Skip to content
    Gaincontrol

    How Zino works.

    The technical reference for the platform and security engineers who will run Zino: where it sits, what it intercepts, how credentials move, what it plugs into, and what a four-week pilot looks like.

    At a glance

    Where it runs
    In-process SDK in each workload. No sidecar, no network hop for policy.
    Identity
    A workload identity from SPIRE, checked by two-layer attestation.
    Policy
    Signed WASM policy from one Policy Server, evaluated on the OPA schema.
    Intercepts
    REST/HTTP, Shell and MCP over stdio, SSE and HTTP.
    Secrets
    Brokered from your vault and injected per call. The agent holds none.
    Audit
    Every decision is written to a hash-chained log.

    Two planes: one decides, one enforces.

    The Policy Server is the single signing authority for the fleet. The Zino SDK runs in-process at every workload, with no sidecar and no network hop for policy evaluation, gating REST, Shell, and MCP calls at the trust boundary before anything leaves.

    Zino architecture: control plane and data planeA Policy Server acts as the single control-plane authority, provisioning identity and signed policy to a fleet of workloads. Each workload runs the Zino SDK in-process, gating its REST, Shell, and MCP calls at the trust boundary before anything leaves. An enterprise vault feeds credentials through the Policy Server, which the SDK injects per call. The agent never holds a long-lived token.BROKERS SECRETSSPIRE ID +SIGNED WASM POLICYSPIRE ID +SIGNED WASM POLICY↑ HASH-CHAINED AUDIT↑ HASH-CHAINED AUDIT
    Enterprise Vaultyour existing secrets store
    Policy ServerControl plane · one authority
    WORKLOAD

    Zino SDK

    in-process · no sidecar · credential injected, never held

    TRUST BOUNDARY
    REST / HTTPchecked here
    Shellchecked here
    MCPchecked here
    WORKLOAD

    Zino SDK

    in-process · no sidecar · credential injected, never held

    TRUST BOUNDARY
    REST / HTTPchecked here
    Shellchecked here
    MCPchecked here
    … AND EVERY OTHER WORKLOAD IN THE FLEET

    Three surfaces. One policy interface.

    REST, Shell, and MCP all speak different dialects. Zino intercepts all three with a single policy engine.

    Surface
    REST / HTTPrequests · httpx · aiohttp
    What it sees
    A CallContext (method, host, path, tool, and arguments) built for every outbound HTTP call.
    Policy decides
    Re-authorized on the same OPA schema. A call to an unapproved host is denied before it is sent.
    Surface
    Shelltool-type aware
    What it sees
    Execution type classified as HTTP, shell, or MCP; shell commands registered straight from policy.
    Policy decides
    Pre-execution callbacks can inspect or veto before any command runs.
    Surface
    MCPclient-session wrap
    What it sees
    Tool name, schema, and arguments on every outgoing MCP call, across stdio, SSE, and HTTP transports.
    Policy decides
    Each call authorized before it leaves the agent, closing the gap to un-vetted MCP servers.

    Zino controls secrets, not the app.

    Tokens are injected at call time, configuration is encrypted at rest, and your enterprise vault stays the source of truth.

    Credential broker · platform-controlled, per call

    1. App makes an outbound call. Any Authorization header it set is stripped.

    2. The interceptor fetches the credential scoped to (host, path, method, tool).

    3. The platform token is injected, decrypted in memory via a per-agent HKDF key.

    The agent never holds a long-lived API token.

    Fronts your enterprise vaults

    • HashiCorp Vault
    • OpenBao
    • AWS Secrets Manager
    • Azure Key Vault
    • Google Cloud
    • CyberArk Conjur
    • Thales
    • Infisical

    Framework adapters

    Zino ships adapters for these agent frameworks. One SDK call instruments an agent for policy enforcement and audit.

    • LangChain
    • CrewAI
    • AutoGen
    • Claude Tool Use
    • LlamaIndex
    • OpenAI Assistants
    • Semantic Kernel

    Four weeks. One agent fleet. Real policy, enforcing.

    A bounded pilot with one sponsor and no infrastructure lift. Walk away with identity, attestation, and a real authorization layer in production.

    1. Week 0

      Setup

      Policy Server in your environment. Trust root provisioned. SPIRE Agent rolled to one fleet. No app changes yet.

    2. Week 1

      Identity

      One initialize() in the pilot agent. Two-layer attestation working end-to-end. Shadow mode: observe only.

    3. Week 2

      Policy

      Interception live across REST, Shell, MCP. Allow/deny enforced. Audit log streaming. Slack alerts on blocks.

    4. Week 3

      Callback

      Pre-execution callbacks wired in. App-specific rules enforced. Joint readout + rollout plan for the next two teams.

    Pilot commitment · 4 weeks · 1 sponsor · 1 fleet · no infrastructure lift