Compatible with every major AI agent and IDE
What is the Descope (Auth Platform) MCP Server?
Connect Descope to your AI agent to manage and test user authentication flows through natural conversation. Descope is a drag-and-drop authentication and user management platform for any application.
What you can do
- OTP Authentication — Initiate and verify One-Time Passwords via Email, SMS, or Voice using tools like
auth_otp_signup_emailandauth_otp_verify_email. - Magic & Enchanted Links — Send secure sign-up/sign-in links and poll for session completion with
auth_magiclink_signup_emailorauth_enchantedlink_poll. - OAuth Integration — Start OAuth flows with providers like Google and exchange codes for active sessions using
auth_oauth_authorize. - Password Management — Handle traditional password-based sign-ups via
auth_password_signup. - Session Verification — Verify tokens and manage the authentication lifecycle directly from your workspace.
How it works
- Subscribe to this server
- Enter your Descope Project ID and optional Management Key
- Start managing your auth flows from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Developers — Test authentication logic and verify OTP/Magic Link flows without leaving the terminal or IDE.
- QA Engineers — Automate the verification of sign-up and sign-in processes through natural language queries.
- Product Managers — Quickly inspect how different auth providers and methods are configured in your project.
Built-in capabilities (33)
Poll for Enchanted Link session
Sign up a user via Enchanted Link
Verify an Enchanted Link token
Exchange an access key for a session JWT
Get public keys for session validation
Sign up or sign in a user via Magic Link
Verify a Magic Link token
Start OAuth flow
Exchange OAuth code for session
Sign in a user via Email OTP
Sign up a user via Email OTP
Sign up a user via SMS OTP
Sign up a user via Voice OTP
Verify an Email OTP
Verify an SMS OTP
Verify a Voice OTP
Reset a user password
Sign in a user with a password
Sign up a user with a password
Finish WebAuthn sign in
Start WebAuthn sign in
Finish WebAuthn sign up
Start WebAuthn sign up
Create a new access key (M2M)
Create a new permission
Create a new role
Create a new tenant
Create a new user
Delete a user
Load a user by login ID
Load all tenants
Search for users
Update an existing user
Why Vercel AI SDK?
The Vercel AI SDK gives every Descope (Auth Platform) tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 33 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Descope (Auth Platform) integration everywhere
- —
Built-in streaming UI primitives let you display Descope (Auth Platform) tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Descope (Auth Platform) in Vercel AI SDK
Descope (Auth Platform) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Descope (Auth Platform) to Vercel AI SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Descope (Auth Platform) in Vercel AI SDK
The Descope (Auth Platform) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 33 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Vercel AI SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Descope (Auth Platform) for Vercel AI SDK
Every tool call from Vercel AI SDK to the Descope (Auth Platform) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I verify an email OTP code sent to a user?
Use the auth_otp_verify_email tool by providing the user's loginId (email) and the code they received. The agent will return the session details if the verification is successful.
Can I start a Google OAuth login flow using this server?
Yes. Use the auth_oauth_authorize tool with 'google' as the provider and specify your redirectURL. The agent will initiate the OAuth flow for you.
What is the purpose of the enchanted link polling tool?
The auth_enchantedlink_poll tool allows the agent to check the status of a pending enchanted link authentication using a pendingRef. It helps determine if the user has clicked the link and completed the session.
How does the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
MyHR
10 toolsSimplify employee management in New Zealand and Australia with leave tracking, timesheets, and HR compliance tools.

LocalAI
19 toolsRun LLMs, generate images, and process audio locally. OpenAI-compatible API for your own hardware.

Kit (ConvertKit)
10 toolsEnable your AI agent to manage email subscribers, organize tags, and monitor broadcast campaigns via the Kit API.

Mailsoftly
8 toolsManage marketing campaigns and contacts via the Mailsoftly REST API.
