Find a bot for every job
Apps that give your bots new tools and skills
Apps that give your bots new tools and skills
Add Arize AX observability to LLM applications — auto-instrumentation, trace export, dataset management, experiment workflows, prompt optimization, and deep linking via the ax CLI.
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
A collection of DataRobot agent skills for model training, deployment, predictions, monitoring, and more.
Brainstorm, plan, debug, review, and compound learnings with AI agents
Simpler, safer way to run MCPs, Skills, and Agents. Discover what's running, enforce security policies in real time, protect secrets, and get full audit trails — all built for how developers actually…
Connect and operate 1000+ external apps from Cursor via the Composio MCP server. Managed OAuth, intelligent tool routing, and a remote sandbox for bulk data processing.
Core skills library: TDD, debugging, collaboration patterns, and proven techniques
UI component and design system framework. Search registries, install components as source code, and audit your project.
Adapter Mind brings your world, and the tribal knowledge contained within it, to Grok Bot and Grok Build in high resolution, before you even ask. Mind does the work before the work, the ETL of your pa…
Opsera DevSecOps Agent — AI-powered architecture analysis, security scanning, compliance auditing, and SQL security for your codebase. Free trial included.
Browser automation for AI agents: navigate, extract, screenshot, and interact with real web pages via a single CLI.
Scaffold and validate new agent plugins. Handles directory setup, manifest generation, and pre-submission quality checks for the marketplace.
Atlan is the context layer for enterprise AI. Connect Cursor to your organization's context repos — the knowledge, data, and semantics your AI agents need to build effectively. Use Atlan's agent skill…
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration,…
Voice AI in Cursor: transcribe audio, synthesize speech, route each leg of a voice pipeline from measured benchmarks, and place real phone calls — through one Speko account.
Connect to Port's agentic SDLC platform in natural language: query the Context Lake, orchestrate workflows, manage agents, and enforce governance.
Skills for working with Langfuse — the open-source LLM engineering platform for tracing, prompt management, and evaluation.
An AI Concierge replaces static forms with adaptive AI conversations that understand real situations, structure key information automatically, and trigger the right next step. Once connected, your AI…
Web search, content extraction, deep research, data enrichment, entity discovery (FindAll), and web monitoring — powered by parallel-cli.
Agent collaboration mail — inbox check, handoffs, and @all threads. Pair with the mutande Mac app MCP.
Simple MCP (Model Context Protocol) server that invokes a single Watson Orchestrate agent remotely. The agent is defined once via environment variables or MCP config. Use this when you want a lightwe…
Load, search, and update your CoreMem mems directly from Cursor. Relevant context loads automatically so every session starts informed.
One group chat for all your AI coding agents. Claude Code, Cursor, Codex CLI, Gemini CLI, Qwen Code and OpenCode sessions talk to each other and to you, share a task sheet with one taker per task, and…
Define private superintelligence and work with Private SuperIntelligence, the private AI concierge for enterprises, family offices and private clients: service overview, six privacy layers, site searc…
Skill and commands that draft ai-ready GitHub Issues and send them to Orbi, an open-source agent that ships each one as a merged PR.
Atomic gap-free id claims, advisory file leases, a shared event ledger + digest, presence, prose handoffs, and a task graph - so multiple agents (Claude Code, Cursor, Codex) stop colliding and re-deri…
A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, Gemini, Mistral, Kimi K2, and DeepSeek.
Zambo is the cross-AI execution layer at zambo.dev. One MCP server with 100+ native tools: crypto prices, site audits, lead research, file tools, and more. Free tier: 20 calls per tool per day, no acc…
Persistent memory for Cursor. Cursor starts each chat cold: it forgets what you told it yesterday and loses context after compaction. MemoryRouter is a remote MCP server that gives Cursor, Claude Code…
Agent skills for building, deploying, evaluating, and monitoring LLM pipelines on the orq.ai platform.
CogmemAi is a persistent cloud memory system for Ai coding assistants. It gives developers self-improving memory that persists across sessions, editors, models, and machines. Key capabilities: - **28…
Integrates neural network-based memory encoding for enhanced long-term information storage and contextually-aware interactions across multiple conversations.
Coordination rooms for AI coding agents — advisory path locks, task board, and conflict alerts so Cursor, Claude Code, and Codex don't collide in one repo. Metadata only: source code never leaves the…
Hand Rush a task from Cursor: an agent does the work in its own cloud sandbox and returns a PR, report or files, with the full trajectory. Start runs, wait for them and read their changes as tool call…
An MCP server that flattens Claude Code sessions — keeping every prompt and event verbatim while reclaiming context tokens, so you resume the exact same raw conversation at a lower token count instead…
User-owned memory for AI agents over remote MCP. Save, search, recall, update, and manage scoped memories across conversations and agents.
Run Cursor's custom subagents on the model in each agent file via Claude Code. Works around Cursor pinning custom subagents to the parent model.
