FusionAuth MCP for AI. Manage every identity detail, from user roles to MFA status.
Works with every AI agent you already use
…and any MCP-compatible client








How this MCP server connects to your AI agent
FusionAuth (Enterprise Identity & Auth) MCP connects your AI client directly to enterprise identity services. Manage users, applications, groups, and authentication flows through natural conversation, letting you audit access, provision accounts, or test MFA sequences without leaving your IDE.
What AI agents can do with FusionAuth (Enterprise Identity & Auth) Automation
Add group member
Assigns a specific user account to an existing group.
Create api key
Generates and provides details for a new API key credential.
Create application role
Defines and sets up a new role specific to an application's permissions.
Create, read, update, or delete user profiles using specific IDs or emails.
List available applications and define granular roles for different users within those apps.
Simulate login attempts, test MFA sequences, or issue new JSON web tokens (JWTs).
Retrieve the current health, version number, and configuration settings of your entire identity platform.
Create, retrieve, update, or delete API keys and user secrets.
Ask an AI about this
Waiting for input…
What AI agents can do with FusionAuth (Enterprise Identity & Auth) 50 Tools
Use these tools to perform every identity action imaginable: managing user accounts, controlling application access, generating credentials, or checking system health.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using FusionAuth (Enterprise Identity & Auth) on VinkiusAdd Group Member
Assigns a specific user account to an existing group.
Create Api Key
Generates and provides details for a new API key credential.
Create Application Role
Defines and sets up a new role specific to an application's permissions.
Create Application
Registers a brand-new application into the identity system.
Create Group
Establishes a new container for managing user access rights.
Create Lambda
Creates a new custom serverless function within the environment.
Create Tenant
Sets up an entirely isolated, top-level container for organizational data.
Create User
Creates a new user account and profile in the system.
Create Webhook
Sets up an automated URL endpoint to receive data notifications.
Delete Api Key
Permanently removes a credential used by external services.
Delete Group
Removes an existing user group and all its associated members.
Delete Lambda
Decommissions a custom serverless function.
Delete Tenant
Completely removes an isolated organizational container and all its data.
Delete User
Permanently deletes a user profile from the system.
Delete Webhook
Deletes an existing notification endpoint URL.
Disable Mfa
Turns off multi-factor authentication for a specific user account.
Enable Mfa
Activates multi-factor authentication requirements for a user.
Generate Mfa Secret
Creates the unique secret key needed to set up MFA on a user's device.
Get Api Key
Retrieves a specific, existing API key credential for reference.
List Application Roles
Returns a list of every defined role available within an application.
Get Application
Fetches the full details and configuration of a single application.
List Applications
Gathers a directory listing of all active applications in the system.
Get Group
Retrieves all members and details for an existing user group.
Get Identity Provider
Fetches the configuration of external identity services (like Google or Azure).
List Identity Providers
Lists every configured external identity source used for authentication.
Get Lambda
Retrieves the code and settings for a custom serverless function.
Get System Configuration
Pulls all current system-level configuration variables and settings.
Get System Health
Checks the overall operational status of the identity platform.
Get System Status
Retrieves the current, high-level operating state of the system.
Get System Version
Displays the exact version number of the installed identity platform software.
Get Tenant
Retrieves the configuration details for a specific organizational tenant container.
Get User
Fetches all profile data and metadata for one specified user account.
Get Webhook
Retrieves the configuration details of a specific notification endpoint.
Idp Login
Completes the login process using an external identity provider service.
Issue Jwt
Generates a new, signed JSON web token for authenticated access.
Login
Authenticates a user by username and password.
Mfa Login
Completes the login process after successfully passing multi-factor authentication.
Patch User
Makes partial edits to an existing user's profile without overwriting all data.
Refresh Jwt
Generates a new JWT token when the current one is nearing expiration.
Register User
Signs up and registers a brand-new user profile for an application.
Remove Group Member
Removes a specific user from a group, revoking their access rights.
Revoke Refresh Tokens
Invalidates and removes long-lived refresh tokens for security reasons.
Start Mfa
Initiates the multi-factor authentication flow process for a user.
Update Api Key
Changes or refreshes the credentials of an existing API key.
