The rules real projects give Cursor's agent, from .cursor/rules.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
srmackeyCursor rulesrmackey/dev-span/.cursor/rules/devspan-router.mdc
How to use the DevSpan MCP server to load and capture engineering context. Applies to all planning and coding work; covers when to recall context and when to create/capture task context proactively.
miapreCursor rulemiapre/mimic-ai/.cursor/rules/mimic-ai.mdc
Golden workflow for building or editing Figma designs with the Mimic AI MCP server (mimic_status, mimic_discover_ds, figma_create_frame, figma_insert_component, mimic_build_table, mimic_build_chart, and related tools).
MANVENDRA-githubCursor ruleMANVENDRA-github/agentry/.cursor/rules/mcp-authoring.mdc
Build a well-behaved Model Context Protocol server — tool and resource design, input schemas, structured errors, transport choice (stdio vs remote), and secret handling. Invoke when writing or extending an MCP server other tools will call. Skip for consuming an existing server.
Prorise-coolCursor ruleProrise-cool/claude-code-plugins/.cursor/rules/claude-code-plugins.mdc
Use when working with Claude Code plugins, skills, agents, hooks, commands, or MCP servers. Plugins extend Claude Code with reusable components that may be installed in user/global locations outside the project.
AWSCursor ruleawslabs/automated-security-helper/ash-agent-plugins/agentic-coding/plugins/cursor/.cursor/rules/ash-mcp.mdc
Run security scans with the ASH (Automated Security Helper) MCP server. Use this skill whenever the user asks to scan for vulnerabilities, run a security check, find CVEs, audit dependencies, check for secrets, run SAST or SCA, scan IaC (Terraform/CloudFormation/Kubernetes), check for hardcoded credentials, or mentions ASH, Bandit, Semgrep, Checkov, Grype, Syft, or detect-secrets. Also trigger when the user wants to find security issues, harden a codebase, or asks "is my code secure". Do NOT trigger for code review without security context, performance audits, or test writing.
edhoferdianCursor ruleedhoferdian/EEF/.cursor/rules/config-hygiene-edho-ferdian.mdc
Clean up the ~/.claude environment: redundant, stale or context-expensive skills, memory, hooks, permissions, MCP servers and caches, one item at a time with an undo path. Use for \"bersihin config\", \"~/.claude berantakan\", \"kebanyakan skill\", \"sesi lambat mulai\", \"context cepat penuh\", \"audit setup gue\".
katalon-labsCursor rulekatalon-labs/true-skills/.cursor/rules/platform-setup.mdc
Set up, verify, and troubleshoot Katalon True Platform/TestOps MCP connectivity for any AI coding agent. Use when you need to install or configure the Katalon MCP server, connect to a Katalon platform account, verify available Katalon MCP tools, diagnose missing authentication or repository access, confirm project/repository discovery, or explain what platform operations are and are not exposed through the MCP. One-time cross-cutting setup, run once by whoever wires the agent to the platform, before any lifecycle skill can work.
moritzkrembReads credentialsCursor rulemoritzkremb/framejam/.cursor/rules/framejam.mdc
Make and review videos and storyboards with the user in the loop, with any video tool (Hyperframes, Remotion, Motion Canvas, ffmpeg, screen recordings). Use when the user wants to make or edit a video, motion graphic or animation, wants a storyboard or shot list reviewed before animating, wants to pick a visual style or a playbook (a method for one kind of video, like a music video, a talking-head short or a product launch), or wants to review a render and send timestamped feedback. Requires the framejam MCP server.
lalal-zzzReads credentialsCursor rulelalal-zzz/mcp-skill-publisher/.cursor/rules/mcp-skill-deployer.mdc
mcp-skill-deployer: when the user explicitly asks to audit, score, optimize, inspect, package, or publish an MCP server or Agent Skill project, run compliance checks, quality scoring, guided optimization, and export file generation. Never execute npm publish, git push, or registry commands without per-step user confirmation.
mchittineniCursor rulemchittineni/cloud-platform-skills/.cursor/rules/skills/ai-agent-security-llm-threats.mdc
Security for LLM and agent systems: direct and indirect prompt injection, the OWASP Top 10 for LLM Applications, MITRE ATLAS technique mapping, excessive agency and tool-scope containment, egress allowlisting to stop data exfiltration, human confirmation for irreversible actions, and treating third-party skills and MCP servers as untrusted code. Use when an agent is given tools or credentials, when retrieved documents or repository files could carry injected instructions, or when reviewing an AI feature before it reaches production.
DXHeroesReads credentialsCursor ruleDXHeroes/mcp-devtools/.cursor/rules/mcp-server-implementation.mdc
MCP Server Implementation Guidelines
Accelar-labsReads credentialsCursor ruleAccelar-labs/sentarys-skills/.cursor/rules/sentarys.mdc
Turn podcasts, streams and long videos into short clips, edit vlogs from raw footage, make faceless videos, caption or translate whole videos, dub clips and publish or schedule them to TikTok, YouTube, Instagram, X and LinkedIn with the Sentarys MCP server, CLI or REST API. Use when the user asks to clip a video or a link into Shorts/Reels/TikToks, edit or export a clip, make a faceless or narrated video, edit a vlog or recap from footage, add captions or subtitles to a video, dub or translate a clip, check Sentarys credits, or post a clip to social accounts.
petrovicistefanCursor rulepetrovicistefan/mcp-api-guardian/.cursor/rules/mcp-tool-server.mdc
Conventions for local-first MCP tool servers in the product family
DXHeroesReads credentialsCursor ruleDXHeroes/mcp-devtools/.cursor/rules/new-package-creation.mdc
Guidelines for Creating a New MCP Server Package
SentryReads credentialsCursor rulegetsentry/spotlight/packages/spotlight/src/server/mcp/.cursor/rules/mcp.mdc
MCP (Model Context Protocol) server development guidelines
bybren-llcReads credentialsCursor rulebybren-llc/safe-agentic-workflow/.cursor/rules/31-mcp-integration.mdc
MCP (Model Context Protocol) server configuration guidance for Cursor IDE.
wchen02Cursor rulewchen02/cursor-agent-learning/.cursor/rules/mcp-patterns.mdc
MCP (Model Context Protocol) usage for agent-framework MCP examples. When to use MCP, check tool schema, server setup, and hooks for audit/gate. Apply when running MCP workflows or editing MCP examples.
frostdev-opsCursor rulefrostdev-ops/gemini-cli/.cursor/rules/03-mcp.mdc
Use this rule to learn how external tools are integrated via MCP, find the MCP host code and server configuration file, identify built-in and external (E5 embedding) servers, and trace how Gemini function calls are executed as MCP tool requests.
airweave-aiReads credentialsCursor ruleairweave-ai/airweave/.cursor/rules/mcp-server.mdc
MCP (Model Context Protocol) server architecture and implementation
arpankernelCursor rulearpankernel/mcp-contributor-guide/.cursor/rules/mcp-contribute.mdc
How to contribute to the modelcontextprotocol org (go-sdk, python-sdk, typescript-sdk, servers, inspector, the spec repo, extensions). Use when finding an MCP issue to work on, evaluating or reproducing an MCP SDK bug, or opening a PR/issue to a modelcontextprotocol repo.
Instruction files for Cursor's agent, kept in .cursor/rules/ as .mdc files.
A rule can apply only to files matching a pattern, or only when the agent asks for it. AGENTS.md always applies.
Copy the .mdc file into your project's .cursor/rules/ directory and adjust its globs.
Open a rule to see its discussion. Reports from people and their agents are coming.
