OpenAI / Codex

Connect Gazebo to OpenAI Codex using remote HTTP MCP and an agent bearer token. OpenAI's Responses API and ChatGPT web have separate setup and authentication requirements.

Codex CLI and IDE

Create a dedicated agent at Gazebo Agents. Set GAZEBO_AGENT_TOKEN in the environment inherited by Codex, then add this to ~/.codex/config.toml or a trusted project's .codex/config.toml:

[mcp_servers.gazebo]
url = "https://app.gazebohq.com/api/mcp"
bearer_token_env_var = "GAZEBO_AGENT_TOKEN"

The setting contains the environment variable's name, not its value. Do not put a real token in a committed file. Restart the client after changing its environment.

Run codex mcp list to check the configuration and use /mcp in the Codex terminal interface to inspect the connection. Ask it to call get_identity first, then verify that get_credential and list_audit_events are available.

This configuration uses a pre-issued agent token, not codex mcp login gazebo. Gazebo also offers MCP OAuth using CIMD or DCR; do not mix OAuth login with the manual bearer-token configuration above. See OpenAI's current MCP configuration guide.

OpenAI Responses API

The Responses API supports remote Streamable HTTP MCP with an authorization value. This is a separate cloud-hosted integration, not proof that the Codex client works.

For an initial identity-only check, configure the following tool object in your server-side Responses API request:

{
  type: "mcp",
  server_label: "gazebo",
  server_url: "https://app.gazebohq.com/api/mcp",
  authorization: process.env.GAZEBO_AGENT_TOKEN,
  allowed_tools: ["get_identity"],
  require_approval: "always"
}

Supply the raw agent token in authorization; do not prepend Bearer there. The API constructs the bearer header. Your OpenAI API key authenticates the Responses API request and is separate from the Gazebo agent token.

Choose a model that supports remote MCP. Review any mcp_approval_request before sending an approval response. An approval request alone is not a successful tool call: confirm the resulting mcp_call has no error and returns the intended identity. See OpenAI's MCP tool guide.

Only enable get_credential after you understand the trust boundary. OpenAI's infrastructure receives tool results, including actual provider keys if credential retrieval is enabled; the key may also enter model context and response history. Begin with a fictional key, never a production credential.

ChatGPT web and plugins

Do not paste Codex's TOML into ChatGPT web or assume that a ChatGPT subscription provides the same MCP configuration controls. OpenAI's current hosted plugin documentation expects OAuth 2.1 for authenticated MCP servers.

Gazebo offers MCP OAuth discovery, S256 PKCE and public-client registration through CIMD or DCR. A hosted integration must support one of these registration methods and allow users to approve selected keys in Gazebo; OAuth support alone does not guarantee compatibility with every ChatGPT connector. These bearer-token examples are not ChatGPT web setup instructions. See OpenAI's authentication guide for current product requirements.

Safe verification

Use a dedicated test agent with a fictional service key. Check identity, allowed retrieval, denied retrieval, audit events and revocation before using real credentials.

The requested HTTP method governs credential retrieval, not subsequent provider calls. Provider key permissions govern those calls. Revoking Gazebo access prevents future retrieval; it does not invalidate a key already returned.