Skip to content

MCP for Claude, Cursor and ChatGPT

Bunker speaks the Model Context Protocol, so agents can create apps, deploy files, edit, share and roll back, with your permissions and nothing more.

Add a connector (Claude, ChatGPT) or an MCP server (Cursor, VS Code, Claude Code) with this URL:

https://bunker.example.com/mcp

The client discovers everything else:

  1. Its first request gets 401 with WWW-Authenticate: Bearer resource_metadata=".../.well-known/oauth-protected-resource/mcp".
  2. It reads the protected-resource metadata (/.well-known/oauth-protected-resource and /.well-known/oauth-protected-resource/mcp) and the authorization-server metadata (/.well-known/oauth-authorization-server, also at /.well-known/openid-configuration).
  3. It identifies itself with a client ID metadata document (an https URL as client_id), or registers itself at /oauth/register.
  4. Your browser opens Bunker’s consent page (/oauth/authorize). You sign in as usual (built-in account or company SSO) and see which app is asking and where it will send you back. Plain-http redirect URIs are only accepted for localhost / 127.0.0.1.
  5. The client exchanges the code at /oauth/token (PKCE S256 only, bound to the /mcp resource). Access tokens last 1 hour (BUNKER_OAUTH_ACCESS_TTL, in seconds); refresh tokens rotate on every use, and reusing an old one revokes the whole family. Revoke at /oauth/revoke or from your token list.
.mcp.json (Cursor, VS Code, Claude Code)
{ "mcpServers": { "bunker": { "url": "https://bunker.example.com/mcp" } } }
Terminal window
claude mcp add --transport http bunker https://bunker.example.com/mcp

Bunker speaks the stateless 2026-07-28 protocol and the earlier session-based versions (2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05), so new and older clients both work.

For agents that run on your machine, using your CLI login:

Terminal window
bunker login https://bunker.example.com
claude mcp add bunker -- bunker mcp
.mcp.json
{ "mcpServers": { "bunker": { "command": "bunker", "args": ["mcp"] } } }
Tool
create_site_from_html Publish an HTML page as a new app
deploy_files Deploy files to an app (publish or draft)
edit_file Edit one file of an app
build_with_ai Ask Bunker’s AI builder to build or change an app
get_sdk_docs The SDK, sandbox and deploy rules
One tool per API operation Generated from GET /api/v1/ops: list, share, versions, restore, data, stats…
fn_list, fn_call, fn_runs List an app’s server functions, call one, and read recent runs with their logs (handy for an agent fixing its own function)
secrets_list, secrets_set, secrets_delete Manage an app’s function secrets. Values can be set, never read

Destructive operations (delete, unshare, discard) are marked so clients can ask you first.

Resources: bunker://docs/agent-guide, bunker://docs/sdk, bunker://docs/sandbox, and bunker://sites/<app> for each app you can open.

  • The agent acts as you. It can’t see apps you can’t see.
  • Page-only limits still apply: an app’s code can never deploy or share; only you, through the agent, can. The same goes for server functions.
  • An agent can store a secret you give it, but can never read one back.
  • Every action is in the audit log, marked as coming from a token.