool call
Enforce between model intent and the external action.
@fidacy/openai-agentsNative agent hooks
Observe sessions, gate actions and export independent proof.
@fidacy/openclaw-pluginFrom AI agents to autonomous systems
One authority architecture.From AI agents to autonomous machines.
Fidacy already implements the core authority chain in software: identity, signed mandates, pre-action decisions, enforceable grants, revocation and independently verifiable evidence.
AI AGENT ACTIONS
Money · data · communications · enterprise systems
Already implemented at the software authority layer.
EDGE AUTHORITY
Gateway · device identity · local enforcement · safety validation
Mission-level authority for robots, drones, vehicles and safety-critical autonomous infrastructure, without entering the motor-control loop.
≈90% is an architecture-reuse estimate, not physical-product readiness or safety certification.
Intelligence decides what to do.Authority decides whether it may happen.
Contributing to trustworthy agentic AI
Public contributionand trust.
European Commission AI Pact, Pillar I. Singapore Model AI Governance Framework. Fidacy contributes implementation practices for trustworthy AI and AI Act readiness.
PUBLIC POLICY CONTRIBUTION · 2026
SINGAPORE
Fidacy submitted a production-backed enforcement case study to Singapore's Model AI Governance Framework for Agentic AI consultation.
Read the technical contribution →
AI PACT · PILLAR I · 2026
EUROPEAN COMMISSION
Fidacy has joined Pillar I, contributing implementation practices for trustworthy AI and AI Act readiness.
View the AI Pact →Enterprise Action-Risk Assessment
Put your highest-risk AI agent actions behind a production boundary.
Map the exposed actions, define signed authority and leave with a deployment scope for your AI agents, executors, policies and evidence requirements.