Comparison

Claude Code vs Cursor

How the two compare on the things that decide whether your setup carries over: open standards, license, models and where they run.

Claude CodeCursor
MakerAnthropicAnysphere
LicenseProprietaryProprietary
ModelsAnthropic Claude modelsSee vendor docs
Runs inTerminal, IDE, Desktop, WebIDE, CLI, Web
MCPMCP: supportedMCP: supported
Agent SkillsAgent Skills: supportedAgent Skills: supported
AGENTS.md?AGENTS.md: not yet verifiedAGENTS.md: supported
ACPACP: supportedACP: supported

Key differences

  • Both are proprietary products from their vendors.
  • Claude Code also runs in Terminal, Desktop; Cursor also runs in CLI.
  • Cursor supports AGENTS.md; we have not verified it for Claude Code.
  • Both support MCP, Agent Skills, ACP, so MCP servers, skills and repo instructions you set up carry over if you switch.

In their own words

Claude Code

Anthropic's agentic coding tool. Reads the codebase, edits files, runs commands, and extends through MCP servers, Skills, subagents, hooks and plugin marketplaces. Project instructions live in CLAUDE.md.

Cursor

AI editor and coding agent. Supports MCP, Agent Skills, AGENTS.md, and runs as both an ACP agent and client.

FAQ

Is Claude Code or Cursor open source?
Claude Code is proprietary. Cursor is proprietary.
Do Claude Code and Cursor support MCP servers?
Claude Code: yes. Cursor: yes.
Can I reuse Agent Skills between Claude Code and Cursor?
Yes. Both read the open Agent Skills (SKILL.md) format, so the same skill folder works in both.

Set up MCP servers in either one

More comparisons

Reviewed Oct 5, 2026.