Agent Toolbox

by Vincentwei1021

4 266 downloads Not rated yet MIT

GitHub Website

AI
Finance

About

<div align="center"> # ⚡ Agent Toolbox **13 production-ready tools for AI agents — one API key, zero complexity.** [![npm](https://img.shields.io/npm/v/agent-toolbox-mcp?color=6366f1&label=npm)](https://www.npmjs.com/package/agent-toolbox-mcp)…

Details

License: MIT

Explore

- 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.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Agent Toolbox

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

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.

13 production-ready tools for AI agents — one API key, zero complexity.

Docs · Playground · OpenAPI Spec · npm

</div>

---

Building AI agents that interact with the real world? You'd normally need:

| Without Agent Toolbox | With Agent Toolbox |
|---|---|
| 6+ API keys (Google, OpenWeatherMap, Yahoo Finance, ...) | 1 API key |
| Different auth methods per service | Unified Bearer auth |
| Parse different response formats | Consistent JSON responses |
| Handle rate limits per provider | Built-in rate limiting |
| No caching, redundant calls | Smart LRU caching |
| Pay $50-200+/mo for APIs | Free tier: 1,000 calls/mo |

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

McpServers

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

13 production-ready tools for AI agents — one API key, zero complexity.

Docs · Playground · OpenAPI Spec · npm

</div>

---

Why Agent Toolbox?

Building AI agents that interact with the real world? You'd normally need:

Quick Start (30 seconds)

1. Get your free API key

curl -X POST https://api.toolboxlite.com/v1/auth/register \
  -H "Content-Type: application/json" \
  -d '{"email": "[email protected]"}'

2. Make your first call

curl -X POST https://api.toolboxlite.com/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "best AI agent frameworks"}'

3. That's it! 🎉

No credit card. No setup. 13 endpoints ready to use.

13 Endpoints

| Endpoint | Description | Cache |
|----------|-------------|-------|
| POST /v1/search | Web search via DuckDuckGo | 5 min |
| POST /v1/extract | Extract content from any URL | 5 min |
| POST /v1/screenshot | Capture webpage screenshots | 1 hr |
| POST /v1/weather | Weather & forecast | 15 min |
| POST /v1/finance | Stock quotes & exchange rates | 15 min |
| POST /v1/validate-email | Email validation (MX + SMTP) | 1 hr |
| POST /v1/translate | Translate 100+ languages | 1 hr |
| POST /v1/geoip | IP geolocation lookup | 1 hr |
| POST /v1/news | News article search | 5 min |
| POST /v1/whois | Domain WHOIS lookup | 1 hr |
| POST /v1/dns | DNS record queries | 5 min |
| POST /v1/pdf-extract | Extract text from PDFs | 1 hr |
| POST /v1/qr | Generate QR codes | 24 hr |

MCP Server

Use Agent Toolbox as an MCP server in Claude Desktop, Cursor, or Windsurf:

npm install -g agent-toolbox-mcp

Add to Claude Desktop config:

{
  "mcpServers": {
    "agent-toolbox": {
      "command": "agent-toolbox-mcp"
    }
  }
}

See MCP Quickstart Guide for full setup instructions.

SDK Integrations

Python — LangChain

pip install langchain-agent-toolbox

from langchain_agent_toolbox import AgentToolboxSearchTool
search = AgentToolboxSearchTool()

result = search.invoke({"query": "AI agents", "count": 3})

Python — LlamaIndex

pip install llamaindex-agent-toolbox

from llamaindex_agent_toolbox import AgentToolboxSearchTool
search = AgentToolboxSearchTool()

result = search.call(query="AI agents", count=3)

Examples

| Example | Description |
|---------|-------------|
| Research Agent | Auto-research any topic → markdown report |
| Website Monitor | Monitor sites with DNS + screenshots + content |
| MCP Quickstart | Claude Desktop / Cursor / Windsurf setup |

Pricing

| Plan | Price | Calls/month | Rate Limit |
|------|-------|-------------|------------|
| Free | $0 | 1,000 | 60/min |
| Pro | $29/mo | 50,000 | 120/min |
| Scale | $99/mo | 500,000 | 300/min |

All plans include all 13 endpoints. No feature gating.

Self-Hosting

git clone https://github.com/Vincentwei1021/agent-toolbox.git
cd agent-toolbox
npm install && npm run build
cp .env.example .env  # Add your config
npm start

Or with Docker:

docker build -t agent-toolbox .
docker run -p 3100:3100 --env-file .env agent-toolbox

Used By

> Building with Agent Toolbox? Open an issue to get listed here.

License

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Why Agent Toolbox?

Quick Start (30 seconds)

1. Get your free API key

2. Make your first call

3. That's it! 🎉

13 Endpoints

MCP Server

SDK Integrations

Python — LangChain

Python — LlamaIndex

Examples

Pricing

Self-Hosting

Used By

License

More like this

Context 7

1Panel

🔎 GPT Researcher

Serena