openfga-mcp
If you are the rightful owner of openfga-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An experimental Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to interact with OpenFGA stores for authorization and vibe coding.
The OpenFGA MCP Server is an innovative server implementation that leverages the Model Context Protocol (MCP) to allow Large Language Models (LLMs) to interact with OpenFGA stores. This server facilitates the reading, searching, and manipulation of OpenFGA stores, enabling advanced authorization capabilities for agentic AI and fine-grained vibe coding for human users. The server is designed to work with Python 3.12+ and requires an operational OpenFGA server. It provides a comprehensive suite of tools for managing stores, authorization models, and relationship tuples, as well as performing relationship queries. The server can be easily integrated with various platforms and is configurable to suit different authentication methods.
Features
- Store Management: Tools for creating, listing, retrieving, and deleting OpenFGA stores.
- Authorization Model Management: Tools for writing and reading authorization models, including retrieving specific model versions.
- Relationship Tuples Management: Tools for writing and reading relationship tuples in OpenFGA.
- Relationship Queries: Tools for checking user-object relationships and listing related objects or users.
