Skip to content
BuildBase
BuildBase in your AI tools

Use BuildBase in Claude Code

BuildBase in your AI tools: connect Claude Code to BuildBase's own MCP server and manage your BuildBase organization from Claude Code. You sign in as yourself, and Claude Code can do only what your role and your organization allow.

Add BuildBase to Claude Code

The address is the same in every AI tool: https://api.console.buildbase.app/mcp. BuildBase signs you in the first time Claude Code connects.

  1. In Claude Code, add a remote MCP server: claude mcp add. Use the address https://api.console.buildbase.app/mcp, or the command or config below.
  2. Sign in: run /mcp. Run /mcp in a session and choose the server; a browser opens for sign-in. If it does not open, copy the address it prints. claude mcp login <name> does the same from the shell.
  3. On BuildBase's sign-in page, sign in as you do to the console, then approve the consent screen, which names Claude Code and what it asks for.
  4. Ask Claude Code something, such as "List my BuildBase organizations."
terminalBash
claude mcp add --transport http buildbase-console https://api.console.buildbase.app/mcp
.mcp.jsonJSON
{
  "mcpServers": {
    "buildbase-console": {
      "type": "http",
      "url": "https://api.console.buildbase.app/mcp"
    }
  }
}

The plan it needs

Claude Code does not name a plan for MCP servers. An organization can allow or deny servers with a managed MCP file.

How sign-in looks in Claude Code

Run /mcp in a session and choose the server; a browser opens for sign-in. If it does not open, copy the address it prints. claude mcp login <name> does the same from the shell.

What is different in Claude Code

  • Claude Code asks before a tool call unless an allow rule says otherwise, and /mcp shows which setting applies to each tool.
  • BuildBase adds its own rules on top: each organization is Off, Read only or Read and change for AI agents (Read only by default), and deletes, member and role changes, sends and money moves need your approval in the chat.
  • For a job with nobody to sign in, send one of your organization's API keys as the bearer instead. Add --header "Authorization: Bearer $KEY" to claude mcp add. In .mcp.json, headers can read an environment variable as ${VAR}.
  • --scope project writes the server to .mcp.json in the repository, so everyone on the project gets it.

If it does not work in Claude Code

Claude Code needs to sign in again
Run /mcp, choose the server, then Re-authenticate. Clear authentication signs it out. Log out before claude mcp remove, which deletes the local token without revoking it.
Claude Code does not connect
claude mcp list shows Connected, Needs authentication or Failed to connect, and claude mcp get <name> adds the reason. MCP_TIMEOUT raises the start-up timeout.
Claude Code says the organization does not let agents in
An owner or admin sets the organization's AI agents setting in the console, under Account, then Security. Off turns every agent away, and an owner or admin can also block one agent for one member there.
Claude Code cannot change anything
The organization is Read only, the default. An owner or admin can switch it to Read and change, and Claude Code can then make changes without signing in again. Deleting, sending to an audience, roles and money still ask you to approve each change.

Frequently Asked Questions

Which Claude Code plan do I need?

Claude Code does not name a plan for MCP servers. An organization can allow or deny servers with a managed MCP file.

Can Claude Code change things in my BuildBase organization?

Only where the organization allows it: Read only is the default. Even then, deletes, member and role changes, sends and money moves need your approval in the chat, and secrets never reach Claude Code.

Can I connect Claude Code with an API key instead of signing in?

Yes, for a job with nobody to sign in: send one of your organization's API keys as the bearer. Add --header "Authorization: Bearer $KEY" to claude mcp add. In .mcp.json, headers can read an environment variable as ${VAR}. The key works in its own organization only, and the organization's AI agents setting still applies.

Where next