Build with Gemini CLI. Build device integrations from your terminal.

Bring Seam’s current documentation into your Gemini CLI session. Explore the API, build a small integration in your project, and verify the result from the terminal.

Set up Gemini CLI Troubleshoot an issue

Gemini CLI

Illustrative sandbox workflow

Set up Seam in Gemini CLI.

Gemini CLI can save the Seam connection directly to your project settings with one command.

01

Register Seam’s MCP server

With Gemini CLI installed, run this in your project. The project scope stores the connection in .gemini/settings.json.

Run in your project

gemini mcp add --transport http --scope project seam https://mcp.seam.co/mcp/authenticated

Sign in through OAuth in the next step; no Seam API key is needed.

02

Inspect the available tools

Start a Gemini CLI session, run /mcp auth seam, and complete browser sign-in. Then run /mcp. Confirm seam is connected, then ask it to search the current Seam API reference for listing devices.

Inside Gemini CLI

/mcp auth seam

03

Build a first sandbox workflow

Paste the setup prompt into the session. Gemini can inspect your project and follow /agents.md to set up a workspace and Seam API key.

Seam agent setup

Paste into Gemini CLI

Set up Seam in this project:
fetch https://seam.co/agents.md and follow its instructions.

Choose your workspace permissions.

After signing in, check that api_request appears alongside the documentation tools. Ask your agent to list your workspaces. If Seam returns a permission-consent link, open it, select the intended scope and Viewer for read-only access, then retry. Device changes require write permissions. No Seam API key belongs in this MCP configuration.

Already connected? Replace the old Seam entry instead of adding a duplicate, reconnect or restart your client, and start a new conversation to refresh its tools. For documentation and skill packs without sign-in, use https://mcp.seam.co/mcp instead and skip OAuth login. This optional anonymous connection cannot access workspace resources.

Read the MCP guide

Troubleshoot with your agent.

Investigate device and connected-account issues, Access Grants, access codes, and API or authentication errors. Seam’s MCP delivers the troubleshooting skill pack directly to your agent, with playbooks for gathering evidence and identifying what is still unknown.

Connect with Viewer access.

Use an MCP client that supports OAuth to connect to Seam’s authenticated endpoint. Sign in and approve Viewer access to the workspace you want to investigate. Refresh the connection and start a new conversation to load its tools.

Use your existing workspace. This skill is available through MCP without a separate plugin install. Replace the placeholders with the affected resource, workspace, and incident time. The investigation uses public API evidence and stays read-only.

Set up troubleshooting

Authenticated MCP endpoint

https://mcp.seam.co/mcp/authenticated

Try this prompt

Use Seam MCP to investigate why access grant <grant_id>
in workspace <workspace_id> failed at <time and timezone>.
Use the troubleshooting skill pack. Keep the investigation
read-only and explain any missing evidence.

Prompts to try.

Give Gemini CLI a concrete task, ask it to check current documentation, and review the result.

Create a device inventory script

Agent prompt

Build a read-only Seam device inventory script in this project’s language. Use the current API reference, read the Seam API key from the environment, and report each device’s connection status and supported capabilities. Verify it against my sandbox workspace.

Add thermostat controls

Agent prompt

Use Seam’s current thermostat documentation to implement a temperature-setting function for a supported device. Validate its HVAC modes and set point bounds, track the requested action, and read the settings back. Keep target temperature separate from measured room temperature.

Turn an API example into a test

Agent prompt

Find the current Seam example that matches our framework and access workflow. Adapt it to this repository and add a sandbox verification script covering creation, an update, cancellation, and cleanup of the test resources.

Questions.

Client setup references

Gemini CLI MCP servers ↗Gemini CLI skills ↗Seam agent setup ↗Seam integration skills ↗

Can I use this connection across all projects?

Yes. Replace --scope project with --scope user when adding the server. Gemini CLI stores user connections in ~/.gemini/settings.json and project connections in .gemini/settings.json.

Can Gemini CLI load the Seam skills?

Yes. Run npx skills add seamapi/seam-plugin and select Gemini CLI. It supports .gemini/skills/ and .agents/skills/ in the workspace. Use /skills list to confirm discovery and /skills reload after changes.

What should I see in /mcp?

Look for seam with a connected status and documentation tools. If it is disconnected, check the saved HTTP URL and network access. A documentation search should work before you start application setup.

Next steps.

Test in a sandbox, then connect your real devices.

Find your device

Get an API key All agent guides

Build with Gemini CLI. Build device integrations from your terminal.

Set up Seam in Gemini CLI.

Register Seam’s MCP server

Inspect the available tools

Build a first sandbox workflow

Troubleshoot with your agent.

Connect with Viewer access.

Prompts to try.

Create a device inventory script

Add thermostat controls

Turn an API example into a test

Questions.

Can I use this connection across all projects?

Can Gemini CLI load the Seam skills?

What should I see in /mcp?

Next steps.

Global Infrastructure for Controlling the Physical World