Each user connects their own account. Every call carries both identities — the agent and the person it is acting for — so the agent can never reach past what that individual can already do.
Tokens live in the vault and attach server-side at call time. The agent holds a session, not a secret, and revoking access does not mean rotating a key.
Who asked, which agent acted, which action ran, and the verdict that let it through — one audit trail across every integration, not one per vendor.
Each action is granted on its own. An agent allowed to read is not thereby allowed to write, and the scope beside each row is what the acting user must have connected for it to run at all.
v0_delete_chats_by_chatidWRITEDelete Chat. DELETE https://api.v0.dev/v2/chats/{chatId}. Deletes a chat and all its associated messages. The requester must have edit access to the chat.
v0_delete_hooks_by_hookidWRITEDelete Webhook. DELETE https://api.v0.dev/v2/hooks/{hookId}. Deletes a webhook. This action is irreversible.
v0_delete_mcp_servers_by_mcpserveridWRITEDelete MCP Server. DELETE https://api.v0.dev/v2/mcp-servers/{mcpServerId}. Deletes an MCP server and cleans up associated OAuth tokens. This action is irreversible.
v0_get_chatsREADList Chats. GET https://api.v0.dev/v2/chats. Lists chats accessible to the authenticated user. Use metadata[key]=value style query parameters to filter by metadata.
v0_get_chats_by_chatidREADGet Chat. GET https://api.v0.dev/v2/chats/{chatId}. Retrieves a chat by ID.
v0_get_chats_by_chatid_connect_statusREADGet Connect Setup Status. GET https://api.v0.dev/v2/chats/{chatId}/connect/status. Polls the status of a Vercel Connect connector setup started by a `configure_vercel_connect` agent action. Open the `setupUrl` from the agent action data in a browser, then poll this endpoint every few seconds while `pending`. When it returns `ready`, resolve the chat with a `vercel-connect-setup` task to resume generation.
v0_get_chats_by_chatid_filesREADGet Chat Files. GET https://api.v0.dev/v2/chats/{chatId}/files. Returns the source files for a chat.
v0_get_chats_by_chatid_messagesREADList Messages. GET https://api.v0.dev/v2/chats/{chatId}/messages. Lists all messages in a chat.
v0_get_chats_by_chatid_messages_by_messageidREADGet Message. GET https://api.v0.dev/v2/chats/{chatId}/messages/{messageId}. Fetches a single message in a chat.
v0_get_chats_by_chatid_previewREADGet Preview URL. GET https://api.v0.dev/v2/chats/{chatId}/preview. Returns the preview URL for a chat. If the preview isn't ready, the response is null. Poll this endpoint until the response is non-null.
v0_get_hooksREADList Webhooks. GET https://api.v0.dev/v2/hooks. Retrieves a list of all webhooks in your workspace.
v0_get_hooks_by_hookidREADGet Webhook. GET https://api.v0.dev/v2/hooks/{hookId}. Retrieves the details of a specific webhook using its ID.
v0_get_mcp_serversREADList MCP Servers. GET https://api.v0.dev/v2/mcp-servers. Retrieves all MCP servers configured for the current user.
v0_get_mcp_servers_by_mcpserveridREADGet MCP Server. GET https://api.v0.dev/v2/mcp-servers/{mcpServerId}. Retrieves a specific MCP server by ID.
v0_get_settings_preview_hostsREADGet Trusted Preview Hosts. GET https://api.v0.dev/v2/settings/preview-hosts. Returns the hostname patterns trusted to embed previews for the current team. Organization child teams inherit the parent organization’s hosts.
v0_get_usage_activityREADGet Usage Activity. GET https://api.v0.dev/v2/usage/activity. Returns chat and project activity for the active billing scope. Team owners and billing members receive team-wide activity by default; other team members receive their own activity.
v0_get_usage_eventsREADList Usage Events. GET https://api.v0.dev/v2/usage/events. Lists individual credit usage events. Each event includes the credits charged and, when available, associated token counts.
v0_get_usage_summaryREADGet Usage Summary. GET https://api.v0.dev/v2/usage/summary. Returns credit usage for the active billing scope. Team owners and billing members receive team-wide usage by default; other team members receive their own usage.
v0_patch_chats_by_chatidWRITEUpdate Chat. PATCH https://api.v0.dev/v2/chats/{chatId}. Updates a chat's title, privacy, or metadata.
v0_patch_chats_by_chatid_filesWRITEUpdate Chat Files. PATCH https://api.v0.dev/v2/chats/{chatId}/files. Creates, updates, or deletes files for a chat. Pass null to delete. This requires the chat's preview to be running.
v0_patch_hooks_by_hookidWRITEUpdate Webhook. PATCH https://api.v0.dev/v2/hooks/{hookId}. Updates the configuration of an existing webhook, including its name, event subscriptions, or target URL.
