Data Studio Agent
Description
Unified MCP server giving AI coding agents direct access to your databases: 70+ SQL databases via SqlKit (PostgreSQL, MySQL, SQL Server, SQLite, ClickHouse, Snowflake, BigQuery) and NoSQL via DocKit (Elasticsearch, MongoDB, DynamoDB). Local-first: credentials never leave your…
About
Unified MCP server giving AI coding agents direct access to your databases: 70+ SQL databases via SqlKit (PostgreSQL, MySQL, SQL Server, SQLite, ClickHouse, Snowflake, BigQuery) and NoSQL via DocKit (Elasticsearch, MongoDB, DynamoDB). Local-first: credentials never leave your machine, read-only by default, 79 tools.
Details
- Author
- geek-fun
- Categories
- Database, Other, Search
Jump to
Setup
Install Data Studio Agent in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/geek-fun/data-studio-agent
Follow the installation instructions in the repository README, then restart your MCP client.
Let your AI coding agent securely access all your databases, in plain language.
Local-first. Enterprise-grade security. Open source.
📖 Product Page·npm·dockit·sqlkit·Releases
This repository contains theData Studio MCP Server, aModel Context Protocolserver that gives AI coding agents direct access to your databases through thedockitandsqlkitdesktop apps.
- SQL(via sqlkit):70+ databases(PostgreSQL, MySQL, SQL Server, Oracle, SQLite, DuckDB, ClickHouse, Snowflake, BigQuery, and more)
- NoSQL(via dockit): Elasticsearch, OpenSearch, MongoDB, DynamoDB
- Any AI coding agent.Claude Code, Cursor, Windsurf, OpenCode, Codex, Cline, Pi, Qoder, GitHub Copilot, or any MCP client.
- Any OS.macOS, Windows, Linux.
- Any LLM model.Bring your own provider. No lock-in.
- One MCP server, one config.Routes to both SqlKit (SQL) and DocKit (NoSQL) bridges over localhost.
- Enterprise-grade security.See below.
Install and launchdockitand/orsqlkit, add a database connection, and make sureSettings → MCP Bridge → Auto-startis enabled (it is by default). Install both apps for the full SQL + NoSQL tool set.
npm install -g @geek-fun/data-studio-mcp
Or run it without installing (npx downloads it on first run):
codex mcp add data-studio -- npx -y @geek-fun/data-studio-mcp
claude mcp add --transport stdio data-studio -- npx -y @geek-fun/data-studio-mcp
Cursor.Create.cursor/mcp.json(project) or~/.cursor/mcp.json(global):
{ "mcpServers": { "data-studio": { "command": "npx", "args": ["-y", "@geek-fun/data-studio-mcp"] } } }
Windsurf.Create~/.codeium/windsurf/mcp_config.json(global only):
{ "mcpServers": { "data-studio": { "command": "npx", "args": ["-y", "@geek-fun/data-studio-mcp"] } } }
OpenCode.Add toopencode.json(project) or~/.config/opencode/opencode.json(global):
{ "$schema": "https://opencode.ai/config.json", "mcp": { "data-studio": { "type": "local", "command": ["npx", "-y", "@geek-fun/data-studio-mcp"], "enabled": true } } }
Any other MCP client.Register a stdio server with commandnpxand args-y @geek-fun/data-studio-mcp.
OpenSettings → MCP Bridgein dockit/sqlkit to control what the agent can do:
Use plain language. The agent queries your databases for you:
- "List all tables in my PostgreSQL database"
- "Show me the last 10 orders from the Elasticsearch indexorders*"
- "Find all users older than 30 in MongoDB"
- "Run this query and explain the results"
The agent reads schemas, runs queries, and explores your data, then shows you every query it executed.
The LLM gets broad access to your data, but it never sees your credentials. The policy model gates every capability by risk level.
- Credentials never leave the apps.The LLM only ever sees an opaqueconnection_id. Real credentials are resolved inside dockit/sqlkit and never cross the MCP boundary. Your passwords and keys stay on your machine, in your app.
- ID-based resource access.Agents access databases strictly by connection ID. Credentials never appear in prompts or tool arguments, so there is no path for the model to obtain or exfiltrate connection secrets.
- Three-tier permission model.Read Only / Data Read-Write / Full Access modes gate every capability by risk level, with per-connection overrides. You can mark any connection read-only or allowlist specific actions.
- Explicit user confirmation.Destructive operations (DELETE, DROP, TRUNCATE) surface asAskin the policy. The client prompts the user for explicit confirmation before anything destructive runs.
- Action-level statement classification.SQL is parsed and classified by statement kind (Read / Write / Delete / DDL) before execution. Write-only tools reject DELETE statements; delete tools reject DDL.
- Local-only bridge.The bridge binds to127.0.0.1exclusively. It is unreachable from other machines, with no server to host and no API keys to manage.
All tools follow thedata_studio__{backend}__{action}convention. TheUser confirmationcolumn shows which operations surface an explicit confirmation prompt in your AI client before they run.
code agent (Claude Code / Cursor / OpenCode ...) | | MCP stdio protocol v @geek-fun/data-studio-mcp ← npm package (pure TypeScript) | | HTTP (localhost) +----------------+----------------+ v v | dockit:9120 sqlkit:9121 | (NoSQL bridge) (SQL bridge) | | | | v v | Elasticsearch PostgreSQL | MongoDB MySQL | DynamoDB SQL Server | OpenSearch SQLite |
The MCP server is a thin routing layer. All database drivers, SSH tunnels, and connection management live in the desktop apps, which expose a local HTTP bridge (127.0.0.1only). The MCP server auto-discovers running backends via each app's port file.
This repository also contains thedata-studio-agent Rust framework, the shared AI agent loop (provider adapters, streaming, tool calling, context compaction) that powers the built-in assistants indockitandsqlkit.
Seecrates/data-studio-agent/README.mdfor installation, architecture, and integration guides.
A Python-based MCP server that connects to an Elasticsearch index with Apple HealthKit data.
Access and cache Google Cloud BigQuery metadata.
Explore, query, and manage data in Google BigQuery.
Access Google BigQuery to understand dataset structures and execute SQL queries.
Execute and validate SQL queries against Google BigQuery. It safely runs SELECT queries under 1TB and returns results in JSON format.
A secure, self-hosted Model Context Protocol (MCP) server for Google BigQuery. Hard table allowlists, per-query scan ceilings, built-in rate limiting, and predictable costs on Cloud Run. Works with Claude, ChatGPT, Cursor, Gemini, and any MCP-compatible AI agent.
Query and export data from various databases including ElasticSearch, MySQL, PostgreSQL, Oracle, and SQLite.
Interact with an Elasticsearch cluster via the Model Context Protocol (MCP), enabling clients to query, manage, and analyze data.
Connect to and interact with an Elasticsearch cluster directly from any MCP client using environment variables for configuration.
Connects agents to Elasticsearch data, enabling natural language interaction with indices.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




