// category · 12 tools · 6 open source
AI Agent Tools & Protocols
The plumbing for agents: tool protocols, sandboxes, browser infrastructure, web data and search APIs.
Agents need more than a model and a loop. They need a standard way to reach tools, a safe place to run code, a browser to act on websites, and search APIs that return clean text. This category collects that infrastructure.
Protocols. The Model Context Protocol (MCP) is the common interface between agents and tools: you write a tool server once, and Claude Code, Cursor, the Vercel AI SDK, LangGraph and many others can use it. The current spec revision is dated 2026-07-28 and makes the protocol stateless. Learn the basics in how to build an MCP server in Python, see where it differs from a normal API in MCP server vs API, and compare it with agent to agent messaging in MCP vs A2A. Composio packages ready made integrations with hosted authentication for hundreds of apps.
Sandboxes. Code that a model writes should not run on your laptop or your production server. E2B and Daytona start isolated cloud machines in seconds through an SDK, so an agent can install packages, run tests and throw the machine away. Our E2B vs Daytona vs Modal guide compares startup time, limits and pricing.
Browsers. Browser Use, Stagehand and Playwright MCP let an agent click, type and read web pages, and Browserbase hosts the headless browsers they drive. See Browser Use vs Stagehand vs Playwright MCP for which to pick.
Search and scraping. Tavily and Exa return search results built for models, and Firecrawl turns whole pages or sites into clean Markdown. Many agents use one search API plus Firecrawl; the trade offs are in Tavily vs Exa vs Firecrawl.
When you add any of these to an agent, treat tool output as untrusted input: a web page or a tool description can carry instructions meant for the model. Limit what each tool can do, require approval for anything that spends money or deletes data, and pin versions so a compromised update cannot slip in. Official references: the MCP specification and the E2B documentation.
Firecrawlfirecrawl.devTurns websites into clean, LLM ready markdown or structured data via API, with crawling and search.Dev Tools & ProtocolsOpen source★ 196.2k
Browser Usebrowser-use.comOpen source Python library and cloud platform that lets an LLM plan and drive a real browser for open ended web tasks, with CLI and MCP options.Dev Tools & ProtocolsFreemium★ 119.3k
Model Context Protocolmodelcontextprotocol.ioOpen protocol that standardises how applications provide tools and context to LLMs and agents.Dev Tools & ProtocolsOpen source★ 9.5k
Browserbasebrowserbase.comHeadless browser infrastructure for AI agents, plus the open source Stagehand automation framework.Dev Tools & ProtocolsFreemium★ 25.8k
Composiocomposio.devIntegration platform that gives agents authenticated access to hundreds of apps and tools.Dev Tools & ProtocolsFreemium★ 30.8k
E2Be2b.devSecure cloud sandboxes for running AI generated code, powered by lightweight virtual machines.Dev Tools & ProtocolsOpen source★ 14.6k
Playwright MCPplaywright.devMicrosoft's Model Context Protocol server that exposes Playwright browser tools to MCP clients using structured accessibility snapshots, not screenshots.Dev Tools & ProtocolsOpen source★ 38.7k
Stagehanddocs.stagehand.devAI browser SDK from Browserbase with act, extract and observe primitives plus Playwright style page APIs, across TypeScript, Python and Go.Dev Tools & ProtocolsOpen source★ 25.8k
NVIDIA OpenShelldocs.nvidia.comSelf hosted runtime from NVIDIA that runs AI agents in sandboxes with YAML policies for files, per binary network access and credentials, plus a policy prover.Dev Tools & ProtocolsOpen source★ 20.4k
Exaexa.aiSearch engine and API built for AI, returning web results and page contents via embeddings based search.Dev Tools & ProtocolsFreemiumHN 3
Daytonadaytona.ioCloud sandboxes for AI generated code: fast Linux containers by default, plus Linux VM, Windows, GPU and macOS options, with SDKs in five languages.Dev Tools & ProtocolsFreemiumHN 1
Tavilytavily.comWeb search and extraction API tuned for agents and RAG workflows.Dev Tools & ProtocolsFreemium// guides
Guides to AI agent tools & protocols
Browser Use vs Stagehand vs Playwright MCP
Compare Browser Use, Stagehand, and Playwright MCP for AI browser agents: who owns the loop, languages, MCP fit, Browserbase hosting, and when to pick each.
How to Start an AI Automation Agency
How to start an AI automation agency in 2026: pick a niche, build a demo, choose a stack, check n8n and Dify licenses, price the work and run agents safely.
