Gazebo
    ServicesAgentsDocsSpecWritingPricing
    Log inSign up
    Log in

    Getting Started

    • Introduction
    • How Gazebo works
    • Core concepts
    • Quickstart

    Agent Access

    • Access profiles
    • Bearer tokens
    • Audit logs

    MCP

    • Overview
    • Cursor
    • Claude Code
    • Windsurf
    • Any MCP client
    • get_credential reference

    Open Standard

    • AIP Specification ↗

    Sharing Agents

    • Overview
    • Publishing an agent
    • The consent screen
    • Installing a shared agent
    • The identity stamp

    REST API

    • Authentication
    • Verification endpoint

    Security

    • Overview
    • Encryption model
    • Credential storage
    • Audit and compliance
    • Responsible disclosure
    Documentation

    Getting Started

    • Introduction
    • How Gazebo works
    • Core concepts
    • Quickstart

    Agent Access

    • Access profiles
    • Bearer tokens
    • Audit logs

    MCP

    • Overview
    • Cursor
    • Claude Code
    • Windsurf
    • Any MCP client
    • get_credential reference

    Open Standard

    • AIP Specification ↗

    Sharing Agents

    • Overview
    • Publishing an agent
    • The consent screen
    • Installing a shared agent
    • The identity stamp

    REST API

    • Authentication
    • Verification endpoint

    Security

    • Overview
    • Encryption model
    • Credential storage
    • Audit and compliance
    • Responsible disclosure
    DocsMCPget_credential reference

    The get_credential tool retrieves a plaintext credential from the Gazebo vault for a named service. Every call is logged in the audit trail regardless of outcome.

    Parameters

    ParameterTypeRequiredDescription
    servicestringYesThe service slug (e.g. "stripe", "github", "vercel")
    methodstringYesThe HTTP method you intend to use the credential for ("GET", "POST", "PUT", "PATCH", "DELETE")

    The method parameter is policy-enforced — declaring "POST" when you intend to make a write call is not optional. If your access profile doesn't permit POST on that service, the call is denied and logged.

    Success response

    On success, get_credential returns the plaintext credential as a string:

    get_credential({ service: "stripe", method: "GET" })
    → "sk_live_..."
    

    Use this value directly in your API call. Do not store it — fetch it again on the next request.

    Denial response

    If the agent is not permitted to access the service or method, get_credential returns a structured JSON object:

    {
      "status": "denied",
      "service": "stripe",
      "method": "DELETE",
      "allowed_methods": ["GET", "POST"],
      "reason": "Method DELETE is not permitted for service stripe",
      "next_action": "Update the agent's access profile to include DELETE, or use a permitted method."
    }
    

    On denial, do not retry without user intervention. The policy will not change between calls. Parse the response, tell the user what happened (including next_action), and stop.

    Not-found response

    If no credential is stored for the requested service:

    {
      "status": "not_found",
      "service": "stripe",
      "reason": "No credential stored for service stripe",
      "next_action": "Connect Stripe in the Gazebo dashboard under Settings → Services."
    }
    

    Error table

    HTTP statusstatus fieldMeaning
    200—Credential returned as plain string
    403deniedService not in access profile, or method not permitted
    404not_foundNo credential stored for this service
    401—Invalid or missing bearer token

    Recommended usage pattern

    1. get_identity()                           → confirm accessible services
    2. get_credential({ service, method })      → fetch the credential
    3. [make your API call using the credential]
    4. list_audit_events({ service, limit: 1 }) → optionally confirm it was logged
    

    Do not store the returned credential in memory beyond the scope of the current API call. Treat it as ephemeral.

    Explore Gazebo

    Gazebo gives each agent an independent access boundary around your agent credentials, with controls for approval, auditing, and revocation.

    Scoped identities for AI agentsGive every agent only the credentials it needs.Credential security and audit controlsSee how access is protected, recorded, and revoked.
    Any MCP clientAIP Specification ↗
    Gazebo

    IAM for AI agents. Scoped credentials, access policies, and audit trails — without rotating keys.

    Product

    • Pricing
    • Status

    Explore

    • Services
    • Agents
    • Workflows
    • Integrations

    Content

    • Writing
    • Topics
    • Blog
    • Docs

    Free Tools

    • Scanner

    Company

    • About
    • hello@gazebohq.com
    • security@gazebohq.com

    © 2026 Gazebo. All rights reserved.

    PrivacyTermsSecurity