Polars MCP Server
MCP server providing Polars API reference documentation via introspection of the installed Polars package and additional information via conceptual guides.
Features
- Polars API searchable by keyword
- Full documentation for any Polars function, method, or class
- Conceptual guides for Polars usage patterns
- pandas to Polars translation guide
- Always up-to-date with your installed Polars version
- No external dependencies or pre-built docs needed
Installation
Important: This server introspects the installed Polars package. Install the same Polars version you use in your project to ensure accurate documentation.
From PyPI
# Or install with latest Polars
uv pip install polars-mcp polars
# Install with your project's Polars version
uv pip install polars-mcp polars==1.35.0
From source
# Clone repository
git clone https://github.com/r-brink/polars-mcp
cd polars-mcp
# Install with uv
uv pip install .
Usage
Add to your MCP settings configuration file.
With uvx
{
"mcpServers": {
"polars-mcp": {
"command": "uvx",
"args": [
"--with",
"polars", # set your Polars version here
"polars-mcp"
]
}
}
}
When installing from source
{
"mcpServers": {
"polars-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/polars-mcp",
"run",
"polars_mcp.py"
]
}
}
}
Refer to the documentation on the Model Context Protocol website on how to connect to local MCP servers for an extensive guide.
Standalone Testing
# Test the server
python polars_mcp.py --help
# Run with MCP inspector
npx @modelcontextprotocol/inspector uv run polars_mcp.py
Available Tools
polars_get_guide
Get conceptual guides about Polars usage patterns.
Parameters:
guide(str): Which guide to retrieve'contexts'- Expression contexts (select, filter, group_by, with_columns, over)'expressions'- Expression system and composition patterns'lazy-api'- Lazy evaluation and query optimization'pandas-to-polars'- Complete pandas to Polars translation guide
Example:
Guide: "pandas-to-polars"
Returns: Complete guide with side-by-side pandas/Polars comparisons
polars_search_api
Search for Polars API elements by keyword.
Parameters:
query(str): Search term (e.g., "groupby", "filter", "lazy")limit(int, optional): Max results (default: 20)response_format(str, optional): "markdown" or "json" (default: "markdown")
Example:
Query: "group by"
Returns: List of all group by-related functions and methods
polars_get_docstring
Get complete documentation for a specific API element.
Parameters:
name(str): Full name (e.g., "DataFrame.filter", "col", "LazyFrame")response_format(str, optional): "markdown" or "json" (default: "markdown")
Example:
Name: "DataFrame.filter"
Returns: Full documentation with signature and examples
Available Guides
polars://guides/contexts
Guide to Polars expression contexts:
- What contexts are (select, filter, group_by, with_columns)
- When to use each context
- How contexts affect expression evaluation
- Common patterns for each context
polars://guides/expressions
Complete guide to the Polars expression system:
- What expressions are and how they work
- Composition patterns (chaining, operators, nesting)
- Expression expansion
- Common patterns (aggregations, window functions, conditionals)
polars://guides/lazy-api
Guide to lazy evaluation:
- Eager (DataFrame) vs Lazy (LazyFrame)
- Query optimization (predicate pushdown, projection pushdown)
- When to use each approach
- Best practices for large datasets
polars://guides/pandas-to-polars
- Side-by-side syntax comparisons for all common operations
- Reading data, column selection, filtering, sorting
- Group by aggregations and window functions
- Joins (including semi/anti joins)
- String, datetime, and missing value operations
- Complete worked examples
- Anti-patterns to avoid
- Performance optimization checklist
This guide is specifically optimized for LLMs to quickly translate pandas code to efficient Polars queries.
Why This Server?
- Always current: Documentation reflects your installed Polars version
- Lightweight: No large pre-built documentation databases
- Comprehensive: Combines API reference with conceptual guides
- Migration-friendly: Includes complete pandas translation guide
- Fast: Uses introspection for instant access to documentation
Project Structure
polars-mcp/
├── polars_mcp.py # Main server
├── pyproject.toml # Dependencies
├── guides/ # Conceptual
│ ├── lazy-api.md # Lazy API guide
│ ├── expressions.md # Expression patterns
│ ├── contexts.md # Context behaviors
│ └── pandas-to-polars.md # pandas to Polars
└── README.md
Contributing
Contributions welcome! Please submit issues or pull requests.
Metadata
Release files for iflow-mcp_r-brink-polars-mcp 0.2.1
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 |
|---|---|---|---|---|
| iflow_mcp_r_brink_polars_mcp-0.2.1.tar.gz | 26.3 kB | Without provenance | Details for iflow_mcp_r_brink_polars_mcp-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_r_brink_polars_mcp-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_r_brink_polars_mcp-0.2.1-py3-none-any.whl |
Total release size: 55.5 kB
Release files / iflow_mcp_r_brink_polars_mcp-0.2.1.tar.gz
| Download URL | iflow_mcp_r_brink_polars_mcp-0.2.1.tar.gz |
|---|---|
| Size | 26.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
eb772601fddfa789024354c9523ca4ada8c4166781bfde27459ba659a5076285
|
|
BLAKE2b-256 checksum How to use checksums |
1e71954819dec4b16ce88f086c4a47393e52015796a8c962008685489e127554
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.8
|
Release files / iflow_mcp_r_brink_polars_mcp-0.2.1-py3-none-any.whl
| Download URL | iflow_mcp_r_brink_polars_mcp-0.2.1-py3-none-any.whl |
|---|---|
| Size | 29.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
342c17c6b157e19ef1f582d96a4f8fe0ac850d9fa0f0029c31fd43c5a2c16c0e
|
|
BLAKE2b-256 checksum How to use checksums |
e65d38bf2f839565e237ca4fcdd7035f792d821b98b90154542992b979a1642f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.8
|
Security for iflow-mcp_r-brink-polars-mcp 0.2.1
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.