Tools

v1.0.0Developer Toolsstable

A set of tools that gives agents powerful capabilities.

agenticagentic-aiagentsaianthropic
Share:
1,066
Stars
0
Downloads
0
Weekly
0/5

What is Tools?

Tools is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to set of tools that gives agents powerful capabilities.

A set of tools that gives agents powerful capabilities.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A set of tools that gives agents powerful capabilities.

Use Cases

Powerful agent capabilities library
Multi-model bedrock agent support
strands-agents

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @squadai/tools

Manual Installation

npx -y @squadai/tools

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Tools

Strands Agents Tools is an open-source Python library providing 50+ pre-built tools for building capable AI agents, covering file I/O, shell execution, web search, browser automation, multi-agent orchestration, memory systems, AWS integration, code execution, and specialized capabilities like video analysis and diagram generation. It integrates with the Strands Agents framework and supports connecting to external MCP servers dynamically, making it a comprehensive toolkit for teams building production-grade autonomous agents across AWS Bedrock, LiteLLM, and other LLM providers. The library is designed for both quick prototyping and enterprise-scale agent deployments.

Prerequisites

  • Python 3.10 or higher
  • pip or uv package manager
  • AWS credentials configured if using AWS-related tools (Bedrock, S3, etc.)
  • Optional API keys: TAVILY_API_KEY for web search, EXA_API_KEY for intelligent search, MEM0_API_KEY for memory, BRIGHTDATA_API_KEY for scraping, TWELVELABS_API_KEY for video analysis
  • An MCP-compatible client if using the MCP interface
1

Install the strands-agents-tools package

Install the base package via pip. Add optional dependency groups for browser automation, memory platforms, RSS, or computer control as needed.

# Base install
pip install strands-agents-tools

# With optional capabilities
pip install strands-agents-tools[mem0_memory,use_browser,rss,use_computer]
2

Set required environment variables

Configure API keys for the tools you plan to use. Only keys for tools you actually call are required.

export TAVILY_API_KEY=tvly-your-key-here
export EXA_API_KEY=your-exa-key
export MEM0_API_KEY=your-mem0-key
export AWS_REGION=us-west-2
export LOG_LEVEL=INFO
3

Import and use tools in your agent

Import specific tools from the library and pass them to your Strands agent. Tools are plain Python callables decorated with @tool.

from strands import Agent
from strands_tools import file_read, file_write, shell, tavily_search, python_repl

agent = Agent(tools=[file_read, file_write, shell, tavily_search, python_repl])
4

Connect to an external MCP server

Use the built-in mcp_client tool to dynamically connect to any MCP server at runtime via stdio, SSE, or streamable HTTP transport.

# Connect via stdio
agent.tool.mcp_client(
    action="connect",
    connection_id="my_tools",
    transport="stdio",
    command="python",
    args=["server.py"]
)

# Connect via HTTP with auth
agent.tool.mcp_client(
    action="connect",
    connection_id="http_server",
    transport="streamable_http",
    server_url="https://api.example.com/mcp",
    headers={"Authorization": "Bearer token"}
)
5

Configure as MCP server for Claude Desktop

Add the tools server to your Claude Desktop MCP configuration to expose Strands tools to Claude.

{
  "mcpServers": {
    "strands-tools": {
      "command": "npx",
      "args": ["-y", "@squadai/tools"],
      "env": {
        "TAVILY_API_KEY": "tvly-your-key-here",
        "AWS_REGION": "us-west-2"
      }
    }
  }
}

Tools Examples

Client configuration

Claude Desktop configuration for the Strands Agents Tools MCP server with common API keys.

{
  "mcpServers": {
    "strands-tools": {
      "command": "npx",
      "args": ["-y", "@squadai/tools"],
      "env": {
        "TAVILY_API_KEY": "tvly-your-key-here",
        "EXA_API_KEY": "your-exa-key",
        "AWS_REGION": "us-west-2",
        "BYPASS_TOOL_CONSENT": "false"
      }
    }
  }
}

Prompts to try

Explore the breadth of Strands Tools capabilities through these example prompts.

- "Search the web for the latest news on AI agent frameworks and summarize the top 3 results"
- "Read the file at ~/data/report.csv, analyze the data, and write a summary to ~/data/summary.md"
- "Execute this Python script and return the output: import math; print(math.pi)"
- "Remember that my preferred coding style uses 2-space indentation and store it in memory"
- "Create a DAG workflow with two agents: one to search the web and one to write a report"
- "Take a screenshot of the current screen and describe what you see"

Troubleshooting Tools

ImportError when importing specific tools

Some tools require optional dependency groups. Install the relevant extras: `pip install strands-agents-tools[use_browser]` for browser tools, `[mem0_memory]` for Mem0, `[use_computer]` for desktop automation, or `[rss]` for RSS tools. Check the package README for the full extras map.

Tavily or Exa search tools return authentication errors

Verify the TAVILY_API_KEY or EXA_API_KEY environment variable is set and exported in the same shell session where your agent runs. Test with `echo $TAVILY_API_KEY`. Keys must be valid and have remaining quota on the respective platforms.

MCP client connection fails with transport errors

For stdio transport, verify the command and args point to an actually running MCP server script. For SSE/HTTP transport, confirm the server URL is reachable and the authorization header format matches what the server expects. Set LOG_LEVEL=DEBUG for detailed connection diagnostics.

Frequently Asked Questions about Tools

What is Tools?

Tools is a Model Context Protocol (MCP) server that set of tools that gives agents powerful capabilities. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Tools?

Install via npm with the command: npx -y @squadai/tools. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Tools?

Tools works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Tools free to use?

Yes, Tools is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "tools": { "command": "npx", "args": ["-y", "@squadai/tools"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Tools?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides