A simple MCP ODBC server using FastAPI, ODBC and SQLAlchemy.
MCPpedia last refreshed this data
MCP Sqlalchemy Server is an MCP server that a simple MCP ODBC server using FastAPI, ODBC and SQLAlchemy. Its tool list has not been published yet over stdio and http, requires no API key, and scores 77/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"my_database": {
"env": {
"API_KEY": "sk-xxx",
"ODBC_DSN": "dsn_name",
"ODBC_USER": "username",
"ODBC_PASSWORD": "password"
},
"args": [
"--directory",
"/path/to/mcp-sqlalchemy-server",
"run",
"mcp-sqlalchemy-server"
],
"command": "uv"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A lightweight MCP (Model Context Protocol) server for ODBC built with FastAPI, pyodbc, and SQLAlchemy. This server is compatible with Virtuoso DBMS and other DBMS backends that implement a SQLAlchemy provider.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y '@modelcontextprotocol/inspector' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
uv allows ZIP payload obfuscation through parsing differentials
## Impact In versions 0.8.5 and earlier of uv, remote ZIP archives were handled in a streamwise fashion, and file entries were not reconciled against the archive's central directory. This enabled two parser differentials against other Python package installers: 1. An attacker could contrive a ZIP archive that would extract with legitimate contents on some package installers, and malicious contents on others due to multiple local file entries. The attacker could choose which installer to target
uv is vulnerable to arbitrary file write through entry point names
### Impact In versions of uv prior to 0.11.15, when installing a distribution containing an entry point specification (under `console_scripts` or `gui_scripts`), uv would place the generated entry point according to the given name even if doing so resulted in a path outside of the environment's scripts directory. A malicious wheel could use this to place an executable outside of the intended environment, including in a directory already present on the user's `PATH`. This could shadow or overwr
uv vulnerable to arbitrary file deletion through RECORD entries
## Impact Wheel RECORD entries can contain relative paths that traverse outside of the wheel’s installation prefix. In versions 0.11.5 and earlier of uv, these wheels were not rejected on installation and the RECORD was respected without validation on uninstall. uv uses the RECORD to determine files to remove on uninstall. Consequently, a malicious or malformed wheel could induce deletion of arbitrary files outside of the wheel’s installation prefix on uninstall. uv does not use the RECORD fi
PYSEC-2026-2295
A flaw was found in uv. This vulnerability allows an attacker to execute malicious code during package resolution or installation via specially crafted ZIP (Zipped Information Package) archives that exploit parsing differentials, requiring user interaction to install an attacker-controlled package.
uv has differential in tar extraction with PAX headers
### Impact In versions 0.9.4 and earlier of uv, tar archives containing PAX headers with file size overrides were not handled properly. As a result, an attacker could contrive a source distribution (as a tar archive) that would extract differently when installed via uv versus other Python package installers. The underlying parsing differential here originates with astral-tokio-tar, which disclosed this vulnerability as CVE-2025-62518. In practice, the impact of this vulnerability is **low**:
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in data
Manage Supabase projects — databases, auth, storage, and edge functions
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
MCP Security Weekly
Get CVE alerts and security updates for Mcp Sqlalchemy Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A lightweight MCP (Model Context Protocol) server for ODBC built with FastAPI, pyodbc, and SQLAlchemy. This server is compatible with Virtuoso DBMS and other DBMS backends that implement a SQLAlchemy provider.

Install uv:
pip install uv
Or use Homebrew:
brew install uv
unixODBC Runtime Environment Checks:
Check installation configuration (i.e., location of key INI files) by running: odbcinst -j
List available data source names by running: odbcinst -q -s
ODBC DSN Setup: Configure your ODBC Data Source Name (~/.odbc.ini) for the target database. Example for Virtuoso DBMS:
[VOS]
Description = OpenLink Virtuoso
Driver = /path/to/virtodbcu_r.so
Database = Demo
Address = localhost:1111
WideAsUTF16 = Yes
SQLAlchemy URL Binding: Use the format:
virtuoso+pyodbc://user:password@VOS
Clone this repository:
git clone https://github.com/OpenLinkSoftware/mcp-sqlalchemy-server.git
cd mcp-sqlalchemy-server
Update your .envby overriding the defaults to match your preferences
ODBC_DSN=VOS
ODBC_USER=dba
ODBC_PASSWORD=dba
API_KEY=xxx
For Claude Desktop users:
Add the following to claude_desktop_config.json:
{
"mcpServers": {
"my_database": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-sqlalchemy-server", "run", "mcp-sqlalchemy-server"],
"env": {
"ODBC_DSN": "dsn_name",
"ODBC_USER": "username",
"ODBC_PASSWORD": "password",
"API_KEY": "sk-xxx"
}
}
}
}
Here are the pyodbc URL examples for connecting to DBMS systems that have been tested using this mcp-server.
| Database | URL Format |
|---|---|
| Virtuoso DBMS | virtuoso+pyodbc://user:password@ODBC_DSN |
| PostgreSQL | postgresql://user:password@localhost/dbname |
| MySQL | mysql+pymysql://user:password@localhost/dbname |
| SQLite | sqlite:///path/to/database.db |
| Once connected, you can interact with your WhatsApp contacts through Claude, leveraging Claude's AI capabilities in your WhatsApp conversations. |
| name | description |
|---|---|
| podbc_get_schemas | List database schemas accessible to connected database management system (DBMS). |
| podbc_get_tables | List tables associated with a selected database schema. |
| podbc_describe_table | Provide the description of a table associated with a designated database schema. This includes information about column names, data types, nulls handling, autoincrement, primary key, and foreign keys |
| podbc_filter_table_names | List tables, based on a substring pattern from the q input field, associated with a selected database schema. |
| podbc_query_database | Execute a SQL query and return results in JSONL format. |
| podbc_execute_query | Execute a SQL query and return results |