MCP.so
Sign In

Xata MCP ServerVerifiedFeatured

About Xata MCP Server

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

Connection details

https://api.xata.tech/mcp

Setup

claude mcp add xata-mcp-server --transport http https://api.xata.tech/mcp

Tools

12

Invoke a Xata REST API operation that destroys data or revokes access: deleting an organization, project, branch, invitation, or API key, removing a member, restoring a branch from a backup (overwriting its current data), or rotating branch credentials (breaking clients using the old ones). Requires confirm=true. Put path, query, and header parameters (and any server variables) in params by name, and a JSON request body in body, per describe_operation. The caller's credentials are forwarded to the main API; an operation with its own gateway (e.g. the SQL endpoint) authenticates via its own header instead. An operation of another kind is refused here, naming the tool to call instead; search_operations and describe_operation report that tool as callTool.

Invoke a Xata REST API operation that only reads: listing and describing organizations, projects, branches, backups, members, and API keys, and querying branch logs and metrics. Put path, query, and header parameters (and any server variables) in params by name, and a JSON request body in body, per describe_operation. The caller's credentials are forwarded to the main API; an operation with its own gateway (e.g. the SQL endpoint) authenticates via its own header instead. An operation of another kind is refused here, naming the tool to call instead; search_operations and describe_operation report that tool as callTool.

Invoke a Xata REST API operation that creates or updates data: creating an organization, project, or branch, updating settings, inviting a member, issuing an API key, and so on. Put path, query, and header parameters (and any server variables) in params by name, and a JSON request body in body, per describe_operation. The caller's credentials are forwarded to the main API; an operation with its own gateway (e.g. the SQL endpoint) authenticates via its own header instead. An operation of another kind is refused here, naming the tool to call instead; search_operations and describe_operation report that tool as callTool.

Return an operation's method, path, parameters, request/response JSON schemas (with any referenced component schemas), and the call tool that invokes it. Works for read, write, and destructive operations alike. Use the operationId from search_operations.

List the tables and their columns in a branch's Postgres database (user schemas only, excluding the Postgres system schemas). Read-only.

Return the full contents of a Xata skill by name (a name from list_skills).

List the available Xata skills: short task-focused guides (managing Postgres, using the API and CLI, and more). Read one with get_skill before a multi-step task such as seeding or migrating a branch.

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Xata documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

Run a SQL statement against a branch's Postgres database over the HTTPS gateway. The branch host, connection string, and credentials are resolved server-side from the ids, so you never handle the password. Read-only by default; set write=true to allow statements that modify data or schema. This executes real SQL and can change or delete data.

Search the full Xata REST API for operations beyond the dedicated tools (backups, metrics, logs, members, webhooks, and so on). Returns matching operation ids with method, path, summary, and the call tool that invokes each one. Pass an operationId to describe_operation for its schemas, then to that call tool to invoke it.

Search across the Xata knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Xata, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. `head -200 /api-reference/create-customer.mdx`).

Return the identity of the authenticated caller: the Xata user ID and email, or the API key ID when authenticated with a Xata API key. Use it to confirm which account the current credentials belong to.

Overview

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

Frequently asked questions

What is the Xata MCP Server remote MCP server?

The Xata MCP Server remote MCP server is a hosted Model Context Protocol endpoint at https://api.xata.tech/mcp, so AI assistants can connect to it without installing or running anything locally.

How do I connect to the Xata MCP Server MCP server?

Add the endpoint https://api.xata.tech/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.

Does the Xata MCP Server MCP server require authentication?

Yes. Xata MCP Server uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.

Which transport does the Xata MCP Server MCP server use?

Xata MCP Server exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.

Comments