Browse and search the AI agent directory
1544 agents found
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with tools it would never use in its normal work
Enhances any agent's reasoning capabilities by integrating the think-tools, as described in [Anthropic's article](https://www.anthropic.com/engineering/claude-think-tool)
An MCP Server that autonomously debugs web applications with browser-use browser agents
Coding agent with basic list, read, replace_in_file, write, execute_command and web search tools. Supports multiple projects concurrently
Helping Your AI Agent Identify Hotspots for Refactoring; Help AI Understand How to 'Make Code Better'
Unified agent work logging and observability across ChatGPT, Claude, Cursor, Codex, and OpenClaw with config-first schemas and pluggable sinks
MCP server for meltbook, an AI-agent political discussion board. 50 AI agents autonomously post, vote, and debate Japanese politics. 11 tools for thread creation, posting, voting, and monitoring
AI agent economic settlement. Verify receipts, emit meters (FREE). Net settlements, credit lines, audit-grade balance sheets (PAID/402)
Dynamically load Claude Code skills into AI agents without copying files. Discover, read, and install skills on demand
Bridge any MCP server to the agent:// network — DNS-like identity, discovery, and trust for AI agents. Makes your tools discoverable and callable by other agents via `agent://` URIs with mTLS, trust scores, and capability search
Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines
OpenAPI-MCP: Dockerized MCP Server to allow your AI agent to access any API with existing api docs
Making enterprise AI infrastructure universally accessible. Edge-first platform unifying 12 providers and 100+ models with multi-agent orchestration, HITL workflows, guardrails middleware, and context summarization
Let the agent speak things out loud, notify you when he's done working with a quick summary
MCP server for querying 8,500+ curated awesome lists (1M+ items) and fetching the best resources for your agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one
Precise character-level string indexing for LLMs. Provides tools for finding, extracting, and manipulating text by exact character position to solve position-based operations
MCP server for EchoRift infrastructure primitives (BlockWire, CronSynth, Switchboard, Arbiter). Makes EchoRift's agent infrastructure callable as MCP tools so any MCP client can treat EchoRift like a native capability layer
AI agent knowledge marketplace where agents share solutions and earn tokens. Search, publish, and unlock previously solved problems to reduce token usage and computational costs
Connects to your Pinecone Assistant and gives the agent context from its knowledge engine
