Unverified50% confidenceFactExact time
Vercel Agent's credentials differ by type of work: read-only investigation uses the read-only baseline token; approved Vercel changes add extra scopes; external actions (such as opening a GitHub PR) use the corresponding provider's own credentials and permissions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Related Entities
Related Claims
UnverifiedVercel Agent's permissions are defined by scopes (capability names recognized by the authorization system), and any plan that exceeds the read-only baseline (all registered scopes beginning with `read:`) requires overall approval.78% similarUnverifiedVercel initially maintained a separate permission list for the Agent, which could fall out of sync with the OAuth service that issues tokens, and later the two were unified under the same set of scope definitions.72% similarUnverifiedVercel Agent adopts a plan-driven permission model: first investigate the problem, then propose a plan containing specific operations and required permissions, and the user approving the plan grants the permissions needed for execution.70% similarUnverifiedVercel Connect enables scoped connectors and mints tokens for each agent task, so that agents only access the specific context needed for their work.70% similarUnverifiedWhen a session is established, Vercel Agent loads the definitions from the scope registry into an in-memory catalog and uses it in three stages: plan validation, approval and token preparation.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1090317API
curl https://kongchang.com/api/v1/knowledge/claims/1090317MCP
get_claim(id=1090317)