Source: vercel.com/changelog/vercel-mcp-now-supports-client-id-metadata-documents
Vercel MCP now accepts Client ID Metadata Documents, so any MCP client can ask to connect without first being reviewed and added to a list by Vercel. Before this change, Vercel reviewed each client and its redirect URIs by hand and rejected any client that was not on that list. Users still log in and approve each connection.
To connect, a client publishes a Client ID Metadata Document (CIMD), a JSON file on its own domain that describes it, and uses the HTTPS URL of that file as its OAuth client_id. This follows the MCP authorization spec, which now recommends CIMD over Dynamic Client Registration.
Because Vercel has not reviewed these clients, the consent screen shows each client's name, its logo, and the hostname that serves its metadata document, such as "Claude Code by claude.ai". CIMD clients do not get the Vercel verified badge, so the hostname is what a user is trusting when approving. Apps already registered with Vercel are unchanged.
Why it matters if you build agents
Agent builders can point MCP clients at Vercel MCP without waiting for Vercel to approve them and add them to an allowlist. Your client needs to publish a CIMD on a domain you control, since that is the URL it presents as its client_id.
Users approving a CIMD client see only its hostname as the basis for trust, with no verified badge. If you build an MCP client, make the name, logo and hostname of your metadata document clear to the people who will approve it.
Get stories like this every weekday
One short email with the day's agent tooling news.