# Strands Agents Tools > A set of tools that gives agents powerful capabilities. - **Type:** MCP server - **Install:** `agentstack add mcp-strands-agents-tools` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [strands-agents](https://agentstack.voostack.com/s/strands-agents) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [strands-agents](https://github.com/strands-agents) - **Source:** https://github.com/strands-agents/tools - **Website:** https://strandsagents.com ## Install ```sh agentstack add mcp-strands-agents-tools ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About Strands Agents Tools A model-driven approach to building AI agents in just a few lines of code. Documentation ◆ Samples ◆ Python SDK ◆ Tools ◆ Agent Builder ◆ MCP Server Strands Agents Tools is a community-driven project that provides a powerful set of tools for your agents to use. It bridges the gap between large language models and practical applications by offering ready-to-use tools for file operations, system execution, API interactions, mathematical operations, and more. ## ✨ Features - 📁 **File Operations** - Read, write, and edit files with syntax highlighting and intelligent modifications - 🖥️ **Shell Integration** - Execute and interact with shell commands securely - 🧠 **Memory** - Store user and agent memories across agent runs to provide personalized experiences with both Mem0, Amazon Bedrock Knowledge Bases, Elasticsearch, and MongoDB Atlas - 🕸️ **Web Infrastructure** - Perform web searches, extract page content, and crawl websites with Tavily and Exa-powered tools - 🌐 **HTTP Client** - Make API requests with comprehensive authentication support - 💬 **Slack Client** - Real-time Slack events, message processing, and Slack API access - 🐍 **Python Execution** - Run Python code snippets with state persistence, user confirmation for code execution, and safety features - 🧮 **Mathematical Tools** - Perform advanced calculations with symbolic math capabilities - ☁️ **AWS Integration** - Seamless access to AWS services - 🖼️ **Image Processing** - Generate and process images for AI applications - 🎥 **Video Processing** - Use models and agents to generate dynamic videos - 🎙️ **Audio Output** - Enable models to generate audio and speak - 🔄 **Environment Management** - Handle environment variables safely - 📝 **Journaling** - Create and manage structured logs and journals - ⏱️ **Task Scheduling** - Schedule and manage cron jobs - 🧠 **Advanced Reasoning** - Tools for complex thinking and reasoning capabilities - 🐝 **Swarm Intelligence** - Coordinate multiple AI agents for parallel problem solving with shared memory - 🤖 **Agent as Tool** - Create nested agent instances with model switching support for multi-model workflows and specialized sub-tasks - 🔗 **Multi-Agent Graph** - Create and manage deterministic DAG-based multi-agent pipelines with output propagation and per-node model configuration - 🔌 **Dynamic MCP Client** - ⚠️ Dynamically connect to external MCP servers and load remote tools (use with caution - see security warnings) - 🔄 **Multiple tools in Parallel** - Call multiple other tools at the same time in parallel with Batch Tool - 🔍 **Browser Tool** - Tool giving an agent access to perform automated actions on a browser (chromium) - 📈 **Diagram** - Create AWS cloud diagrams, basic diagrams, or UML diagrams using python libraries - 📰 **RSS Feed Manager** - Subscribe, fetch, and process RSS feeds with content filtering and persistent storage - 🖱️ **Computer Tool** - Automate desktop actions including mouse movements, keyboard input, screenshots, and application management ## 📦 Installation ### Quick Install ```bash pip install strands-agents-tools ``` To install the dependencies for optional tools: ```bash pip install strands-agents-tools[mem0_memory, use_browser, rss, use_computer] ``` ### Development Install ```bash # Clone the repository git clone https://github.com/strands-agents/tools.git cd tools # Create and activate virtual environment python3 -m venv .venv source .venv/bin/activate # On Windows: venv\Scripts\activate # Install in development mode pip install -e ".