Compatible with every major AI agent and IDE
What is the Xata (Serverless DB) MCP Server?
Connect your Xata account to any AI agent to manage your serverless data infrastructure through natural conversation. Xata combines the power of a relational database with the ease of use of a spreadsheet, all accessible via this MCP server.
What you can do
- Organization Management — List, create, and update organizations and manage team members or invitations using
list_organizationsandlist_members. - Project & Branch Control — Create and manage projects and database branches across different regions with
create_projectandcreate_branch. - SQL Execution — Run SQL queries or batches directly against your database branches to fetch or manipulate data using
execute_sql. - Infrastructure Insights — Retrieve branch metrics, credentials, and project limits to monitor your serverless environment with
get_branch_metricsandget_project_limits.
How it works
- Subscribe to this server
- Enter your Xata API Key
- Start managing your databases from Claude, Cursor, or any MCP-compatible client
No more switching between your IDE and the Xata dashboard to check schema or run quick queries. Your AI acts as a database administrator and developer advocate.
Who is this for?
- Backend Developers — run SQL queries and manage database branches directly from the code editor.
- DevOps Engineers — monitor project limits and branch metrics to ensure infrastructure health.
- Data Analysts — quickly explore organizational data and project structures through natural language.
Built-in capabilities (30)
Create a new database branch
Create a new organization
Create a new project
Delete a branch
Delete an organization invitation
Delete a project
Execute a SQL query against a branch
Execute a batch of SQL queries in a single transaction
Get branch details
Retrieve branch credentials
Retrieve branch metrics
Get organization details
Get project details
Get resource limits for projects
List all branches in a project
List available images
List available instance types for a region
List organization invitations
List organization members
List all organizations
List all projects in an organization
List available regions
Remove a member from an organization
Request organization deletion
Resend an organization invitation
Rotate branch credentials
Send an invitation to join an organization
Update branch details
Update organization details
Update project details
Why Cursor?
Cursor's Agent mode turns Xata (Serverless DB) into an in-editor superpower. Ask Cursor to generate code using live data from Xata (Serverless DB) and it fetches, processes, and writes. all in a single agentic loop. 30 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Xata (Serverless DB) in Cursor
Xata (Serverless DB) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Xata (Serverless DB) to Cursor 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 Xata (Serverless DB) in Cursor
The Xata (Serverless DB) 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 30 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor 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
Xata (Serverless DB) for Cursor
Every tool call from Cursor to the Xata (Serverless DB) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I execute raw SQL queries on my Xata branches?
Yes! You can use the execute_sql tool to run any valid SQL statement against a specific database branch. For multiple statements, use execute_sql_batch.
How do I check the performance or usage of a specific database branch?
Use the get_branch_metrics tool. It provides real-time insights into the operational status and usage metrics of your targeted database branch.
Is it possible to manage team access and invitations through the AI?
Absolutely. You can use list_members to see who has access, and send_invitation to invite new collaborators to your organization directly.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Slack Webhook Notifier
1 toolsThis MCP does exactly one thing: it sends messages to your Slack channels. That's its only function, and nothing else. Zero bloat, incredible for giving your AI agents a voice.

Douyin Mini-Game
10 toolsDouyin mini-game developer API — manage cloud storage, leaderboards, user sessions, and content moderation for casual games.

Deterministic Cron Schedule Engine
3 toolsEquip your AI with precise cron job parsing. Deterministically translate cron to natural language, format schedules, and calculate exact next execution times.

ANOVA Calculator Engine
1 toolsRun exact One-Way ANOVA tests to compare means across multiple groups local. Get CPU-guaranteed F-scores and p-values, not LLM guesses.