Tavily vs Exa vs Firecrawl: Web Search for Agents
Tavily vs Exa vs Firecrawl for giving AI agents web access: search quality approach, page extraction, crawling, MCP servers, pricing models and code examples.
NVIDIA OpenShell: What It Is and How to Use It
NVIDIA OpenShell explained: how the open source agent sandbox enforces file, network and credential policy, how to install it, and how it compares to Docker.
Claude Managed Agents: Pricing and How It Works
Claude Managed Agents explained: what Anthropic hosts, the $0.08 session hour plus token pricing, self hosted sandboxes, budgets, limits and open source options.
Code Mode MCP Explained: Tool Calls as Code
Code Mode lets an AI agent write a short program that calls its MCP tools instead of calling them one by one. How it works, who supports it, and when to use it.
What Is MCP? The Model Context Protocol Explained
What is MCP? The Model Context Protocol explained: hosts, clients, servers, tools, resources, the stateless 2026 spec, security risks and a tested first run.
Cloudflare Security Audit Skill: How to Use It
How the Cloudflare security audit skill works, how to install it for Claude Code or Codex, what its six phases produce, and the sandbox rules it needs.
How to Use MCP Server in GitHub Copilot
How to use an MCP server in GitHub Copilot: the config file for VS Code, JetBrains, Visual Studio, Copilot CLI and the cloud agent, plus the GitHub MCP server.
How to Run an MCP Server Locally (2026 Guide)
How to run an MCP server locally with npx, uvx or Docker, test it with the MCP Inspector, then connect it to Claude Code, Cursor, VS Code or Codex safely.
How to Build an AI Agent from Scratch in Python
How to build an AI agent from scratch in Python: a tool loop, safe file tools, approvals, a step cap and memory in about 125 lines, on OpenAI or Ollama.
OpenCode 2.0: What's New and How to Upgrade
OpenCode 2.0 adds a shared background service, Code Mode for MCP and a new plugin API, and 2.1 renames SDK fields. Here's what changed and how to upgrade.
AI Agents for Small Business: 8 Real Setups
AI agents for small business, made practical: 8 setups for shops, salons, restaurants, trades and freelancers, with the tools, steps and guardrails for each.
What Is an Agent Harness? (2026 Guide)
An agent harness wraps an LLM with tools, memory, sandboxes, and guardrails. How it differs from a framework, plus Claude, LangChain, and Docker examples.
E2B vs Daytona vs Modal: Agent Sandboxes Compared
E2B vs Daytona vs Modal for running AI agent code safely: isolation, startup, persistence, time limits, GPUs and SDKs compared, with code for each sandbox.
Power BI MCP Server: Which One to Use (2026)
Which Power BI MCP server to use in 2026: Fabric IQ for questions, the Authoring server (hosted or local) for model edits, with setup for Copilot and Claude.
LangChain vs n8n: Which Should You Use?
LangChain vs n8n compared: a code library for agents vs a visual workflow platform built on LangChain JS. Licenses, pricing, MCP and how to use both together.
LangChain vs CrewAI: Which Should You Use?
LangChain vs CrewAI compared with tested code: one agent loop with middleware vs a crew of role based agents. Models, MCP, pricing and using both together.
AI Agents for Trade Businesses: 5 Practical Setups
How to build an AI agent for a trade business: missed call texts, photo quotes, booking, invoices and reviews, wired to Jobber, Housecall Pro or ServiceTitan.
Best Open Source Vector Database in 2026
The best open source vector database for agents and RAG in 2026: Qdrant, Milvus, pgvector, Chroma, LanceDB and Weaviate compared by license, setup and scale.
LanceDB vs Milvus: Which Should You Use?
LanceDB vs Milvus for AI agents: an embedded library on files, or a vector database that grows from a local file to a cluster. Setup, limits and the pick.
What Is Weaviate? Features, Pricing and Use Cases
Weaviate is an open source vector database in Go with hybrid search and a built in MCP server. How it works, a tested agent memory example and cloud pricing.
Vercel AI SDK Guide: Build an Agent With AI SDK 7
The Vercel AI SDK is a free, open source TypeScript toolkit for LLM apps and agents. AI SDK 7 changes, a tested ToolLoopAgent, streaming UI, MCP and costs.
LiteLLM Compromised: What to Do About 1.107.0
LiteLLM compromised again: release 1.107.0 on PyPI and Docker carried a credential stealer. How to check every host, what to rotate and how to pin safely.