QueryWeaver MCP Server

An MCP server for Text2SQL: transforms natural language into SQL using graph schema understanding.

Local serverstdioPython

What is the QueryWeaver MCP server?

Connect QueryWeaver to Claude, Cursor or any other MCP client and it stops being a tab you switch to. An MCP server for Text2SQL: transforms natural language into SQL using graph schema understanding. The queryweaver mcp server is what makes that connection.

What the server does

QueryWeaver is an open-source Text2SQL tool that converts plain-English questions into SQL using graph-powered schema understanding. It helps you ask databases natural-language questions and returns SQL and results.

QueryWeaver exposes a small REST API for managing graphs (database schemas) and running Text2SQL queries. All endpoints that modify or access user-scoped data require authentication via a bearer token. In the browser the app uses session cookies and OAuth flows; for CLI and scripts you can use an API token (see tokens routes or the web UI to create one).

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Overview — QueryWeaver exposes a small REST API for managing graphs (database schemas) and running Text2SQL queries. All endpoints that modify or access
  • Installation — The Installation tool exposed by this server
  • Requirements — The Requirements tool exposed by this server
  • Prerequisites — The Prerequisites tool exposed by this server

Installation

Installation goes through your MCP client rather than a global install: point it at queryweaver on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

Configuration is passed through the environment: FASTAPI_SECRET_KEY, GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GITHUB_CLIENT_ID, GITHUB_CLIENT_SECRET, AZURE_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Python 3.12+ - FalkorDB instance (local or remote) - OpenAI or Azure OpenAI API key (for LLM) - Target SQL database (PostgreSQL or MySQL)

Where it fits

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. QueryWeaver's toolset — Overview, Installation, Requirements and 1 more — is a fair guide to whether it matches your workflow. It is maintained by com.falkordb; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against QueryWeaver's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
OverviewQueryWeaver exposes a small REST API for managing graphs (database schemas) and running Text2SQL queries. All endpoints that modify or access user-scoped data require authentication via a bearer token. In the browser the
InstallationThe Installation tool exposed by this server.
RequirementsThe Requirements tool exposed by this server.
PrerequisitesThe Prerequisites tool exposed by this server.

How to install the QueryWeaver MCP server

{
  "mcpServers": {
    "queryweaver": {
      "command": "uvx",
      "args": ["queryweaver"],
      "env": {
        "FASTAPI_SECRET_KEY": "your-value",
        "GOOGLE_CLIENT_ID": "your-value",
        "GOOGLE_CLIENT_SECRET": "your-value",
        "GITHUB_CLIENT_ID": "your-value",
        "GITHUB_CLIENT_SECRET": "your-value",
        "AZURE_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "GEMINI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.12+ - FalkorDB instance (local or remote) - OpenAI or Azure OpenAI API key (for LLM) - Target SQL database (PostgreSQL or MySQL)
VariableDescriptionRequired
FASTAPI_SECRET_KEYCredential the server authenticates with.Yes
GOOGLE_CLIENT_IDConfiguration value read at startup.Optional
GOOGLE_CLIENT_SECRETCredential the server authenticates with.Yes
GITHUB_CLIENT_IDConfiguration value read at startup.Optional
GITHUB_CLIENT_SECRETCredential the server authenticates with.Yes
AZURE_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use QueryWeaver to Overview.
  • Use QueryWeaver to Installation.
  • Use QueryWeaver to Requirements.

Frequently asked questions

It connects QueryWeaver to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Overview, Installation, Requirements, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with QueryWeaver directly.