01 / BEFORE THE ACTION
Establish the identity.
Connect each request to a registered agent, its verified identity, and the organization it belongs to.
Know your agents. Govern their tools. Keep people in control.
Your agents can read, write, and change systems. Aphura verifies, checks, and records every action.
01 / BEFORE THE ACTION
Connect each request to a registered agent, its verified identity, and the organization it belongs to.
02 / AT THE BOUNDARY
Evaluate policy, tool integrity, sensitive data, and action budgets. Allow, require approval, or block the call.
03 / AFTER THE DECISION
Record decisions, approvals, and outcomes reported by the gateway in a connected audit trail.
Identity, permissions, approvals, inspection, budgets, and audit evidence in one control layer.
See registered agents, their owners, verified identities, and the systems they can access.
IDENTITY & INVENTORYApply signed policies and scoped permissions to the tool calls your agents make at runtime.
POLICY & PERMISSIONSRequire an independent person to approve a sensitive operation and its exact arguments.
HUMAN APPROVALSCheck tool definitions, detect sensitive data, and inspect traffic at the MCP gateway.
TOOL GOVERNANCE & DATA CONTROLSSet action budgets, investigate exposure, and suspend an agent’s access through Aphura.
BUDGETS & RESPONSEConnect decisions, approvals, and reported outcomes in a tamper-evident audit trail.
AUDIT & INVESTIGATIONConnect your agents, choose what they can use, and let Aphura check and record every action.
Give each agent a verified identity, then route all its tool calls through Aphura.
Grant included Azure tools or your own MCP servers, with access that expires.
Apply signed policy and action budgets. Send sensitive calls for human approval.
Trace every decision and outcome in a tamper-evident ledger you can search.
Let permitted work continue, send sensitive operations for approval, and block unsafe actions.
A registered agent requests a tool it has permission to use.
The call meets policy and stays within the agent’s action budget. Aphura authorizes the handoff and records the reported outcome.
Verify the requesting agent and its organization, then check the identity and permissions behind the action.
Check signed policy, reviewed tool definitions, sensitive data, and action budgets before allowing a tool call.
Allow permitted actions, require approval for the exact operation, or block calls that cross a defined boundary.
Connect each policy decision and authorized handoff to the gateway’s reported result in the audit trail.
Every plan includes the Aphura Agent Model, powered by OpenAI GPT-6 Luna on Microsoft Foundry in US regions.
Point any OpenAI-compatible SDK at Aphura and call aphura-agent-1 as is.
Prompts and completions are never stored, and every call stays in US regions.
Secrets are blocked, and every model call is recorded in the Aphura audit trail.
Open-source MCP servers you run yourself, reviewed before publication and governed on every call.
Each server is tied to an exact, reviewed commit of its public source repository.
Only MIT or Apache-2.0 servers that you host in your environment are admitted.
Tool definitions are reviewed and pinned. A changed tool is held for a new review.
The same policy, approvals, budgets, and audit trail apply to every server call.
Govern agent access, review sensitive actions, and investigate every decision in one place.
Connect verified agent identities to scoped permissions and signed policies for all approved tool access.
Require a person to review and approve the exact operation before a sensitive tool request can proceed.
Connect requests, approvals, and reported outcomes in an audit trail your team can investigate.
Enforcement runs inside your Azure network, next to your agents. Subscribe through Azure Marketplace.
The gateway and policy checks run in your own Azure virtual network, right next to your agents. Aphura hosts and updates the console, sign-in, approvals, and policy management for you.
The full platform runs in your own Azure subscription, and the Aphura Agent Model runs on your own Microsoft Foundry endpoint. Only usage reports ever leave your subscription, for billing.
Choose your monthly action volume. Every plan includes unlimited agents and the Aphura Agent Model.
$499/ month
Starter includes 100,000 governed actions per month, shared across every agent in your account.
Actions
One governed action is one tool call Aphura evaluates, allowed or blocked. No seat charge for adding an agent.
Model
The Aphura Agent Model is included, with no separate Aphura model charge. Ledger entries are included too.
Give agents a clear boundary. Give your team a clearer view.
Talk to sales