mcp-sql-multi
Enables querying multiple SQL Server, Azure SQL, or Synapse databases through a single MCP interface, with support for read-only targets and various authentication methods.
README
mcp-sql-multi
One MCP server that fronts several SQL Server / Azure SQL / Synapse databases.
Each tool takes a database argument naming a target declared in
connections.json; call list_databases first to see them.
Tools
| Tool | Purpose |
|---|---|
list_databases |
List configured targets (name, server, database, read-only). |
list_tables |
List base tables in a target (optional schema filter). |
describe_table |
Columns, types, lengths, nullability for a table. |
run_query |
Run a query, return up to 1000 rows as JSON (writes blocked on read-only targets). |
Configure targets
Copy the example and edit it with your own databases:
copy connections.example.json connections.json
connections.json is git-ignored (it holds your server names/logins). Passwords
are not stored there — each SQL-auth target names an env var via
password_env, supplied through .env (git-ignored) or the MCP host config.
Supported auth values:
sql- SQL login (user+password_env)aad-integrated- Azure AD using your signed-in Windows/Entra identity (no secret)aad-interactive- Azure AD with a browser sign-in popupaad-service-principal- Azure AD app (client_id+client_secret_env)
Mark trusted-network or service targets "readonly": true to block write/DDL.
Run / test standalone
.venv\Scripts\activate
python -c "import db; print(db.list_targets())"
python -c "import server; print(server.list_tables('dev','dbo'))"
Register with an MCP host
See examples/mcp.json. Point command at
.venv\Scripts\python.exe and args at server.py.
Safety
- Read-only targets refuse write/DDL statements (regex guard).
- Results capped at 1000 rows; 60s query timeout.
aad-interactivetargets trigger a browser sign-in on first query.
License
MIT (c) 2026 Rajiv Datta
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.