342 boosters for "agents" — open source, verified from GitHub, ready to install
"id": "ai.proofslip/mcp-server", "name": "ProofSlip", "description": "Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects",
Heuristic scoring (no AI key configured).
An emergency escalation agent that routes system problems to human operators when any agent encounters errors or uncertainty. Useful for systems requiring human oversight, but highly specialized and environment-dependent.
A hierarchical taxonomy (L0-L5) for classifying data agents by autonomy level, helping teams clarify capabilities, set expectations, and allocate responsibility in LLM-powered data systems. Useful for architects, product managers, and developers building or evaluating data agents.
Agents Specification provides a standardized framework for configuring AI voice assistants that handle phone calls with customizable personalities and behaviors. Developers building conversational phone systems and businesses deploying automated customer service agents benefit from this reusable specification.
Beelancer is a platform for AI agents to collaborate on tasks, learn skills, and earn rewards within a gamified 'hive' ecosystem. It's designed for developers building multi-agent systems who want to create autonomous workflows with incentive mechanisms.
TinyFish AI Web Agent enables developers to automate website navigation and interaction using AI agents, from single-page tasks to large-scale workflows. It's ideal for teams needing intelligent web automation without manual scripting.
Moltbook is a social network platform designed for AI agents to interact, share content, and build communities through posts, comments, and upvotes. Developers building multi-agent systems and AI applications benefit from this skill to enable agent-to-agent communication and collaboration.
aTars MCP provides crypto market signals, technical indicators, and sentiment analysis capabilities for AI agents working with cryptocurrency data. Developers building crypto trading bots, portfolio analysis tools, and market intelligence systems would benefit from this integration.
A skill booster that enforces opinionated UI constraints and best practices for building accessible, performant interfaces with AI agents on Claude Code. Developers using terminal-based IDEs (Neovim, tmux) benefit from clear, enforceable standards for component selection, animation, and interaction patterns.
SafeRun provides automatic safety guardrails for AI agents by classifying shell commands as BLOCK, ASK, or ALLOW before execution, preventing dangerous operations like force pushes and recursive deletes. Developers and AI systems that execute shell commands benefit from this protection without needing manual configuration.
Prawn Task Manager is an MCP server that converts natural language into structured development tasks with dependency tracking and iterative refinement, enabling AI agents to reason about and manage complex workflows. It's designed for developers building AI-powered systems that need task decomposition and chain-of-thought capabilities.
A comprehensive guide for creating and managing autonomous agents in the CrewAI framework, enabling developers to build specialized AI agents with defined roles, capabilities, and collaboration features.
Turkey-build is a multi-agent orchestration system for software development that supports 7 workflow modes (greenfield, iteration, bugfix, refactor, UI polish, migration, audit) with automated quality gates and visual QA. It benefits developers and teams building or maintaining complex applications who need structured, agent-coordinated development workflows.
DevCrew's AI Agents Architecture provides a specialized multi-agent system with defined roles (Project Manager, Architect, Engineer, QA, Writer) for coordinating software development tasks. Development teams building complex projects benefit from this structured agent framework for automated planning, design, implementation, testing, and documentation.
A comprehensive guide for integrating tools with Claude agents, covering tool registration, custom development, composition patterns, and optimization. Developers building agent-based applications benefit from clear patterns for extending agent capabilities.
A comprehensive guide for developers to build custom agent types and extend the AgentVerse system with reusable, role-based agents. Ideal for teams looking to create specialized AI agents across multiple projects.
A multi-agent red-teaming framework that orchestrates coordinated AI security testing with an arbiter to consolidate findings and maintain an immutable audit trail. Security engineers and AI developers use it to systematically test LLM vulnerabilities with repeatable, deterministic results.
PRISM is a prompt IDE that helps engineers design, test, and iterate on LLM prompts and agents through visual templates and dataset-driven feedback. It benefits prompt engineers, product teams, and developers building AI-powered applications who need structured prompt management and testing workflows.
A safe, high-signal web browsing MCP server that enables Claude to fetch and extract content from web pages using Playwright, ideal for LLM agents needing reliable real-time information. Developers building Claude integrations that require web access will find this particularly valuable.
Converts deepagents' single `task` tool into individual `AgentTool` instances for cleaner sub-agent delegation in adk-deepagents. Developers building hierarchical multi-agent systems benefit from this more modular approach to agent composition.
A modular framework for building security-focused AI agents (Detection, Advisor, Quality) that integrate with MCP servers and multiple LLM providers. Developers building security automation tools and threat analysis pipelines benefit from its extensible architecture and shared tooling.
TnC Helper is a multi-agent AI architecture with 5 specialized GPT-4o agents that inherit from a common BaseAgent class for coordinated task execution. It benefits developers building complex applications requiring distributed AI task handling across multiple domains.
