Integration

Xata integration

Serverless database API built on PostgreSQL with integrated search and analytics. Query, aggregate, search, and manage data through a unified REST API. Features vector search for AI applications, file attachments, and branching. Perfect for modern web applications and AI-powered backends.

Connect Xata How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Xata.Built from the 16 Xata tools below, on the connection you add once.

Common Xata use cases

CRUD operations
Dashboards
Content discovery
AI chat
Reports
Analytics
Data import
Data updates
Data creation
Data deletion

What you can do with Xata

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Record, 10 operations

bulk_insertBulk insertPOSTInserts multiple records in batch.
delete_recordDelete recordDELETEDeletes a record by ID.
get_recordGet recordGETRetrieves a single record by ID.
insert_recordInsert recordPOSTInserts a new record into a table.
query_tableQuery tablePOSTQueries records from a table with filtering and sorting.
search_branchSearch branchPOSTSearches across all tables in a branch.
search_tableSearch tablePOSTFull-text search across table records.
update_recordUpdate recordPATCHUpdates fields in an existing record.
upsert_recordUpsert recordPUTInserts or updates a record by ID.
vector_searchVector searchPOSTPerforms vector similarity search.

Ask, 2 operations

askAskPOSTAsks AI questions about your data.
ask_follow_upAsk follow upPOSTAsks a follow-up AI question within an existing session.

Aggregate, 1 operation

aggregate_tableAggregate tablePOSTRuns aggregation queries on table data.

Database, 1 operation

list_databasesList databasesGETLists all databases in a workspace.

Schema, 1 operation

get_schemaGet schemaGETRetrieves table schema definition.

Summary, 1 operation

summarize_tableSummarize tablePOSTCreates summaries with grouping.

Use Xata from Claude Code, Cursor or Codex

Connect Xata in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Xata operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Xata

Create your workspace
Sign up free. Nothing to install.
Connect Xata once
Add your Xata connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Xata integration FAQ

What can you do with the Xata integration?

LiveContext exposes 16 operations on Xata, covering record, ask, aggregate and database. Common uses include CRUD operations, Dashboards and Content discovery.