OpenCode

Branch off your dev environment to create an isolated config so you control the agent's blast radius.

Branch configs are prefixed with the environment slug. dev_agent_opencode lives under dev and inherits from its root unless you override.

Scope it down to the API key for whichever provider you've configured opencode with, plus any work credentials the agent actually needs, nothing more. opencode is multi-provider, so the exact key depends on the model you've configured (ANTHROPIC_API_KEY, OPENAI_API_KEY, etc.).

Do not let the agent populate or modify its own secrets. A human decides what goes in this config. The token in the next step is read-only, so the agent can't write back.

Bound to this one config, with an expiration so a leaked token dies on its own. Capture it into an environment variable so the next steps can reference it without pasting the raw value around.

Service tokens are read-only by default. The agent can fetch secrets, never change them. This is the agent's identity.

Bind the agent's token to a single directory so the CLI only uses it there. Run this from the folder OpenCode will work in.

The --scope . flag locks the token to the current directory. Any doppler command run inside that folder, the doppler run launch below, and anything opencode itself invokes, resolves with this scoped agent token and never your personal CLI token.

Note: Run the agent in a sandbox scoped to that directory. And proceed with caution on production workloads: a non-deterministic agent with live credentials is real blast radius, so keep it pointed at dev/test configs unless you have a specific reason not to.

OpenCode reads provider keys from the environment, so doppler run is all that's needed. No .env, and when the process exits, the secrets are gone.

Steps 1-6 give OpenCode the credentials it runs with. The MCP server lets OpenCode see and operate Doppler itself: list projects, inspect a config, and understand the secret layout before depending on it. Useful in almost any session, so set it up alongside the injection above.

The MCP server uses the same scoped, read-only token you minted in step 4. opencode defines MCP servers in opencode.json, and its config expands {env:VAR} references, so point DOPPLER_TOKEN at the token you exported in step 4 instead of pasting the raw value. Add --read-only because the server can't infer read-only from the token alone.

Alternatively, authenticate once with npx @dopplerhq/mcp-server login and drop the environment block entirely. Restart opencode after editing the config.