[dev]" # Install pre-commit hooks pre-commit install ``` ### Tools Overview Below is a comprehensive table of all available tools, how to use them with an agent, and typical use cases: | Tool | Agent Usage | Use Case | |------|-------------|----------| | a2a_client | `provider = A2AClientToolProvider(known_agent_urls=["http://localhost:9000"]); agent = Agent(tools=provider.tools)` | Discover and communicate with A2A-compliant agents, send messages between agents | | file_read | `agent.tool.file_read(path="path/to/file.txt")` | Reading configuration files, parsing code files, loading datasets | | file_write | `agent.tool.file_write(path="path/to/file.txt", content="file content")` | Writing results to files, creating new files, saving output data | | editor | `agent.tool.editor(command="view", path="path/to/file.py")` | Advanced file operations like syntax highlighting, pattern replacement, and multi-file edits | | shell* | `agent.tool.shell(command="ls -la")` | Executing shell commands, interacting with the operating system, running scripts | | http_request | `agent.tool.http_request(method="GET", url="https://api.example.com/data")` | Making API calls, fetching web data, sending data to external services | | tavily_search | `agent.tool.tavily_search(query="What is artificial intelligence?", search_depth="advanced")` | Real-time web search optimized for AI agents with a variety of custom parameters | | tavily_extract | `agent.tool.tavily_extract(urls=["www.tavily.com"], extract_depth="advanced")` | Extract clean, structured content from web pages with advanced processing and noise removal | | tavily_crawl | `agent.tool.tavily_crawl(url="www.tavily.com", max_depth=2, instructions="Find API docs")` | Crawl websites intelligently starting from a base URL with filtering and extraction | | tavily_map | `agent.tool.tavily_map(url="www.tavily.com", max_depth=2, instructions="Find all pages")` | Map website structure and discover URLs starting from a base URL without content extraction | | exa_search | `agent.tool.exa_search(query="Best project management tools", text=True)` | Intelligent web search with auto mode (default) for optimal results, plus fast and deep search modes | | exa_get_contents | `agent.tool.exa_get_contents(urls=["https://example.com/article"], text=True, summary={"query": "key points"})` | Extract full content and summaries from specific URLs with live crawling fallback | | python_repl* | `agent.tool.python_repl(code="import pandas as pd\ndf = pd.read_csv('data.csv')\nprint(df.head())")` | Running Python code snippets, data analysis, executing complex logic with user confirmation for security | | calculator | `agent.tool.calculator(expression="2 * sin(pi/4) + log(e**2)")` | Performing mathematical operations, symbolic math, equation solving | | code_interpreter | `code_interpreter = AgentCoreCodeInterpreter(region="us-west-2"); agent = Agent(tools=[code_interpreter.code_interpreter])` | Execute code in isolated sandbox environments with multi-language support (Python, JavaScript, TypeScript), persistent sessions, and file operations | | use_aws | `agent.tool.use_aws(service_name="s3", operation_name="list_buckets", parameters={}, region="us-west-2")` | Interacting with AWS services, cloud resource management | | retrieve | `agent.tool.retrieve(text="What is STRANDS?")` | Retrieving information from Amazon Bedrock Knowledge Bases with optional metadata | | nova_reels | `agent.tool.nova_reels(action="create", text="A cinematic shot of mountains", s3_bucket="my-bucket")` | Create high-quality videos using Amazon Bedrock Nova Reel with configurable parameters via environment variables | | agent_core_memory | `agent.tool.agent_core_memory(action="record", content="Hello, I like vegetarian food")` | Store and retrieve memories with Amazon Bedrock Agent Core Memory service | | mem0_memory | `agent.tool.mem0_memory(action="store", content="Remember I like to play tennis", user_id="alex")` | Store user and agent memories across agent runs to provide personalized experience | | bright_data | `agent.tool.bright_data(action="scrape_as_markdown", url="https://example.com")` | Web scraping, search queries, screenshot