LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
SkillRisingofficial publisher

cursor.directory

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires cursor

Directory of Cursor rules and MCP servers, with prompts ready to paste.

Practical for starting a project within a clean framework.

Overall score
8.8 /10
Security: nothing to flag
Utility
7.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Setting up an AI-assisted code editor often requires searching for rules, MCP servers or prompts suited to a project, which takes time and yields uneven results. cursor.directory centralises these resources in a single community directory, accessible directly from the browser.

The site lists Cursor rules (.mdc files), MCP servers, skills, agents, hooks and LSP servers, all submitted by the community via a GitHub repository URL. Each plugin is automatically reviewed by a Cursor SDK agent that assigns it a security status (safe, suspicious or malicious) before it appears in the directory.

cursor.directory is aimed at developers using Cursor or Windsurf who want to start a project with already-tested rules and configurations, without starting from scratch. Prompts and rules are ready to copy and paste directly into the editor.

The service is less useful for anyone not working in a compatible editor or looking for AI tools unrelated to code development.

What it offers

  • ·Directory of Cursor rules in .mdc format, ready to copy into a project.
  • ·Listing of MCP servers submitted by the community.
  • ·Support for multiple component types: skills, agents, hooks and LSP servers.
  • ·Plugin submission via a simple GitHub repository URL, no pull request needed.
  • ·Automatic security scan of each submitted plugin, with a displayed verdict (safe, suspicious or malicious).
  • ·Client-side fuzzy search to quickly find a plugin or rule.
  • ·Compatible with Cursor and Windsurf editors.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
cursor, windsurf
Host
cursor
Licence
MIT
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 September 2024

How to install cursor.directory

1. Go to cursor.directory from your browser. 2. Browse or search for a rule, MCP server or other component suited to your project. 3. Check that the plugin's security status is 'safe' before using it. 4. Copy the rule or prompt content and paste it into the appropriate folder of your Cursor or Windsurf project. 5. To submit a plugin, sign in with GitHub or Google at cursor.directory/plugins/new, then paste your GitHub repository URL.

In the same category

Whole category Frame (methods, guardrails) →