CursorSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/cursor-mcp-tool)
A Model Context Protocol (MCP) implementation that enables seamless integration between Claude AI and desktop applications through Cursor IDE. This tool serves as a bridge between Claude's capabilities and desktop software, allowing for enhanced AI-powered development workflows.
Quick Start (Windows)
Installing via Smithery
To install Cursor for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install cursor-mcp-tool --client claude
Installing Manually
- Prerequisites
- Node.js v18 or higher
- Cursor IDE
- Windows 10 or higher
- Installation
# Install globally npm install -g mcp-cursor # Or install locally git clone https://github.com/yourusername/cursor-mcp.git cd cursor-mcp npm install
- Configuration
- Create a
.envfile in your project root:
# Windows path example DEFAULT_WORKSPACE_PATH=C:/Users/YourUsername/Documents/cursor-workspaces
- Add to Claude's MCP Configuration
Add the following to your Claude configuration:
{
"name": "cursor",
"type": "mcp",
"config": {
"server": "https://glama.ai/mcp/servers/4fg1gxbcex",
"capabilities": ["cursor_control", "window_management"]
}
}- Start the Server
# If installed globally mcp-cursor # If installed locally npm start
Features
- Real-time AI assistance in your development workflow
- Context-aware code suggestions and completions
- Seamless integration with Cursor IDE
-
82aacfb0d0dbOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-cursor -- npx -y [email protected]
{
"mcpServers": {
"mcp-cursor": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (9)
8 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
OpenCursorEval | read | Evaluates the open_cursor tool functionality |
cursor_command | write | Execute commands in a Cursor IDE instance |
cursor_commandEval | read | Evaluates executing a command in a specific Cursor IDE instance |
openCline | read | Opens a new Cline AI assistant tab |
openExtensions | read | Opens the extensions panel |
openSettings | read | Opens Cursor settings |
openTerminal | read | Opens a new terminal |
open_cline_tab | read | Opens a new Cline tab in a specific Cursor instance |
open_cursor | read | Opens Cursor IDE and returns an instance identifier |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, clipboardy, dotenv, fs-extra, mcp-evals, node-window-manager, robotjs, uuid
The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentatio
Gates applied: no_behavioural_pass.
82aacfb0d0dbfull audit observations/trust-audit/mcp-server/buga-luga__cursor.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 82aacfb0d0db | SAFE | B | 89 | first audit |
Questions
What tools does Cursor expose?
9 in total: 8 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Cursor safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Cursor need?
No credential environment variables were found in its source, so it appears to need none.
How does Cursor run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-cursor at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (82aacfb0d0db), read on 2026-10-08. The repository is watched and re-audited when it changes.