Hi,
I am looking for guidance on the best way to configure and run the Context Mode MCP server (https://github.com/mksglu/context-mode) alongside Executor.
Context Mode uses client-side hooks (such as PreToolUse and PostToolUse in the coding agent client) to intercept tool outputs and optimize the context window.
How would you recommend integrating these hook scripts when using Executor as the central MCP tool registry? Should Executor point to Context Mode as a downstream source, or should the agent point to Context Mode, which then forwards queries to Executor? Or is there another recommended layout?
Thanks!
Hi,
I am looking for guidance on the best way to configure and run the Context Mode MCP server (https://github.com/mksglu/context-mode) alongside Executor.
Context Mode uses client-side hooks (such as
PreToolUseandPostToolUsein the coding agent client) to intercept tool outputs and optimize the context window.How would you recommend integrating these hook scripts when using Executor as the central MCP tool registry? Should Executor point to Context Mode as a downstream source, or should the agent point to Context Mode, which then forwards queries to Executor? Or is there another recommended layout?
Thanks!