Turso for AI agents

Turso is a serverless SQLite database platform with global replication, used by developers who want low-latency data access without managing database servers. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Databases and spreadsheetsAPI keyMCP + RESTturso.tech
AUDIT LOG · TURSOPOLICY: acme-support
09:41:07 · claude · u_8f2read
turso.validate_api_token
Validate API Token✓ allowed · 212ms
09:41:09 · claude · u_8f2write
turso.closest_region
Closest Region✓ approved · approved by user
EVERY TURSO CALL, ON THE RECORD
01 · USE CASES

What agents do in Turso.

01

Validate an API token

Check that an API token is still valid before using it for further requests.

02

Find the closest region

Look up the nearest available database region for lowest latency.

03

Listen for database changes

Subscribe to change events on a database as a read-only monitoring step.

02 · ACTIONS

3 Turso actions, graded by risk.

Every Turso action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

1

Look things up. Allowed by default.

  • turso.validate_api_token
    Validate API Token

write

2

Create and change things. Allow, or ask the user first.

  • turso.closest_region
    Closest Region
  • turso.listen_to_changes
    Listen To Changes

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Turso in three steps.

  1. 01Your users connect TursoThey add their Turso api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “closest Region” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Turso through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('turso', {
  read: 'allow',
  write: 'ask',        // closest_region
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Turso connects.

Users add their Turso api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Turso connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Turso from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Turso and Arc0, answered.

Q01

Can I use Turso with Claude, ChatGPT or Cursor?

Yes. Connect Turso to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Turso actions you allow.

Q02

How do users connect Turso?

Users add their Turso api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Turso actions can my agent take?

3 in total: 1 read, 2 write and 0 destructive, such as “closest Region”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Turso?

Yes. Allow read actions and deny writes in the Turso policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Turso too?

Yes. The same Turso connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Turso into your agent.

Your users connect Turso once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan