Skip to main content

Python CLI for kFinance

Project description

kFinance

The kFinance Python library provides a simple interface for the LLM-ready API, streamlining API requests and response handling. It can be used on its own, with LLMs, or integrated into applications.

For a complete overview of the functions, usage, and features of the kFinance Python library, please refer to documentation here.

Any questions or suggestions can be sent to the kFinance Maintainers.

Setup

You can install kFinance on PyPI via

pip install kensho-kfinance

Getting started

To receive access, please email S&P Global Market Intelligence for information on free trials and pricing.

Once access is obtained, get started using the Authentication Guide and Usage Guide.

To get started, we provide some notebooks:

  • The LLM-ready API Basic Usage notebook demonstrates how fetch data with the kFinance client.
  • The tool_calling notebooks show how the kFinance library can be used for tool calling. We provide notebooks for OpenAI (GPT), Anthropic (Claude), and Google (Gemini). Each of these integrations comes in a langchain version, which uses langchain as a wrapper to simplify the integration, and as a lower level non-langchain version.

We also provide an interactive notebook that demonstrates some usage examples.

MCP (Model Context Protocol)

To run the kFinance MCP server use:

python -m kfinance.mcp

This function initializes and starts an MCP server that exposes the kFinance tools. The server supports multiple authentication methods and transport protocols to accommodate different deployment scenarios.

The server's full signature is as follows:

kfinance.mcp [--stdio,-s]/[--sse, ] --refresh-token <refresh-token> --client-id <client-id> --private-key <private-key>

Authentication Methods (in order of precedence):

  1. Refresh Token: Uses an existing refresh token for authentication. The --refresh-token <refresh-token> argument must be provided.
  2. Key Pair: Uses client ID and private key for authentication. Both the --client-id <client-id> and --private-key <private-key> arguments must be provided.
  3. Browser: Falls back to browser-based authentication flow. This occurs if no auth arguments are provided.

Transport Layers:

  • stdio can be set by passing either --stdio or -s
  • sse can be set by passing --sse or no other transport related flag

Development

Working with Local Package Version

If you need to develop using a local version of the kFinance package in another project that uses poetry for package and dependency management, follow these steps:

  1. In your dependent project's pyproject.toml, replace the kFinance package version specification:

    # Replace this:
    # kensho-kfinance = "~2.0.1"
    # With this:
    kensho-kfinance = { path = "/absolute/path/to/kfinance", develop = true }
    

    The develop = true flag ensures that the package always matches your local version without requiring reinstallation after changes.

  2. Update your project's dependencies:

    poetry update    # Update poetry.lock with new changes
    poetry install   # Install dependencies with updated configuration
    

    If you encounter the error "your pyproject.toml file has significantly changed", run:

    poetry lock     # Sync the changes to poetry.lock
    

Versioning

The kFinance uses semantic versioning (major, minor, patch). To bump the version, add a new entry in CHANGELOG.md. This will generate a new version of the library as part of the release process.

License

Use is solely in accordance with the signed agreement between your entity and S&P.

Copyright 2025-present Kensho Technologies, LLC. The present date is determined by the timestamp of the most recent commit in the repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kensho_kfinance-5.0.0.tar.gz (151.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kensho_kfinance-5.0.0-py3-none-any.whl (173.1 kB view details)

Uploaded Python 3

File details

Details for the file kensho_kfinance-5.0.0.tar.gz.

File metadata

  • Download URL: kensho_kfinance-5.0.0.tar.gz
  • Upload date:
  • Size: 151.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for kensho_kfinance-5.0.0.tar.gz
Algorithm Hash digest
SHA256 8c212c8be4b4ae292071aaf3df2b00ae4cb00a4674d603a6184530807487cff7
MD5 02cfaa669713bc9362d98e709fe5a386
BLAKE2b-256 81b942143223fff4f8f47aad0b9847bd5a8cf92b7263ed25086e6afd74d8c351

See more details on using hashes here.

Provenance

The following attestation bundles were made for kensho_kfinance-5.0.0.tar.gz:

Publisher: python-publish.yml on kensho-technologies/kfinance

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file kensho_kfinance-5.0.0-py3-none-any.whl.

File metadata

  • Download URL: kensho_kfinance-5.0.0-py3-none-any.whl
  • Upload date:
  • Size: 173.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for kensho_kfinance-5.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6464e7bab8f2bfff1164117604af57011d93591bb68f541dfeb7b093ac51d9a4
MD5 9b08c3c9f65cab64e98b12f337cacd32
BLAKE2b-256 03943ef5ec81c2cd11e539a50531500d2c2fc5aa7e039c5edd62dc6c32f1f002

See more details on using hashes here.

Provenance

The following attestation bundles were made for kensho_kfinance-5.0.0-py3-none-any.whl:

Publisher: python-publish.yml on kensho-technologies/kfinance

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page