- Add the remote server
bashclaude mcp add --transport http --scope user \ --client-id falconer-claude-code --callback-port 49152 \ "falconer" "https://falconer.com/api/mcp" - Open Claude Code and authorize
text/mcp
Sign in through the browser when prompted. If port 49152 is taken, swap in another local callback port and rerun.
- Add it manually as a custom connector
texthttps://falconer.com/api/mcp
Name it Falconer and leave the OAuth Client ID and Secret empty, then connect and sign in when Claude asks.
Falconer is officially listed in the ChatGPT plugin directory, so you can install it from there. Click + on Falconer, then sign in when ChatGPT asks.
- Or add it manually to ~/.cursor/mcp.json
json{ "mcpServers": { "falconer": { "type": "http", "url": "https://falconer.com/api/mcp" } } } - For Cursor Agent, use this as the server URL
texthttps://falconer.com/api/mcp
Name it Falconer, then click Login to start the Falconer OAuth flow.
- Add the remote server
bashcodex mcp add falconer --url "https://falconer.com/api/mcp" \ --oauth-client-id falconer-codex-cli \ --oauth-resource "https://falconer.com/api/mcp" - Verify it’s listed
bashcodex mcp list
- Create the connector from your Vercel project
bashvercel link vercel connect create https://falconer.com/api/mcp --name falconer vercel env pull
Vercel returns oauth/falconer. See the Vercel Connect guide for the full SDK setup.
- Point your client at the remote endpoint
texthttps://falconer.com/api/mcp
Any tool that supports remote HTTP MCP works. OAuth runs in your browser on first connect, so there are no API keys to manage.