openaiCodex

Bubbling...

Connect Dstl8 to OpenAI Codex (CLI, VS Code extension, or Desktop app) for observability access while coding.

Prerequisites

Setup (CLI)

The quickest way is via the CLI:

codex mcp add Dstl8 --env DSTL8_TOKEN=<your-token> -- npx -y mcp-remote https://<org_id>.app.dstl8.ai/mcp --header "Authorization: Bearer <your-token>"

Replace <org-id> and <your-token> with your credentials from Settings → Integrations → MCP.

Setup (config file)

Codex stores MCP config in ~/.codex/config.toml. For project-scoped config, use .codex/config.toml in your project root.

If your Dstl8 MCP endpoint supports direct HTTP connections:

[mcp_servers.Dstl8]
url = "https://<org_id>.app.dstl8.ai/mcp"
bearer_token_env_var = "DSTL8_TOKEN"

Then set the environment variable in your shell profile (.bashrc, .zshrc, etc.):

Option B: Via mcp-remote

If direct HTTP doesn't connect (e.g. due to transport compatibility), use mcp-remote as a stdio bridge:

Replace <org-id> and <your-token> with your credentials.

Verify

In the Codex CLI, run:

You should see Dstl8 listed as connected.

In the VS Code extension, go to the gear icon → MCP settings to check server status.

Troubleshooting

Server fails to connect — Test mcp-remote directly:

Timeout on startup — Increase the startup timeout in your config:

Last updated