Plugins, MCP servers, events, and 77.7k+ developers building with Cursor.
The Postmark MCP server exposes these Postmark capabilities as tools: sendEmail: Send individual transactional emails with full control sendEmailWithTemplate: Use your existing Postmark templates listTemplates: Browse available email templates getDeliveryStats: Analyze your sending performance
With the Midday MCP you can manage your business directly from tools like Cursor and Claude, features including: - Track time - Manage invoices - View reports like burn rate/expenses and more - List latest transactions - Plus 59 more tools Generate an API key in the Midday Dashboard.
Integrates with Mailtrap Email Platform to enable sending transactional emails via API.
Effortlessly design, deploy, and scale production-grade databases in minutes. Just describe your requirements in natural language, and GibsonAI generates the rest: - A managed, AI-optimized database usable from anywhere, including serverless functions - CRUD API with documentation to manage your data - ORM models and validation schemas - Entity-Relationship Diagram (ERD) to visualize your database - Distinct development and production environments ... and much more Get started at gibsonai.com
Next.js rules and best practices for Cursor
Front End rules and best practices for Cursor
Expo rules and best practices for Cursor
Fastapi rules and best practices for Cursor
This server provides integration with Github's issue tracking system through MCP, allowing LLMs to interact with Github issues.
Data Analyst rules and best practices for Cursor
Java rules and best practices for Cursor
This is an MCP server for PostgREST. It allows LLMs perform database queries and operations on Postgres databases via PostgREST.
At Speakeasy we’re building the next generation of API infrastructure. We aim to give all of our customers a stripe-like developer experience through best in class developer surfaces. Great developer experience drives API adoption, reduces the burden on support and engineering and paves the way for emergent use cases.
ViewOur AI agent is the heartbeat of our product—a sophisticated system combining advanced LLMs, powerful search infra, a modular MCP integrations framework, and intuitive UI to deliver a magical experience for users. We're looking for a talented, driven, and experienced engineer to elevate our AI agent to its full potential. The compensation for this role ranges from $215k to $275k salary & between 1% and 2% equity. This is a leadership role intended for a truly exceptional, senior candidate.
View🍞 Mixedbread (6-person seed team) bakes next-gen search; our OSS models pull millions of HF downloads. Role: Full-Stack AI/Backend Engineer | SF or remote | $100-300k+equity Ship Next.js or Fastapi + Ray features, scale multimodal search, work tight with founders. You: Python or Next wiz, distributed systems, FastAPI/SQLAlchemy/React. Stack: Python, Ray, FastAPI, SQLAlchemy, Next.js, Turborepo, K8s. Perks: free meals, health+gym, epic offsites, visa sponsor. DM: x.com/juliuslipp
ViewSkene is a growth automation layer that reads your codebase: stack, growth surfaces, and revenue leakage. It turns that into prioritized growth loops scored by impact and complexity, not generic advice. Each loop comes with implementation-ready prompts and, on Supabase, deployable SQL. A validator confirms the loop is actually in the repo. From "what should we do for growth?" to "is it implemented and measurable?" in one system, grounded in your code.
Bernstein takes a goal, breaks it into tasks, assigns them to AI coding agents running in parallel, verifies the output, and merges the results. You come back to working code, passing tests, and a clean git history. No framework to learn. No vendor lock-in. Agents are interchangeable workers — swap any agent, any model, any provider. The orchestrator itself is deterministic Python code. Zero LLM tokens on scheduling.
5-person team in London. You'll lead the buildout for AI agents. And unlock even more levels in Gas Town. 3-5 years, Python, LLMs in production.
Announcement · Pricing Claude Opus 4.7 is now available in Cursor! Opus 4.7 is now available in Cursor. We’ve found it to be impressively autonomous and more creative in its reasoning. Have you tried it yet? We’r…
Hi, I just noticed that my Cursor included request quota seems to have changed from 500 to 2000. In the billing/usage page, it now shows Included-Request Usage: 1054 / 2000, and I did not manually change my plan. I wan…
Where does the bug appear (feature/product)? Cursor IDE Describe the Bug The “Model” dropdown vanished Steps to Reproduce Start a new chat Expected Behavior Some way to pick the model I want to use Screenshots / Scre…
Feature request for product/service AI Models Describe the request Issue: Korean text renders as garbled characters (diamond question marks) only when using Composer 1.5 and 2. GPT-5.4 works fine. Request ID: 8090d3c5-…
Where does the bug appear (feature/product)? Cursor IDE Describe the Bug Hi Cursor Team, I recently upgraded to Cursor 3 (latest version), and immediately after the update, I started experiencing critical issues with c…
Where does the bug appear (feature/product)? Cursor IDE Describe the Bug I have PRO plan subscription. Today Cursor IDE always fails to connect any model though network checks are ok. Then it writes “We’re experiencing…
Describe the Bug Clouds would not work with a specific model Steps to Reproduce I am just starting this model with cloud agent and it says always AI provider does not work Screenshots / Screen Recordings Operating S…
Where does the bug appear (feature/product)? Cursor IDE Describe the Bug always getting this response when trying to use 3.1 pro or 3.0 flash (2.5 flash works fine): Provider Error We’re having trouble finding the res…
Persistent long-term memory for Cursor — connect to Membase MCP for long-term memory with hybrid vector search and knowledge graph. No CLI or API keys needed.
Load, search, and update your CoreMem mems directly from Cursor. Relevant context loads automatically so every session starts informed.
Forge app builder skill bundle with Forge MCP integration for building, deploying, and troubleshooting Atlassian Forge apps.
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.
ContextMatic turns your AI agents from API-guessers into API-experts. By feeding agents exact, version-aware SDK methods and typed models for providers like PayPal, Spotify, and Twilio, ContextMatic replaces guesswork and outdated training data with high-fidelity ground truth. This eliminates hallucinations and broken code, ensuring surgical accuracy across 7+ languages so your agents build with precision instead of wasting tokens on trial and error.
Cultural Intelligence Infrastructure for AI Agents. Analyze cultural context, check sensitivity, localize content, compare cultures, and get communication style guidance across 200+ markets.
AI search visibility audit — triple scoring: AEO, GEO, Agent Readiness. Mention readiness, AI Identity Card, competitive gap analysis, business profile detection. Free scan, $1 audit, $3 compare, $5 fix.
29 .mdc rules preventing AI hallucinations: getSession auth bypass, synchronous params crash, deprecated imports, missing RLS, Stripe key exposure. Built for Cursor Agent and Claude Code.
MCP server for Dash, the macOS API documentation browser. Search 200+ up-to-date API docsets and cheat sheets.
Swiss weather data for AI assistants — forecasts, current conditions, stations, and pollen from MeteoSwiss Open Data. Free, no API key required.
pocketlantern plugin for Cursor
Zendesk MCP Server serves as a secure, real-time bridge that lets Cursor fetch, read, and analyze ticket data on demand.
409 API tools from 121 providers through one MCP endpoint. Search flights, get stock quotes, check weather, search jobs across 70+ countries, look up Amazon products, decode VINs, track packages, and 350+ more tools. Pay per call with x402 (USDC on Base) or MPP (USDC on Tempo) — no subscriptions. Auto-registration, no API key setup required.
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
Anti-over-engineering skill for AI coding agents. Teaches your AI when to stop.
Generate software engineering diagrams from text, JSON, ASCII diagram, Mermaid, or images using AI Diagram Maker
