Zed

Zed reads MCP servers from its settings.json, under context_servers.

Get a token

Open the dashboard's Connect an agent page and create a token. Read & write is the recommended choice — it lets the agent deploy, restart, and manage your apps hands-free. Pick read-only if the agent should only look. The full token is shown once, at creation — copy it now.

Add the server

Add this to Zed's settings.json (~/.config/zed/settings.json), with your token in place of {{token}}. If the file already has a context_servers object, add the orbitorca entry inside it:

{
  "context_servers": {
    "orbitorca": {
      "url": "https://api.orbitorca.com/mcp",
      "headers": {
        "Authorization": "Bearer {{token}}"
      }
    }
  }
}

Open Settings → AI → MCP Servers: a green dot next to orbitorca means the server is active.

Try it

Ask Zed's agent to "list my OrbitOrca apps". If it comes back with your apps, you're connected.

Approvals

Zed asks before any tool runs: agent.tool_permissions.default is "confirm" unless you change it to "allow" or "deny". Rules for a single tool use the key mcp:orbitorca:<tool> — for example mcp:orbitorca:list_user_apps — so you can allow the read tools you use often and keep confirming the rest. See Zed's MCP docs for the exact settings.

OAuth instead of a token

Zed can also connect over OAuth. Leave out the headers entry and Zed asks you to sign in when it first connects. The consent screen offers write access only when the connecting app asks for it — if it doesn't, the connection is read-only. Use a token when you want the agent to deploy and change apps.

The dashboard's Connect an agent page generates this block with your token already filled in — copy it from there if you'd rather not edit by hand.

Next: what a token can and can't do.