logo
Free, unlimited AI code reviews that run on commit
git-lrc git-lrc GitHub Install Now We'd appreciate a star git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt

inkeep-rag-service-interface

Establishes connectivity with a robust API infrastructure, enabling efficient orchestration and retrieval of knowledge resources. It supports the creation of sophisticated applications capable of fluidly interfacing with documented assets.

Author

inkeep-rag-service-interface logo

inkeep

MIT License

Quick Info

GitHub GitHub Stars 22
NPM Weekly Downloads 0
Tools 1
Last Updated 2026-02-19

Tags

documentationpythonmcpbusiness toolsinteract documentationintegrates documentation

Inkeep-Powered RAG Service Interface (Python)

This repository provides the necessary components to power the Model Context Protocol (MCP) server using your proprietary documentation and product knowledge via Inkeep.

Prerequisites

  • An active subscription with Inkeep for managing and serving the Retrieval-Augmented Generation (RAG) backend.
  • The uv utility, designated as the Python environment manager (repository link).

Local Environment Configuration

Execute the following sequence of shell commands to initialize the local environment:

bash git clone https://github.com/inkeep/mcp-server-python.git cd mcp-server-python uv venv uv pip install -r pyproject.toml

Retain the absolute directory path to this repository; this location will be designated as <YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH> subsequently.

Securing the Authorization Credential

To enable authenticated access to the Inkeep services, perform these steps:

  1. Log into your dedicated Inkeep Administration Portal.
  2. Navigate to the project management area and select the relevant project.
  3. Access the 'Integrations' tab.
  4. Initiate the creation of a new integration, selecting the 'API' option.
  5. Assign a descriptive identifier to this new API credential.
  6. Finalize the creation process.
  7. The system will present a newly generated API Key. This token is required for authenticating all service requests.

We will denote this credential as <YOUR_INKEEP_API_KEY> for the ensuing configuration stages.

Client Integration with MCP Framework

Refer to the official quickstart guide to configure the target client application (e.g., Claude Desktop).

Within your client configuration file, specifically claude_desktop_config.json, inject the following definition into the mcpServers object:

claude_desktop_config.json { "mcpServers": { "inkeep-mcp-server": { "command": "uv", "args": [ "--directory", "", "run", "-m", "inkeep_mcp_server" ], "env": { "INKEEP_API_BASE_URL": "https://api.inkeep.com/v1", "INKEEP_API_KEY": "", "INKEEP_API_MODEL": "inkeep-rag", "INKEEP_MCP_TOOL_NAME": "search-product-content", "INKEEP_MCP_TOOL_DESCRIPTION": "Fetches detailed technical specifications and documentation pertinent to Inkeep products. Queries should be framed as natural language inquiries regarding the Inkeep ecosystem." } }, } }

Note: If necessary, the command field may require the system's absolute path to the uv executable (obtainable via which uv on Unix-like systems or where uv on Windows).

See Also

`