/explore
|
You are here 
|
til.simonwillison.net | ||
| | | | |
simonwillison.net
|
|
| | | | | ||
| | | | |
simonwillison.net
|
|
| | | | | ||
| | | | |
simonwillison.net
|
|
| | | | | ||
| | | | |
ezyang.github.io
Model Context Protocol servers provide a standard interface for LLMs to interact with their environment. Cursor Agent mode and Claude Code use agents extensively. For example, instead of needing a separate RAG system (e.g., as previously provided by Cursor) to find and feed the model relevant context files, the LLM can instead call an MCP which will let it lookup what files it wants to look at before deciding what to do. Similarly, a model can run tests or build and then immediately work on fixing problems when this occurs. It is clear that Anthropic's built-in MCP servers are useful, and you should use agent mode when you can. |
|
| | | |||
