Goals:

• Integrate the OpenShift Logging stack with the Loki Model Context Protocol server to allow the end-user to interact with Loki (e.g. running queries)  through natural language conversations using the model of their choice (referenced by API_URL and API_KEY).

• Integration of an MCP client into the OpenShift UI, either by adopting an existing implementation or by developing a native one, to allow conversational interactions with MCP servers (e.g., Loki) directly within the console (improving the UX).

• Evaluate the integration of a tiny LLM (e.g., Qwen3-0.6B) for customers who do not have any LLM to leverage on.

Non-Goals

N/A

Motivation

Model Context Protocol (aka MCP) is becoming a standard in the artificial intelligence industry for integrating external tools with LLM, and since Loki provides its own, we should integrate it into OpenShift.

Alternatives

Acceptance Criteria

Risk and Assumptions

Documentation Considerations

Open Questions

Additional Notes

What is MCP? From here:

Model Context Protocol (MCP) is an open protocol developed by Anthropic that enables AI assistants (like Claude) to seamlessly interact with external tools and data sources. Through MCP, AI assistants are no longer limited to their training data but can directly access, query, and operate real-world systems.

The following is an example from ElasticSearch:
https://www.youtube.com/watch?v=wojHoZLyBsI