Coding agents

Your coding agent, with your databases already in it

Claude Code, Codex and opencode start in a dock inside SnoutData, in your workspace, with your connections handed over the moment they open. No .env file, no connection string in a repo, no copy of your password.

SnoutData

A real recording. The agent asks, you allow, and the app moves.

Bring the one you already use

An agent gets an icon in the activity bar when it is installed on this computer and you have not switched it off.

Claude Code

Anthropic's CLI, handed the local broker by flag, so it has your databases from the moment it starts.

Codex

OpenAI's CLI, in the same dock, in the same workspace folder, with the same access.

opencode

The open-source alternative, treated exactly the same way as the other two.

Closing the dock detaches the session rather than killing it, so a long job survives you putting the panel away.

It does more than print text at you

The app publishes what it can do as tools, so the agent works the product rather than describing it.

It queries your databases

Through the app, over the connections you allow, read-only by default.

It drives the app

Opens tabs, puts SQL in the editor, changes settings, reads app state and logs, posts notifications. The tools run in the live interface, so the window updates while the agent works.

It draws real interface

Anything it has no tool for it can still show: markdown comes back as prose, a SQL block as a card with a Run button, a chart as a chart. The console has no message box, because the terminal already is one.

It builds things you keep

Ask for a dashboard and it opens the view and creates the widgets, instead of printing SQL for you to paste.

You answer for everything it changes

The agent has to ask, and the asking is the point.

It never receives your credentials

Your passwords and keys stay in your operating system's keychain. The app hands the agent capabilities, not secrets, so nothing it is given contains your database password.

Changes are approved one at a time

Anything that changes the app is denied until you say yes. When it is an action you will allow again and again, you can grant it standing permission by name, instead of clicking through the same prompt forever.

Everything it did is written down

An activity timeline in the Agent log, a notifications centre, an entry in the same AI audit trail the assistant writes to, and an indicator in the status bar while it is acting.

You choose what it can reach

Agent access is opt-in per connection and off by default, so the agent sees the databases you picked and no others.

Or from outside the app

The same broker, for any MCP client.

If you would rather keep your agent where it already lives, SnoutData runs a local MCP server on your own machine, behind a bearer token, offering the same read-only tools over the connections you opt in. Your agent gets the data, your credentials stay in the keychain, and every call it makes is written to the same audit log as everything else.

Give your agent your databases

Free to start, on Windows, macOS and Linux.