Atlan MCP. Find what your data means and who can use it.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Atlan MCP connects your AI agent directly to an active metadata catalog. You stop guessing which data asset is right by querying business glossaries, checking data classifications (like PII), and discovering lineage across the entire connected data ecosystem.
What your AI agents can do
List classifications
Lists every configured security classification tag used across the Atlan catalog.
List glossaries
Retrieves a list of all official business glossaries maintained in the workspace.
List personas
Lists every configured access control profile (Persona) within Atlan.
Find specific tables, dashboards, or columns across your entire catalog using natural language search.
Retrieve official business glossaries containing verified terms and acronyms used by the company.
List registered users and the access control profiles (Personas) tied to specific job roles.
Get a list of active data classifications, like PII or Confidential tags, applied across your data estate.
See what specific business purposes are configured for data sharing and usage policies.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Atlan: 6 Data Discovery Tools
These six tools let you query everything from user lists and access roles to compliance tags and the core data assets themselves.
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 Atlan on Vinkius019d7554list classifications
Lists every configured security classification tag used across the Atlan catalog.
019d7554list glossaries
Retrieves a list of all official business glossaries maintained in the workspace.
019d7554list personas
Lists every configured access control profile (Persona) within Atlan.
019d7554list purposes
Retrieves a list of all defined data sharing purposes and policies.
019d7554list users
Lists every user account registered within the Atlan workspace.
019d7554search assets
Searches for specific data assets, like tables or dashboards, across the entire catalog.
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 Atlan, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 Atlan. 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
Works with 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 server provides 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Manual governance checks are slow and fragmented.
Today, checking if a new report uses compliant data is a nightmare. You're bouncing between documentation portals, running manual SQL queries just to check column names, and sending emails asking three different people for the official definition of 'Active Client.' It takes hours just to build context.
With this MCP, you ask your agent one thing: 'Check the compliance status of customer data.' The AI pulls everything it needs—the definitions from glossaries, the tags from classifications, and the ownership details from personas—and gives you a single answer. You get instant, auditable confidence.
You gain full visibility over what your business data actually means.
The manual steps that vanish include: cross-referencing multiple spreadsheets to define KPIs; waiting for a Subject Matter Expert (SME) to confirm if 'client' means an individual or a company; and manually confirming which compliance tag applies to every single field.
What you get now is context. You stop working with raw data dumps and start working with verified knowledge, making your AI agent far more reliable.
What you can do with this MCP connector
Need to know what a column means before you write a single query? This MCP gives your AI agent instant access to organizational context. It lets you search an entire data environment—tables, dashboards, columns—using plain language queries. Instead of hunting through separate governance portals for definitions or compliance tags, you ask the system directly.
You can instantly list which data classifications apply (e.g., GDPR) and find trusted business terms using verified glossaries. When your agent pulls this metadata, Vinkius ensures every single call is recorded in a cryptographically signed audit trail, so nobody ever questions who saw what or when. This capability turns raw data into governed, trustworthy information.
019d7554-2193-7133-bdf0-f6b5371dab72 
How Atlan MCP Works
- 1 First, subscribe to this MCP and provide your Atlan API URL and key.
- 2 Next, connect your preferred agent client (Claude, Cursor, etc.) to the Vinkius platform using that single connection point.
- 3 Then, ask your AI agent a governance question—like 'What are our KPIs?' or 'Are there PII tags on the user data table?'—and it pulls definitions and context instantly.
The bottom line is you get deep, conversation-based knowledge of what your data means, where it lives, and who owns it.
Who Is Atlan MCP For?
Data Analysts who waste hours hunting down definitions. Data Stewards whose job is manually auditing compliance tags. Security Engineers needing to map out access roles for audits.
Discovers the verified table names and dashboards needed for a new report without emailing five different Subject Matter Experts.
Systematically audits metadata completeness, checking both PII tags via list_classifications and ensuring all necessary business glossaries are up to date.
Inspects broad access personas using list_personas and verifies data-sharing policies with list_purposes for compliance checks.
What Changes When You Connect
- Stop wasting time. You find the right tables immediately by running a search using
search_assetsinstead of guessing names or asking colleagues for pointers. - Compliance is simpler. Use
list_classificationsto see every PII tag applied across your data estate, making audits fast and systematic. - Trust definitions instantly. Before building anything, check the authoritative terms in a business glossary using
list_glossaries; you don't want conflicting internal terminology. - Understand access boundaries. Review who has permission using
list_personasor checking user accounts withlist_users. It keeps governance tight. - Build complex automations by chaining this MCP with others in the Vinkius catalog, letting your agent combine data discovery with message sending or billing checks.
Real-World Use Cases
Starting a New Project
A data analyst needs to build a dashboard on customer churn. Instead of asking three different stakeholders for the correct table name, they ask their agent to search assets and get definitions, using search_assets and list_glossaries. The agent pulls the verified tables and metrics in seconds.
Running a Compliance Audit
A security engineer must prove that sensitive customer data is properly tagged. They ask the agent to list all classifications, running list_classifications, verifying that tags like 'PII' are present and correctly mapped across relevant tables.
Debugging a Report
A finance team member gets an error because they used an outdated KPI metric. They ask the agent to list glossaries, which instantly provides the correct, approved definition for 'Monthly Recurring Revenue,' allowing them to fix the report.
Onboarding a New Team Member
A manager wants to know who has access to highly confidential HR records. They use list_personas and list_users to map out all current roles and verify that only authorized Personas can view the sensitive data.
The Tradeoffs
Treating search like a database query
Just typing 'show me user profiles' into an LLM without context. The agent might pull random, unvalidated user lists.
→
Use the specific list_users tool to get a complete directory, or if you need data discovery, run search_assets. Never assume general search covers governance.
Ignoring definitions
Building reports using terms like 'Active User' without knowing if the source system defines it differently. The numbers will be wrong.
→
Always check list_glossaries first. That tool gives you the single, authoritative definition for metrics across your whole company.
Assuming access is universal
A new feature rolls out and assumes everyone can see all data, leading to a potential breach.
→
You must check list_personas every time you deploy something sensitive. It maps the exact roles that need permission.
When It Fits, When It Doesn't
Use this MCP if your problem is context, governance, or discovery. If you need to know what data exists, who owns it, how it's defined, or if it's compliant, this is the tool. Don't use it if you just need raw SQL execution—that requires a different type of connector. Similarly, don't rely on it to run ETL jobs; that’s outside its scope. It only provides context and structure. If your goal is simply data movement or transformation without first verifying definitions or classifications, look at other MCPs in the Vinkius catalog.
Common Questions About Atlan MCP
How does the Atlan MCP help me find a specific table? +
You run search_assets. This tool searches across the entire data catalog using natural language to pinpoint exact tables, dashboards, or columns for you.
I need to check if my project has PII tags. How do I use list_classifications? +
You call list_classifications. This tool pulls a complete list of all active classification tags (like GDPR or Confidential) used across the entire Atlan estate.
What is the difference between search_assets and list_glossaries? +
search_assets finds the physical data structures (the tables). list_glossaries provides the human-readable, verified definition of what a term means across the business.
Can I see who has access to my department's data? +
You use list_personas. This tool lists all defined access roles and profiles in Atlan, letting you verify exactly which groups can view sensitive data.
If I want to know what data sharing rules are active, how do I use list_purposes? +
It lists every configured purpose for data usage. This tells you the approved contexts—like 'Research' or 'Billing'—that must be attached to any dataset before it can be accessed by your agents.
I need to check our defined roles and permissions; how do I use list_personas? +
This shows all configured Personas, which are Atlan's access control profiles. You get a clean view of structured roles, ensuring your AI agent only recommends data based on approved business functions.
What security steps does the MCP take when I provide my API key? (Relates to list_users) +
Your credentials pass through a zero-trust proxy. They are used for the call, but they're never stored on disk, keeping your keys completely isolated from the system running the MCP.
How do I get a full roster of every account in our workspace? (Relates to list_users) +
Running list_users retrieves a complete directory of all registered users within Atlan. This is useful for auditing who has accounts and verifying user existence before running deeper data governance checks.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.