In Claude Code, add the server, then run /mcp in a session and choose vozora to sign in with your browser. No key to create or paste. Read the spend warning first.
claude mcp add --transport http vozora https://mcp.vozora.io/mcpOn claude.ai, use Customize, Connectors, Add custom connector, enter https://mcp.vozora.io/mcp and select Connect. Other clients are listed below. Approval happens on a Vozora consent page, and it creates a key that expires after 90 days and that you can disconnect from your API keys page.
Name the server vozora, prod or agent. Names that join our brand to another word, such as vozora-prod, are refused by our impersonation filter.
Tested by us against production
Add the server:
claude mcp add --transport http vozora https://mcp.vozora.io/mcpThen run /mcp inside a Claude Code session, choose vozora and finish the sign-in in your browser. From a plain terminal (or over SSH), claude mcp login vozora does the same.
Tested by us against production
Open Customize, then Connectors, choose Add custom connector, and enter this URL (the Settings, Connectors path in older builds is the same list):
https://mcp.vozora.io/mcpSelect Connect and approve on the Vozora consent page. On Team and Enterprise plans an owner adds the connector for the organisation first.
Setup follows the client's own docs; we have not tested this client yet.
Add the server:
codex mcp add vozora --url https://mcp.vozora.io/mcpThen sign in:
codex mcp login vozoraSetup follows the client's own docs; we have not tested this client yet.
Add this to ~/.cursor/mcp.json, or .cursor/mcp.json in a project:
{
"mcpServers": {
"vozora": {
"url": "https://mcp.vozora.io/mcp"
}
}
}Open Cursor's MCP settings, find vozora and sign in when Cursor offers it. Approve on the Vozora consent page.
Setup follows the client's own docs; we have not tested this client yet.
Run MCP: Add Server from the Command Palette and choose HTTP, or put this in .vscode/mcp.json (MCP: Open User Configuration for every workspace):
{
"servers": {
"vozora": {
"type": "http",
"url": "https://mcp.vozora.io/mcp"
}
}
}Start the server from the file or the MCP Servers view. A browser window opens for the sign-in the first time it connects.
Setup follows the client's own docs; we have not tested this client yet.
In the prompt box open the + menu, choose MCPs, then add a custom MCP server. Set the name to vozora and the URL to:
https://mcp.vozora.io/mcpSet authentication to OAuth, save, and approve on the Vozora consent page.
Setup follows the client's own docs; we have not tested this client yet.
In the Cascade panel open the menu, choose Open MCP config file, and add:
{
"mcpServers": {
"vozora": {
"serverUrl": "https://mcp.vozora.io/mcp"
}
}
}Refresh the MCP list, then sign in to vozora and approve on the Vozora consent page.
Setup follows the client's own docs; we have not tested this client yet.
Run zed: open settings file and add:
{
"context_servers": {
"vozora": {
"url": "https://mcp.vozora.io/mcp"
}
}
}Zed prompts you to authenticate; approve on the Vozora consent page.
Setup follows the client's own docs; we have not tested this client yet.
Add the server:
gemini mcp add --transport http vozora https://mcp.vozora.io/mcpThen, inside Gemini CLI, sign in:
/mcp auth vozoraSetup follows the client's own docs; we have not tested this client yet.
Run goose configure, choose Add Extension, then Remote Extension (Streamable HTTP), and enter this URL. In the desktop app use Extensions, then Add custom extension:
https://mcp.vozora.io/mcpGoose registers itself and opens the sign-in in your browser; approve on the Vozora consent page.
ChatGPT is coming soon: we have not proven it yet, so we do not list it as working.
Use one of the clients above for now.
Any client that supports remote MCP over Streamable HTTP with OAuth works with this URL. Vozora uses OAuth 2.1 with PKCE (S256) and dynamic client registration, so the client needs no pre-registered ID:
https://mcp.vozora.io/mcpClients discover the rest from the standard metadata:
https://mcp.vozora.io/.well-known/oauth-protected-resource
https://mcp.vozora.io/.well-known/oauth-authorization-serverAn MCP server is a standard interface AI agents use to call tools. Point a client at https://mcp.vozora.io/mcp and the operations the scopes you approve allow appear in the agent's tool list. Every call runs through the same checks as a request from your own scripts.
This agent will be able to spend your money. It can order servers and other paid resources, charged to your saved payment method, and it can delete servers and data. Vozora asks agents to confirm with you first, but an agent is software you chose and may not always ask. You are responsible for what it does. You can limit it with the permissions below, and disconnect it at any time. Every account has a spend cap, but it is a brake rather than a guarantee, and fixed-term plans are paid in advance.
Use a key when there is no browser to sign in with. Create it in the panel with the "Connect an AI agent" preset, and start with the narrowest scopes (read-only) before granting more. Put the key in an environment variable, never in a file you commit, then give it to your client.
read -rs VOZORA_API_KEY && export VOZORA_API_KEY # paste the key; it stays out of shell history
claude mcp add --transport http vozora https://mcp.vozora.io/mcp \
--header "Authorization: Bearer $VOZORA_API_KEY"{
"mcpServers": {
"vozora": {
"url": "https://mcp.vozora.io/mcp",
"headers": { "Authorization": "Bearer ${env:VOZORA_API_KEY}" }
}
}
}Export VOZORA_API_KEY in the environment Cursor starts from, then add this to ~/.cursor/mcp.json, or to the project's own .cursor/mcp.json.