Update Group
Modifies the name, description, or membership list of a group.
Update Lambda
Replaces the code and settings for an existing serverless function.
Update System Configuration
Modifies core, system-wide operational parameters.
Update Tenant
Makes structural changes to a specific organizational tenant container.
Update User
Updates all general information fields for an existing user profile.
Update Webhook
Modifies the URL or payload settings of an active webhook endpoint.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with FusionAuth (Enterprise Identity & Auth), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FusionAuth. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 50 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The Identity Admin Headache
Right now, managing a user's access means logging into three different portals: the user directory to check their status, the application dashboard to see what roles they have, and finally, maybe running an API script locally just to test if their credentials still work. You end up clicking tabs, copying IDs, pasting keys, and manually cross-referencing data across a dozen screens.
With this MCP connected via Vinkius, you ask your agent one question: 'What is the current access level for Jane Doe?' The response isn't a list of links; it’s a single block of structured facts. You get instant answers about her user profile, group memberships, and application roles without ever leaving your IDE.
Full Identity Control with FusionAuth MCP
You eliminate the need for manual credential audits by using tools like `get_api_key` to retrieve current keys and running `delete_api_key` immediately after an employee leaves. You also stop forgetting which services are connected by automatically listing all webhook endpoints with `get_webhook`.
The difference is control. Instead of managing identities piecemeal across scripts and dashboards, you manage the entire system's state through a single conversational interface that knows every tool available—from creating tenants to updating core system configuration.
What your AI can actually do with this
Managing user identities used to mean jumping between dashboards—checking a user's roles here, running a script in the terminal there, and manually updating an application key somewhere else. This MCP lets your AI agent handle that whole mess through conversation.
It gives you control over every part of your identity stack. Need to onboard a new developer? You can ask it to create their account, assign them to the 'backend-team' group, and give them specific application roles—all in one go. Want to audit compliance? Ask it to list all applications and retrieve details on who has access.
The whole process feels like talking to an expert teammate who already knows where everything is stored. When you connect this MCP via Vinkius, your agent gains immediate visibility into complex structures like tenants, API keys, and multi-factor authentication settings. It's not just reading data; it’s performing full lifecycle management for all your digital assets.
019e5d1d-3231-7275-b952-26da8a2182ff Here's how it actually works
The bottom line is, you get to manage complex identity infrastructure using simple, natural language commands.
First, connect this MCP to your AI client by providing the FusionAuth URL and a valid API Key.
Next, give your agent a directive: 'List all applications that need user roles defined.'
The agent executes the necessary calls, returning structured data on users, groups, or application details directly into your chat window.
Who is this actually for?
This MCP is critical for DevOps Engineers who need to audit system permissions rapidly, Security Analysts enforcing compliance checks, and Backend Developers testing auth integrations. If your job involves making sure users have exactly the right access at any given moment, this is for you.
Needs to quickly check user accounts or modify application roles without leaving their terminal environment.
Must inspect user profiles, verify MFA status, and audit API keys during incident response for compliance.
Needs to test full authentication flows (like login or JWT refreshing) directly from their code editor.
What Changes When You Connect
You stop jumping between dashboards. Instead of manually checking credentials or running local scripts, you simply ask your agent to retrieve details—whether it's getting a full list of applications or fetching the latest system health report using get_system_health.
Compliance auditing gets faster. Instead of exporting and reviewing CSV files, your agent can pull specific data points, like retrieving all application roles via list_application_roles or checking if MFA is enabled using enable_mfa, giving you immediate answers.
Onboarding new users becomes a single command sequence. You don't have to manually run multiple scripts; you just ask the agent to create the user, then assign them to groups, and finally update their profile with necessary metadata.
Secure credential handling is centralized. Need to rotate an API key? Instead of finding it in old documentation, your agent handles get_api_key, allows you to update_api_key, and even cleans up the old credentials using delete_api_key.
You can test complex flows without breaking anything. Developers use this MCP to simulate real-world access by running functions like login or mfa_login directly, verifying that user roles are applied correctly before deployment.
See it in action
Investigating a compromised account.
