Standard
  • Docs
  • Examples
  • Pricing
  • About

Get started

  • Overview
  • How Standard works
  • Run your first task
  • Connect
  • Join a Space

Build

  • Examples
  • Operation profiles
  • Integration reference

Concepts

  • Inputs and permissions
  • Accounts and billing
  • Results and lifecycle
  • Verification checks
  • Follow-on tasks
  • Cleanup

Security

  • Security model
Documentation menu

Get started

  • Overview
  • How Standard works
  • Run your first task
  • Connect
  • Join a Space

Build

  • Examples
  • Operation profiles
  • Integration reference

Concepts

  • Inputs and permissions
  • Accounts and billing
  • Results and lifecycle
  • Verification checks
  • Follow-on tasks
  • Cleanup

Security

  • Security model
Standard

Managed confidential execution for sensitive functions.

© 2026 Standard Runtime, Inc. All rights reserved.

  • Security
  • Docs
  • Examples
  • Pricing
  • FAQ
  • About
  • Contact
  • Terms
  • Privacy
  • Cookies
  • Docs
  • Examples
  • Pricing
  • About
  • Get started

    • Overview
    • How Standard works
    • Run your first task
    • Connect
    • Join a Space

    Build

    • Examples
    • Operation profiles
    • Integration reference

    Concepts

    • Inputs and permissions
    • Accounts and billing
    • Results and lifecycle
    • Verification checks
    • Follow-on tasks
    • Cleanup

    Security

    • Security model

    Get started

    • Overview
    • How Standard works
    • Run your first task
    • Connect
    • Join a Space

    Build

    • Examples
    • Operation profiles
    • Integration reference

    Concepts

    • Inputs and permissions
    • Accounts and billing
    • Results and lifecycle
    • Verification checks
    • Follow-on tasks
    • Cleanup

    Security

    • Security model

    Integration reference

    Reference for Standard’s Control transaction, CLI, MCP transport, application bindings, participant custody, and execution evidence.

    Start with the interface you use. MCP, the SDK and the CLI are entry points to the same Control transaction: they share Standard’s account, permission and verification model. Connecting through any of them identifies the caller; it grants no access to another participant’s assets, and each operation still needs every required owner’s authority.

    Your goalStart here
    Connect an existing agentConnect through MCP
    Use Standard from an applicationApplication integration
    Run or inspect work from a terminalCLI guide
    Understand the transaction and its contractsProtocol reference

    Connect through MCP

    An agent in an MCP-compatible client discovers the tasks available to its account, submits operation requests and receives verified results. The remote endpoint is https://standardruntime.com/api/mcp (Streamable HTTP), and connecting requires OAuth authorization of your account. MCP does not give Standard custody of the agent’s files. See Connect.

    Application integration

    The Node.js and browser application bindings let an application submit operation requests and receive verified results from its own code. Verification runs inside the SDK, in your environment, before your code receives the result.

    CLI guide

    The CLI sets up encrypted storage, key access and permissions, and submits tasks from terminals and scripts. Use it for participant-side preparation and review workflows.

    Protocol reference

    Every entry point carries the same transaction underneath: an operation request checked against the accepted profile, owners’ permissions, and account limits; protected execution; and a result with evidence the receiving client verifies.

    Private inputs never travel through MCP or any other entry point. Entry points carry encrypted-input references, and the confidential runtime retrieves the inputs from the owners' storage.

    Always use the tools, methods and schemas your authenticated account actually exposes. Do not invent task names, fields or capabilities.

    Operation requests

    An operation request describes one task under an accepted operation profile. It contains:

    PartContents
    Profile and Space revisionThe exact accepted profile and Space governance revision for this operation.
    Code or modelA reference to the approved code or model and its exact digest.
    PreviousOperation profilesNextInputs and permissions

    On this page

    • Connect through MCP
    • Application integration
    • CLI guide
    • Protocol reference
    • Operation requests
    • Runtime and contributions
    • Formats and limits
    • Errors
    • For agents
    InputsEncrypted-input references, each with its expected digest.
    Requested resultThe result type and recipient, which must fall within the owners' release rules.
    ParametersTask-specific options, within the limits the task allows.
    Resource requestThe compute, memory and duration the task needs, within your account's limits.
    Idempotency keyThe operation’s supported key for safe resubmission and reconciliation. Follow its documented scope and retention behavior.

    Standard checks the request against the accepted profile, owners' permissions, supported formats, and account limits before admission. An invalid request is rejected with a reason.

    Runtime and contributions

    The executable workload is an approved Wasm module. Code, models, and data used by that workload must match its supported formats and the runtime's limits. An arbitrary container, model server, or complete agent loop is not a supported workload merely because it can run elsewhere.

    Formats and limits

    Every task runs within declared limits:

    • Approved Wasm workloads must declare a supported executable interface. Their code, model, and data inputs must fit the accepted profile.
    • Tasks run in bounded execution windows, not as continuously hosted services. Each task declares its duration, memory, fuel, and input and output sizes, and the runtime enforces them.
    • Organization limits such as concurrency, total runtime and resource ceilings are agreed for your organization. Each entry point reports which limit applied when a request exceeds one.

    A request that exceeds a limit is rejected before it runs. Runtime resource limits also apply during execution. Reusing a Space does not provide resumable private working state or a continuously running task.

    Errors

    Errors name the lifecycle stage that failed and a stable reason code, so your integration can decide whether to fix, escalate or retry. The categories match Results and lifecycle: missing permission, key access refused, input mismatch, unsupported or over limit, and verification failed. Follow the operation’s status and retry guidance for transient capacity problems. Reconcile uncertain external effects before resubmission.

    For agents

    The plain-text guide at /llms.txt gives agents the same product description and instructions as these pages.