[Enhancement]: Optimize token usage for MCP server #7006
mansiibm
started this conversation in
Feature Requests & Suggestions
Replies: 2 comments 3 replies
-
Use agents, where you can select which individual tools to use from an MCP server. |
Beta Was this translation helpful? Give feedback.
1 reply
-
I'm experiencing an issue when trying to use the Playwright MCP, the
|
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
What features would you like to see added?
Hi , I had configured the playwright mcp in LC. For a single query the token usage touches to 20k . Used gpt-4o mini from azureOpenAI. Same happens for agents set for - google (gemini-2.0-flash-001), openai(gpt-4o-mini) ,anthropic(claude-3-5-haiku).
More details
Used the mcp -server- playwright
librechat-dev-api- danny-avila/librechat-dev-api:1e6b1b9554601179e612123435c9ae394367d5ce
Model used for above conversation - azureOpenAI- gpt-4o-mini
MCP server config- https://github.com/microsoft/playwright-mcp
Which components are impacted by your request?
Other
Pictures
No response
Code of Conduct
Beta Was this translation helpful? Give feedback.
All reactions