Agent Toolbox

Name: Agent Toolbox
Author: Vincentwei1021

@Vincentwei1021

代码仓库

关于 Agent Toolbox

暂无概览

#web-search #content-extraction #screenshot #weather #finance #email-validation #translation #mcp-server

基本信息

分类

AI 与智能体

许可证

MIT

运行时

node

传输方式

stdio

发布者

Vincentwei1021

提交者

Yihao Wei

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "agent-toolbox": {
      "command": "node",
      "args": [
        "/path/to/agent-toolbox/dist/mcp-server.js"
      ],
      "env": {}
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Agent Toolbox?

Agent Toolbox is an MCP server and API that provides 13 production-ready tools for AI agents, such as web search, weather, finance, translation, and PDF extraction. It requires a single API key instead of multiple provider keys, and offers consistent JSON responses and built-in rate limiting. It is for developers building agents that need to interact with the real world.

How to use Agent Toolbox?

Get a free API key via a curl request, then send HTTP POST requests to the API endpoints (e.g., /v1/search) with Bearer auth. For MCP support, install the npm package agent-toolbox-mcp and add it to your MCP client configuration (e.g., Claude Desktop, Cursor, or Windsurf). Python SDKs for LangChain and LlamaIndex are also available.

Key features of Agent Toolbox

13 endpoints covering search, weather, finance, translation, and more.
Single API key with unified Bearer authentication.
Smart LRU caching to reduce redundant calls.
Built-in rate limiting per provider.
Free tier with 1,000 calls per month, no credit card.
Self‑hosting option via Docker or direct install.

Use cases of Agent Toolbox

Building a research agent that automatically gathers web content and produces reports.
Monitoring websites via DNS, screenshots, and content extraction.
Enhancing a chatbot with real‑time weather, stock quotes, or news lookups.
Validating and enriching user‑provided data (emails, domains, IP addresses).

FAQ from Agent Toolbox

What exactly does Agent Toolbox provide?

It is an MCP server and REST API bundling 13 tools (search, extract, screenshot, weather, finance, validate‑email, translate, geoip, news, whois, dns, pdf‑extract, qr) under one key.

How do I get started quickly?

Register via curl to obtain a free API key, then call any endpoint with a Bearer token. For MCP, install the npm package and add it to your client’s MCP servers config.

Are there any runtime dependencies?

The hosted API has no local dependencies beyond the ability to make HTTP requests. The MCP server requires Node.js. The Python SDKs (LangChain, LlamaIndex) require a Python environment with those libraries.

Where does my data live?

When using the hosted API, data is processed on the Agent Toolbox servers. Self‑hosting places all data on your own infrastructure.

What are the transport and authentication methods?

The server communicates via HTTP (REST) or the MCP protocol. Authentication uses a Bearer token in the Authorization header.

AI 与智能体分类下的更多 MCP 服务器

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416