And you can configure custom tools via MCP in Cursor Settings -> Features:
@cursor_ai
-
Cursor Agent Ships Custom Tools and Semantic Search Features
By
–
Cursor going entirely from ticket to PR!
— Cursor (@cursor_ai) 10 février 2025
We've shipped several improvements to Cursor's agent, including support for custom tools, better semantic search, and the ability to fix lints. pic.twitter.com/si9CpXZTVBCursor going entirely from ticket to PR! We've shipped several improvements to Cursor's agent, including support for custom tools, better semantic search, and the ability to fix lints.
-
New Agent Feature Available in Composer
By
–
Try it out by opening a new composer, then selecting agent. pic.twitter.com/u2yASsAGqQ
— Cursor (@cursor_ai) 10 février 2025Try it out by opening a new composer, then selecting agent.
-
o3-mini Launches Free for Cursor Users, Sonnet Preferred
By
–
o3-mini is out to all Cursor users! We're launching it for free for the time being, to let people get a feel for the model. The Cursor devs still prefer Sonnet for most tasks, which surprised us.
-
Deepseek models now available in Cursor editor
By
–
Deepseek models are available now in Cursor! Hosted on US servers. While we're big fans of Deepseek, Sonnet still appears to perform much better on real-world tasks. Enjoy!
-
Enable DeepSeek R1 and V3 Models in Settings
By
–
To enable, head to Settings > Models. Then, check deepseek-r1 or deepseek-v3.
-
Cursor Raises $105M Series B for AI Code Editor
By
–
We've raised $105m in Series B funding from Thrive, Andreessen Horowitz, Benchmark, and existing investors. We're delighted to report that Cursor is now used by millions of engineers as their editor of choice. Our tailor-made models generate more code than almost any LLMs in
-
Apply Model Now Edits 5000 Tokens Per Second
By
–
We shipped several upgrades to our Apply model this month. It can now accurately edit over 5k tokens per second.
— Cursor (@cursor_ai) 31 décembre 2024
Try it out in chat, composer, or agent! pic.twitter.com/NHiird1KuqWe shipped several upgrades to our Apply model this month. It can now accurately edit over 5k tokens per second. Try it out in chat, composer, or agent!
-
Speed and Accuracy Improvements in AI Model Training and Inference
By
–
Achieving this speed and accuracy required clever work on training and inference. We hope to release more improvements very soon.
-
New Tab Model Handles Larger Edits Release
By
–
Our new Tab model can handle larger edits! Out now. pic.twitter.com/TtW3AIAD3w
— Cursor (@cursor_ai) 23 décembre 2024Our new Tab model can handle larger edits! Out now.