Version: 2.6.19 - Clocking over 100% CPU on MCP call -> not responding

[ccwd]

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Version 2.6.19 Cursor MCP calls are causing % CPU to exceed 100 leading to IDE freeze. No crash logs recorded in Macbook Console logs report. This issue was not present in previous Cursor version. Prompt is not resolved, Tokens are used nevertheless.

Steps to Reproduce

12 available MCP’s (mainly docs: netlify, starwind ui, astro, etc)
Use any agent
agent calls MCP Astro Docs
???
Freeze

Expected Behavior

Cursor freezes and the only option is to Reopen or close: "The window is not responding. You can reopen or close the window or keep waiting. [ Reopen ] [ Close ] [ Keep Waiting ] “Don’t Restore Edits”

CPU Time jumps from minutes of real use to hours. Cursor restarted but when running it jumped hours:

Screenshots / Screen Recordings

Operating System

MacOS

Version Information

Version: 2.6.19
VSCode Version: 1.105.1
Commit: 224838f96445be37e3db643a163a817c15b36060
Date: 2026-03-12T04:07:27.435Z
Build Type: Stable
Release Track: Default
Electron: 39.4.0
Chromium: 142.0.7444.265
Node.js: 22.22.0
V8: 14.2.231.22-electron.0
OS: Darwin x64 24.6.0

For AI issues: which model did you use?

sonnet 4.6, opus 4.6

Additional Information

Macbook Pro, 2018, 2.2 GHz 6-Core Intel Core i7, Radeon Pro 555X 4 GB, Intel UHD Graphics 630 1536 MB, 16 GB 2400 MHz DDR4, Mac OS Sequoia 15.7.4

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

[deanrie]

Hey, this is a known issue. The chat markdown renderer can freeze when it processes large responses from MCP servers. A regex in the parser blocks the UI thread, which leads to 100%+ CPU on Cursor Helper Renderer and the app showing not responding.

The Astro docs MCP has already been identified as one of the triggers since it returns large text payloads. There’s a similar thread with a detailed root cause analysis: Window becomes unresponsive and reloads when MCP tool returns large response (markdown lexer regex hang)

The team is aware and the bug is logged. There’s no ETA yet, but your report helps with prioritization.

Workarounds for now:

• Reduce the number of active MCP servers. Keep only the ones you need right now. Running 12 doc servers at once on a 2018 MacBook makes it worse.
• If you can, add a rule telling the agent to request specific docs sections instead of the whole page. That keeps responses smaller.

Let me know if it gets better.