Browser MCP for logged-in tasks — runs in your own Chrome, credentials stay local, zero-token deterministic replay.
API-key remote MCP connections for ONCE action records and CLAIM leases/fencing. Free developer betas; no universal exactly-once guarantee; consumers enforce fencing downstream. Public client examples…
Use the local Codex CLI from Cursor for reviews, delegated tasks, and resumable session transfer.
Context engineering skills for building production-grade AI agent systems — covering fundamentals, degradation patterns, compression, optimization, multi-agent coordination, memory systems, tool desig…
Durable memory for your coding agents: recall past decisions before answering, save the why that should outlive the session.
Bridges Needle AI platform with MCP servers to enable advanced natural language processing and machine learning capabilities.
coti-sdk-private-messaging plugin for Cursor
Build, test and publish Olbrain AI agents (chat agents, automatic jobs, teams and research agents) from Cursor, with Olbrain's Alchemist builder.
Persistent memory for AI agents, shared across tools: write a memory in Cursor, recall it in Claude Code, VS Code, or any MCP client. OAuth sign-in, no API key to paste.
A wiki about your life that writes itself. Save from any AI chat, recall it in the next.
One MCP connector for 53,000+ servers plus your team's private MCPs, from Claude, ChatGPT, Cursor and VS Code. OAuth 2.1, no per-server tokens.
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
Industrial-strength Vibe & Verify engineering suite. Let humans direct the vibe while agents enforce architecture, security, TDD, and multi-tier verification.
Zero-dependency macOS desktop automation MCP server. Control mouse, keyboard, screenshots, and window management using native macOS APIs.
Signed, publicly logged records of what your AI agent did, with proofs anyone can check offline. A proof shows a record existed, unchanged, by a certain time, not that its content is true.
Agents-Hefesto plugin for Cursor
Give Cursor its own cloud computer: a signed-in browser, its own email address and files, for jobs that outlast your session.
Searchable library of 5,900+ agent skills your agent loads on demand — 10 MCP tools. Free tier serves metadata; a free API key unlocks full skill content. Run: npx -p skilldb skilldb-mcp
Persistent memory and project continuity for AI agents. Preserve context, decisions, task progress, and cross-agent handoffs across Cursor sessions.
Know Your Agent: fail-closed eval (ALLOW | DENY | REQUIRE_APPROVE), dual-plane host=ide|runtime, human approval. This plugin is a thin MCP gate — the control plane is the sole PEP.
Local-first MCP server that sits transparently between your AI editor and any model, classifying intent, selecting the right files, and compiling focused context — with zero manual invocation.
Keeps your leads, lists and results in one place for your AI. Saves only when you ask, or automatically after you type "sync datastash". Tells you every time it saves, and deletes on request. Export…
safe-agent-kit plugin for Cursor
Any to Any AI sub-agent. Generate images, videos, PDFs, presentations, research reports, music, spreadsheets, 3D models, memes, diagrams, prototypes, game assets, stickers, and more — from natural lan…
Ask your chat for a tool. Smia builds it, tests it, and keeps it on your own server URL, ready in the same conversation and shareable with your team.
Use the apps you connect to Corsair (Gmail, Slack, GitHub, Linear, Notion and about 400 more) from Cursor: search synced data, read and act in them, and set up automations.
Free, advisory check of a proposed agent action against its operator's written mandate: permit, deny or escalate, with the deciding clause. Cannot stop an action; keeps no request content.
make.fun's MCP server lets an AI agent find bounties, read their requirements, track its entries and claim cash rewards. Reads are public; writes need a key.
Discover, compare, and run 63,000+ API tools from AI agents through one authenticated MCP connection and one pay-per-use balance.
Behavioral trust scoring for 14,800+ MCP servers. Check trust scores, detect anomalies, get leaderboards, and report tool call outcomes before your agent executes sensitive operations.
Let your Cursor agent talk to teammates’ and collaborators’ agents across tools. Share messages and files in persistent rooms with a transcript everyone can read.
Use when you want a delegated second opinion or implementation from GPT (Codex), Gemini, Grok (xAI), or OpenRouter (config-driven, 400+ models) - seven expert subagents (Architect, Plan Reviewer, Scop…
An MCP server with one tool, model_salt. Before a creative task the model calls it and gets back a few choices to settle this time, drawn from randomness outside the model (atmospheric and quantum noi…
MCP server giving your agent Google Gemini's tools: grounded Google Search, deep research, Nano Banana image generation and editing, Veo 3.1 video and real SVG. Free and open source. By Houtini, AI fo…
Open-source E2EE communication protocol, MCP server, and skill for personal AI agents across different owners (https://a4a.network)
Self-hosted identity, memory, and soul for AI agents. Persistent semantic memory that lives in your Flair/Harper instance, not Cursor cloud, and follows the same agent across Cursor, Grok Bot, and Cla…