A security analyst gets an alert. They ask their agent to get the user's profile using get_user, check if MFA is enabled, and then immediately call revoke_refresh_tokens to lock down access while they investigate.
Adding a new service integration.
A developer needs to connect a billing microservice. They ask their agent to create the necessary application via create_application, generate a dedicated key using create_api_key, and then set up an automated notification URL with create_webhook.
Restructuring user access levels.
The team is splitting departments. Instead of manually updating hundreds of records, the agent lists all applications using list_applications, identifies necessary roles via list_application_roles, and then uses tools like add_group_member to enforce the new permissions.
Auditing system changes.
An SRE needs to know if a recent configuration change broke anything. They ask their agent to retrieve the current system status using get_system_status and then check the overall operational health with get_system_health.
The honest tradeoffs
Calling tools sequentially for state changes
Trying to manually update user data by running separate calls: first calling update_user, then forgetting to call a related cleanup tool like remove_group_member when the user leaves.
When making major user lifecycle changes, always confirm the full sequence with your agent. For example, if you use delete_user, make sure you also run checks on all associated groups and applications using their respective delete tools.
Assuming read access equals write permission
Reading a user's profile using get_user and thinking that because the data exists, you can simply change it. This ignores necessary validation steps.
If you want to modify any account detail after retrieving it, always use the dedicated update tools like update_user or patch_user. Don't try to build modification logic from a read-only call.
Using general authentication methods for specific tasks
Trying to manage application roles by just calling the generic login tool. That only handles auth, not resource access control.
For granular permissions and role management, use dedicated tools like list_application_roles, which is designed specifically to map users to what they can actually do within a given app.
When It Fits, When It Doesn't
Use this MCP if your workflow requires managing the full identity lifecycle: creating accounts, assigning permissions, testing access flows, and auditing system credentials. It's ideal for security-focused tasks like revoking tokens (revoke_refresh_tokens) or ensuring MFA compliance. Don't use it if you only need to check a single piece of public information—for example, just listing all tenants using list_identity_providers is often enough, and the full MCP might be overkill. If your problem is simply 'What is my username?' then no complex toolset is required; but if the question is 'Does this user have permission to do X?', you need the granular control provided by tools like get_application and list_application_roles.
Questions you might have
How do I check a user's details using the get_user tool? +
You must provide exactly one unique identifier (like an ID or email) when calling get_user. The agent will return their full profile data, including group memberships and status.
Can I change a user's role using the add_group_member tool? +
Yes, that's what add_group_member does. You just need to tell the agent which specific user ID you want to add and which group they belong in.
What is the difference between create_user and register_user? +
create_user manages the core identity profile, while register_user specifically signs a new user up for an application. They handle different stages of the account lifecycle.
How do I make sure my API keys are secure with create_api_key? +
When you use create_api_key, your agent handles the generation and retrieval process securely. You can also follow up by using update_api_key to refresh credentials without downtime.
If I delete a tenant, what happens to my data? (delete_tenant) +
Calling delete_tenant removes the entire isolated container and all associated resources within it. This action is irreversible, so confirm your scope first.
How do I initiate a Multi-Factor Authentication flow using the `start_mfa` tool? +
Running start_mfa begins the MFA process for a user. This function doesn't complete the login itself; instead, it sends the initial challenge or setup details needed to proceed through the full authentication sequence.
What happens when I use the `remove_group_member` tool? +
The user immediately loses all permissions tied to that specific group. This is a critical step for access revocation, ensuring they can no longer utilize resources granted only through that membership.
How can I verify if the identity service is operational using `get_system_health`? +
Calling get_system_health returns a comprehensive status object. You get real-time metrics covering service uptime, database connection integrity, and overall performance indicators for immediate auditing.
Can I search for a user using their username instead of an ID? +
Yes! The get_user tool allows you to search by username, email, or loginId in addition to the userId UUID.
How do I list all the roles defined for a specific application? +
Use the list_application_roles tool and provide the applicationId. It will return all roles like 'admin', 'user', or custom roles configured for that environment.
Is it possible to update only a few fields of a user without sending the whole object? +
Yes, use the patch_user tool. It allows you to send a partial JSON body containing only the specific fields you wish to modify.
We've already built the connector for FusionAuth. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 50 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.