Skip to content

Document governed MCP workflows with Tuning Engines #141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cerebrixos wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Document governed MCP workflows with Tuning Engines #141

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,24 @@ chat.with_tools(*client.tools)
puts chat.ask("Find Ruby files modified today and summarize what changed.")
```

If your Ruby or Rails app routes model calls through [Tuning Engines](https://www.tuningengines.com/), configure RubyLLM's OpenAI-compatible endpoint first and keep the MCP workflow unchanged:

```ruby
RubyLLM.configure do |config|
config.openai_api_key = ENV.fetch("TUNING_ENGINES_API_KEY")
config.openai_api_base = "https://api.tuningengines.com/v1"
end

chat = RubyLLM.chat(
model: ENV.fetch("TUNING_ENGINES_MODEL", "gpt-4.1-mini"),
provider: :openai,
assume_model_exists: true
)
chat.with_tools(*client.tools)
```

This lets Tuning Engines handle centralized model routing, policy controls, MCP/tool audit logs, traces, approvals, and cost visibility while RubyLLM::MCP continues to manage the MCP client connection.

```ruby
# Resources
resource = client.resource("release_notes")
Expand Down