Advertise
MCP.so
Sign In

MCP Server ODBC via PyODBC

@OpenLinkSoftware

Repository

Basic information

Category

Other

License

MIT

Transports

stdio

Author

OpenLinkSoftware

About MCP Server ODBC via PyODBC

A simple MCP ODBC server using FastAPI, ODBC and PyODBC.

MCP Server ODBC via PyODBC config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-pyodbc-server": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "uv",
        "--directory",
        "/path/to/mcp-pyodbc-server",
        "run",
        "mcp-pyodbc-server"
      ]
    }
  }
}

MCP Server ODBC via PyODBC tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Server ODBC via PyODBC?

It is a lightweight MCP (Model Context Protocol) server that provides ODBC database access via FastAPI and pyodbc. It is compatible with Virtuoso DBMS and any other DBMS that has an ODBC driver.

How to use MCP Server ODBC via PyODBC?

Install uv and configure an ODBC Data Source Name (DSN) in ~/.odbc.ini. Clone the repository, set environment variables (ODBC_DSN, ODBC_USER, ODBC_PASSWORD, API_KEY) in a .env file. For Claude Desktop, add the server to claude_desktop_config.json using the uv command. The server exposes tools such as podbc_get_schemas, podbc_get_tables, podbc_describe_table, podbc_filter_table_names, podbc_query_database, and Virtuoso‑specific tools.

Key features of MCP Server ODBC via PyODBC

  • List database schemas via podbc_get_schemas
  • Retrieve table names and metadata per schema
  • Describe table structure including columns, keys, and nullability
  • Search tables by name substring
  • Execute SQL queries returning JSONL or Markdown results
  • Support for Virtuoso‑specific SPASQL queries and AI assistant

Use cases of MCP Server ODBC via PyODBC

  • Discover available schemas and tables in any ODBC‑connected database
  • Inspect table definitions for data modeling or migration tasks
  • Execute SQL queries from MCP clients and receive structured results
  • Run SPASQL (SQL/SPARQL hybrid) queries against Virtuoso DBMS
  • Interact with Virtuoso’s AI Support Assistant via a dedicated tool

Frequently asked questions

1

What are the runtime dependencies?

`uv` (package installer), `pyodbc`, and `unixODBC` with a properly configured ODBC DSN. An `.env` file must set `ODBC_DSN`, `ODBC_USER`, `ODBC_PASSWORD`, and `API_KEY`.

2

Which databases are supported?

Any DBMS that provides an ODBC driver. Virtuoso is explicitly supported, and the server works with other ODBC‑compatible databases.

3

How is authentication handled?

Authentication is passed via environment variables (`ODBC_USER`, `ODBC_PASSWORD`) or per‑call optional parameters. An `API_KEY` is used for additional security and can be configured in the environment.

4

Where does the data live?

The data remains in the remote database system accessed through the ODBC connection. No data is stored locally by the server.

5

What transport protocol does the server use?

The server communicates over standard MCP via stdio. For debugging, the MCP Inspector can be used with `npx`.

Comments

More Other MCP servers

ICSS

chokcoco

不止于 CSS

20.7K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
Advertise