DB Query MCP

Created By
NewToolAIa year ago
db-query-mcp is a mcp tool supporting diverse database querying and exporting.
Overview

Q: What is db-query-mcp?

A: It's a versatile database query and export tool (MCP) that supports multiple databases, converts natural language to SQL, and offers secure read-only access by default. Key features include compatibility with ElasticSearch, MySQL, PostgreSQL, and more, plus CSV/JSON export options.


Q: How do I install db-query-mcp?

A:

  • Basic install:
    pip install db-query-mcp
    
  • For ElasticSearch:
    pip install db-query-mcp[elasticsearch]
    
  • From GitHub:
    pip install git+https://github.com/NewToolAI/db-query-mcp
    

Q: What databases are supported?

A:

  • SQLite (built-in)
  • MySQL (requires pymysql)
  • PostgreSQL (requires psycopg2-binary)
  • Oracle (requires cx_Oracle)
  • SQL Server (requires pyodbc or pymssql)
  • ElasticSearch (added in v2025-06-02)

Q: How do I configure db-query-mcp for different databases?

A: Use a JSON config file. Examples:

{
  "mcpServers": {
    "sqlite_db_mcp": {
      "command": "db-query-mcp",
      "args": [
        "--db",
        "sqlite",
        "--uri",
        "sqlite:///sqlite_company.db",
      ]
    },
    "es_db_mcp": {
      "command": "db-query-mcp",
      "args": [
        "--db",
        "elasticsearch",
        "--uri",
        "https://user:password@localhost:9200?index=test_data_index&ca_certs=/home/user/http_ca.crt",
      ]
    }
  }
}

Q: Is db-query-mcp secure?

A: Yes! It defaults to read-only mode to protect your data.


Q: Can I export query results?

A: Absolutely! Export data to CSV or JSON formats directly from the tool.


Q: What’s next for db-query-mcp?

A: Future updates will add support for MongoDB and GraphDatabase, aiming to become a full-stack DB query MCP.


Q: How do I contribute?

A: PRs are welcome! Check the GitHub repo:
🔗 https://github.com/NewToolAI/db-query-mcp


Q: What’s the license?

A: Apache 2.0 (open-source and free to use).


Need more help? Open an issue on GitHub! 🚀

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
NewToolAI
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago