agents/apiTHE ENCYCLOPEDIA
Tools & integrations

Vaults & MCP authentication

Keep reusable MCP credentials separate from agent definitions and attach them to authorized sessions.

Credential store
Session vault IDs
Matching MCP URL
Authorized server call

Separate configuration from secrets

A reusable agent stores behavior and tool configuration. Reusable credentials belong in a vault. Attach the vault ID when creating a session. This lets a credential be managed without placing the secret directly in a saved agent definition.

Understand the connection boundary

Vault authentication is for service-origin MCP connections. Credentials are matched to the server URL. If multiple credentials match, select the intended credential explicitly. Environment-origin connections need a different authentication approach.

Scope the credential

Use the narrowest downstream permissions needed by the task and restrict the exposed tool set. A vault stores a credential; downstream permissions still determine what the tool can access. Separate tenants and revoke access when it is no longer needed.

Keep secrets out of generated code

Do not put access tokens in prompts, repositories, examples, or sandbox files. A credential injected into an environment can be read by agent-generated code. A trusted broker can inject credentials outside that boundary.

Read the official reference

Check the source for current API fields, account requirements, and service limits.

OpenAI: vaults

23 matching topics

What is the OpenAI Agents API?FoundationsAgents API vs Agents SDK vs Responses APIComparisonsAgents API quickstartGetting startedSessions, turns & durable stateCore conceptsHosted vs self-hosted sandboxesInfrastructureConnect MCP servers to Agents APITools & integrationsFunction calling & application toolsTools & integrationsMulti-agent orchestrationCore conceptsStreaming, webhooks & event handlingIntegration guidesFiles, outputs & published artifactsCore conceptsVaults & MCP authenticationTools & integrationsAgent security & credential boundariesProductionTracing, usage & debuggingProductionAgents API pricing & cost planningProductionOpenAI Agents API with PythonGetting startedAgents API with TypeScript & Next.jsIntegration guidesWhat is the OpenAI Agents SDK?FoundationsResponses API in the agent stackFoundationsAgent Skills & SKILL.mdTools & integrationsProgrammatic Tool CallingTools & integrationsRAG, file search & vector storesTools & integrationsWeb search & source citationsTools & integrationsChatKit & Agent BuilderIntegration guides
K to open Esc to close