meeseeql
A FastMCP server for exploring multiple databases with support for SELECT queries, table sampling, and structure inspection.
Features
- Multiple Database Support: Configure multiple databases with connection strings or individual fields
- Safe Query Execution: Only SELECT queries allowed for read-only exploration
- Table Sampling: Sample rows from tables with configurable limits
- Schema Inspection: View table structure, columns, and foreign key relationships
Available Tools
- search - Search across tables, columns and enum values
- table_summary - Gets table structure including columns, data types, and foreign keys
- execute_query - Executes SELECT queries on databases with pagination support
- show_database_config - Returns the configured DBs + path to the loaded config file
- reload_config - Reloads configuration. Allows agents to make changes on-demand
- test_connection - Tests database connection to verify configuration
Supported Databases
- PostgreSQL (via psycopg2)
- MySQL (via PyMySQL)
- SQLite (local files and in-memory)
- SQL Server (via pyodbc)
- Snowflake (data warehouse)
Installation
From PyPI:
uvx meeseeql
From GitHub:
uvx --from git+https://github.com/txsmith/meeseeql.git meeseeql
For development:
git clone https://github.com/txsmith/meeseeql.git
cd meeseeql
uv sync --dev
Configuration
Create a config.yaml file with your database connections. The config file is searched in this order:
--config /path/to/config.yaml(command line flag)MEESEEQL_CONFIGenvironment variable./config.yaml(current working directory)~/.config/meeseeql/config.yaml(recommended for users)~/meeseeql.yaml(simple alternative)
See config_example.yaml for more examples of both formats.
- Run the server:
fastmcp dev main.py
Installing as MCP Server
Claude Desktop
claude mcp add --scope user sql-explorer uvx meeseeql
Cursor
Add to your MCP settings in Cursor:
- Open Cursor Settings → Features → Model Context Protocol
- Add a new server configuration:
{
"sql-explorer": {
"command": "uvx",
"args": ["meeseeql"]
}
}
Security considerations
Configure your databases with read-only users to prevent destructive operations. The server does not restrict query types at the application level. Also make sure to keep your config.yaml private as this will likely contain sensitive information.
Development
Running Tests
uv run pytest
Code Formatting
uv run black .
uv run flake8
Metadata
Release files for meeseeql 1.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| meeseeql-1.1.1.tar.gz | 546.5 kB | With provenance | Details for meeseeql-1.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| meeseeql-1.1.1-py3-none-any.whl | Python 3 | none | any | Details for meeseeql-1.1.1-py3-none-any.whl |
Total release size: 580.1 kB
Release files / meeseeql-1.1.1.tar.gz
| Download URL | meeseeql-1.1.1.tar.gz |
|---|---|
| Size | 546.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
39558ebebddbfbf3a471a0a29a5519313fd708e3e84570ab741e39ed04b34c57
|
|
BLAKE2b-256 checksum How to use checksums |
480881bc1c5dd2841c310de518e05aa2063207abd1ae8a5d392c3b420b43d35b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 8, 2025.
Transparency logRelease files / meeseeql-1.1.1-py3-none-any.whl
| Download URL | meeseeql-1.1.1-py3-none-any.whl |
|---|---|
| Size | 33.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0161e31ac8cc834a7ea899d9a05998b8972cc095f4c918fb8d4c8b6c8f4e7b40
|
|
BLAKE2b-256 checksum How to use checksums |
424ec22a544f3837acff505a302573bc588e189aa972c48bacd62aa83f1978a6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 8, 2025.
Transparency logSecurity for meeseeql 1.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for meeseeql-1.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 8, 2025.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.