Compatible with every major AI agent and IDE
What is the SuperTokens MCP Server?
Connect your SuperTokens Core instance to any AI agent to manage user lifecycles, session security, and Role-Based Access Control (RBAC) through natural language.
What you can do
- User Management — Sign up new users, sign in existing ones, and retrieve detailed user profiles or link multiple accounts together.
- Session Control — Create, refresh, and revoke sessions (JWT or database-backed) to maintain tight security over user access.
- RBAC & Permissions — Create roles, define permissions, and assign them to users to manage authorization levels dynamically.
- User Metadata — Store and update custom JSON metadata for users to track preferences or application-specific data.
- Account Linking — Seamlessly link or unlink different recipe user IDs to a primary user identity.
How it works
- Subscribe to this server
- Enter your SuperTokens Core URL and API Key
- Start managing your authentication layer from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Backend Developers — quickly debug user sessions or update roles without writing manual scripts or using a CLI.
- Support Teams — inspect user metadata and account status to resolve login issues or permission errors instantly.
- Security Engineers — audit roles and revoke suspicious sessions directly through a conversational interface.
Built-in capabilities (18)
Assign a role to a user
Bulk import users
Create or update a user role
Create or update a tenant
Create a new session for a user
Delete metadata for a user
Get tenant details
Get user details by ID
Get metadata for a user
Link two user accounts together
List all roles
List roles assigned to a user
Refresh an existing session
Remove/revoke a session
Sign in a user
Sign up a new user
Unlink a user account
Update metadata for a user
Why LlamaIndex?
LlamaIndex agents combine SuperTokens tool responses with indexed documents for comprehensive, grounded answers. Connect 18 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine SuperTokens tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain SuperTokens tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query SuperTokens, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what SuperTokens tools were called, what data was returned, and how it influenced the final answer
SuperTokens in LlamaIndex
SuperTokens and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect SuperTokens to LlamaIndex 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 SuperTokens in LlamaIndex
The SuperTokens 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 18 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex 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
SuperTokens for LlamaIndex
Every tool call from LlamaIndex to the SuperTokens MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I retrieve specific user information using their ID?
Yes, by using the get_user tool with the specific User ID, you can fetch the full profile, including email and account linking status.
How do I assign a specific role like 'admin' to a user?
You can use the assign_role_to_user tool. Just provide the User ID and the role name to update their permissions immediately.
Is it possible to update custom user data or preferences?
Absolutely. The update_user_metadata tool allows you to pass a JSON object to store or update custom information for any user.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query SuperTokens tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp
Explore More MCP Servers
View all →
Senado Federal
21 toolsAccess real-time data from the Brazilian Federal Senate — track legislative proposals, senator profiles, and mandate histories.

Deterministic EdTech Quiz Scorer
1 toolsTransform your AI into a ruthless, high-precision EdTech examiner. Automatically cross-reference quiz answers against weighted keys to generate granular performance metrics instantly.

Mapflow
7 toolsExtract geospatial features from satellite imagery with AI that detects buildings, roads, and vegetation patterns automatically.

Honeywell Forge
11 toolsConnect Honeywell Forge to any AI agent via MCP.