v0_patch_mcp_servers_by_mcpserveridWRITEUpdate MCP Server. PATCH https://api.v0.dev/v2/mcp-servers/{mcpServerId}. Updates an existing MCP server configuration.
v0_post_chatsWRITECreate Chat. POST https://api.v0.dev/v2/chats. SPENDS v0 CREDITS (runs a model generation). Creates a new chat from a prompt. The request blocks until the model response is complete and returns the chat.
v0_post_chats_asyncWRITECreate Chat (Async). POST https://api.v0.dev/v2/chats/async. SPENDS v0 CREDITS (runs a model generation). Creates a new chat with a user message and processes it in the background. Returns immediately with the chat ID and message ID. Poll for the assistant message by ID until `finishReason` is non-null.
v0_post_chats_by_chatid_deployWRITEDeploy Chat. POST https://api.v0.dev/v2/chats/{chatId}/deploy. Triggers a Vercel deployment for a chat. Creates a Vercel project if one does not exist.
v0_post_chats_by_chatid_duplicateWRITEDuplicate Chat. POST https://api.v0.dev/v2/chats/{chatId}/duplicate. Creates a new chat by duplicating an existing chat.
v0_post_chats_by_chatid_messagesWRITESend Message. POST https://api.v0.dev/v2/chats/{chatId}/messages. SPENDS v0 CREDITS (runs a model generation). Sends a new message to an existing chat. Blocks until the model response is complete and returns the message response.
v0_post_chats_by_chatid_messages_asyncWRITESend Message (Async). POST https://api.v0.dev/v2/chats/{chatId}/messages/async. SPENDS v0 CREDITS (runs a model generation). Sends a new message to an existing chat and processes it in the background. Returns immediately with the assistant message ID. Poll GET /chats/:chatId/messages/:messageId and check `finishReason` to detect completion.
v0_post_chats_by_chatid_messages_by_messageid_stopWRITEStop Message. POST https://api.v0.dev/v2/chats/{chatId}/messages/{messageId}/stop. Stops an in-flight assistant message generation. The agent aborts at the next safe point and the message is marked finished.
v0_post_chats_by_chatid_messages_resolveWRITEResolve Task. POST https://api.v0.dev/v2/chats/{chatId}/messages/resolve. SPENDS v0 CREDITS (runs a model generation). Resolves a pending task in a chat. Blocks until the model response is complete and returns the resulting message.
v0_post_chats_by_chatid_messages_resolve_asyncWRITEResolve Task (Async). POST https://api.v0.dev/v2/chats/{chatId}/messages/resolve/async. SPENDS v0 CREDITS (runs a model generation). Resolves a pending task and processes it in the background. Returns immediately with the assistant message ID. Poll GET /chats/:chatId/messages/:messageId and check `finishReason` to detect completion.
v0_post_chats_by_chatid_restore_messageWRITERestore Message. POST https://api.v0.dev/v2/chats/{chatId}/restore-message. Restores the files associated with an assistant message. The associated files must not already be the latest files in the chat.
v0_post_chats_by_chatid_vercel_projectWRITECreate Vercel Project. POST https://api.v0.dev/v2/chats/{chatId}/vercel-project. Creates a Vercel project and attaches it to the chat.
v0_post_chats_from_filesWRITECreate Chat From Files. POST https://api.v0.dev/v2/chats/from-files. SPENDS v0 CREDITS (runs a model generation). Creates a new chat from inline source files.
v0_post_chats_from_repoWRITECreate Chat From Repository. POST https://api.v0.dev/v2/chats/from-repo. SPENDS v0 CREDITS (runs a model generation). Creates a new chat from a GitHub repository.
v0_post_chats_from_vercel_projectWRITECreate Chat From Vercel Project. POST https://api.v0.dev/v2/chats/from-vercel-project. SPENDS v0 CREDITS (runs a model generation). Creates a new chat from an existing Vercel project.
v0_post_chats_from_zipWRITECreate Chat From ZIP. POST https://api.v0.dev/v2/chats/from-zip. SPENDS v0 CREDITS (runs a model generation). Creates a new chat from a zip archive.
v0_post_hooksWRITECreate Webhook. POST https://api.v0.dev/v2/hooks. Creates a new webhook that listens for specific events. Supports optional association with a chat.
v0_post_mcp_serversWRITECreate MCP Server. POST https://api.v0.dev/v2/mcp-servers. Creates a new MCP server configuration. Limited to 100 servers per user.
v0_put_settings_preview_hostsWRITESet Trusted Preview Hosts. PUT https://api.v0.dev/v2/settings/preview-hosts. Sets the host patterns trusted to embed previews for a standalone team or parent organization. Organization child teams cannot override this setting.
Put v0 behind one governed endpoint.
Same permissions, same audit trail, whatever else you connect next.