mcp-sql-api
Allows interaction with a PostgreSQL database, enabling SQL queries and data retrieval through an MCP interface.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-sql-apishow me the top 5 customers by revenue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-sql-api/ ├── app/ │ ├── main.py # FastAPI entry point │ ├── api/ # Endpoint layer │ │ ├── sql.py # Raw SQL execution (step 1) │ │ ├── query.py # Query execution API (step 3) │ │ └── agent.py # GPT integration (step 2) │ │ │ ├── core/ # Core logic │ │ ├── db.py # DB connection (PostgreSQL) │ │ └── security.py # SQL control (SELECT restrictions, etc.) │ │ │ ├── services/ # Business logic │ │ ├── sql_executor.py # SQL execution engine │ │ ├── query_service.py # Template query execution │ │ ├── llm_service.py # SQL generation with GPT │ │ └── ir_service.py # Intermediate representation → SQL conversion (step 4) │ │ │ ├── models/ # Data models │ │ ├── schema.py # DB schema definition │ │ ├── query.py # Query definition (with semantics) │ │ └── ir.py # Intermediate representation (crucial) │ │ │ ├── repositories/ # DB access layer │ │ └── base.py │ │ │ └── utils/ │ ├── logger.py │ └── validator.py │ ├── metadata/ # ← Core of MCP │ ├── schema.yaml # Table definitions (for LLM) │ ├── metrics.yaml # KPI definitions │ └── queries.yaml # Semantic API definitions │ ├── prompts/ # Prompts for GPT │ ├── sql_generation.txt │ └── ir_generation.txt │ ├── tests/ │ ├── test_sql.py │ ├── test_query.py │ └── test_ir.py │ ├── requirements.txt └── README.md
This server cannot be deployed
Maintenance
Related MCP Connectors
Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL.
Ask data questions in natural language. Get SQL, insights, and charts from your databases.
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Ask questions in plain language, get answers from your business database. No SQL required.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to query databases using natural language, with automatic schema discovery and SQL compilation.1,042 npm3,168Apache 2.0

Bollard MCPofficial
AlicenseAqualityDmaintenanceEnables safe, AI-driven database interactions with schema discovery, intent validation, and session memory, supporting multiple databases.1426 PyPI2AGPL 3.0- AlicenseNot gradedqualityDmaintenanceEnables natural language querying of SQL databases using AI, supporting multiple database types and automatic schema discovery.1MIT
- AlicenseAqualityBmaintenanceEnables natural-language querying of databases via SQLBot, with datasource discovery, metadata inspection, and report generation.5MIT