capture, and structured data extraction from websites and different data feeds| | memory | `agent.tool.memory(action="retrieve", query="product features")` | Store, retrieve, list, and manage documents in Amazon Bedrock Knowledge Bases with configurable parameters via environment variables | | environment | `agent.tool.environment(action="list", prefix="AWS_")` | Managing environment variables, configuration management | | generate_image_stability | `agent.tool.generate_image_stability(prompt="A tranquil pool")` | Creating images using Stability AI models | | generate_image | `agent.tool.generate_image(prompt="A sunset over mountains")` | Creating AI-generated images for various applications | | image_reader | `agent.tool.image_reader(image_path="path/to/image.jpg")` | Processing and reading image files for AI analysis | | journal | `agent.tool.journal(action="write", content="Today's progress notes")` | Creating structured logs, maintaining documentation | | think | `agent.tool.think(thought="Complex problem to analyze", cycle_count=3)` | Advanced reasoning, multi-step thinking processes | | load_tool | `agent.tool.load_tool(path="path/to/custom_tool.py", name="custom_tool")` | Dynamically loading custom tools and extensions | | swarm | `agent.tool.swarm(task="Analyze this problem", swarm_size=3, coordination_pattern="collaborative")` | Coordinating multiple AI agents to solve complex problems through collective intelligence | | current_time | `agent.tool.current_time(timezone="US/Pacific")` | Get the current time in ISO 8601 format for a specified timezone | | sleep | `agent.tool.sleep(seconds=5)` | Pause execution for the specified number of seconds, interruptible with SIGINT (Ctrl+C) | | agent_graph | `agent.tool.agent_graph(agents=["agent1", "agent2"], connections=[{"from": "agent1", "to": "agent2"}])` | Create and visualize agent relationship graphs for complex multi-agent systems | | graph | `agent.tool.graph(action="create", graph_id="pipeline", topology={"nodes": [...], "edges": [...]})` | Create and manage deterministic DAG-based multi-agent graphs using Strands SDK Graph implementation with per-node model configuration | | cron* | `agent.tool.cron(action="schedule", name="task", schedule="0 * * * *", command="backup.sh")` | Schedule and manage recurring tasks with cron job syntax **Does not work on Windows | | slack | `agent.tool.slack(action="post_message", channel="general", text="Hello team!")` | Interact with Slack workspace for messaging and monitoring | | speak | `agent.tool.speak(text="Operation completed successfully", style="green", mode="polly")` | Output status messages with rich formatting and optional text-to-speech | | stop | `agent.tool.stop(message="Process terminated by user request")` | Gracefully terminate agent execution with custom message | | handoff_to_user | `agent.tool.handoff_to_user(message="Please confirm action", breakout_of_loop=False)` | Hand off control to user for confirmation, input, or complete task handoff | | use_llm | `agent.tool.use_llm(prompt="Analyze this data", system_prompt="You are a data analyst")` | Create nested AI loops with customized system prompts for specialized tasks | | use_agent | `agent.tool.use_agent(prompt="Analyze this code", system_prompt="You are a code analyst.", model_provider="bedrock")` | Create nested agent instances with model switching, multi-model workflows, cost optimization, and specialized sub-tasks | | workflow | `agent.tool.workflow(action="create", name="data_pipeline", steps=[{"tool": "file_read"}, {"tool": "python_repl"}])` | Define, execute, and manage multi-step automated workflows | | mcp_client | `agent.tool.mcp_client(action="connect", connection_id="my_server", transport="stdio", command="python", args=["server.py"])` | ⚠️ **SECURITY WARNING**: Dynamically connect to external MCP servers via stdio, sse, or streamable_http, list tools, and call remote tools. This can pose security risks as agents may connect to malicious servers. Use with caution in production. | | batch| `agent.tool.batch(invocations=[{"name": "current_time", "arguments": {"timezone": "Europe/London"}}, {"name": "stop", "arguments": {}}])` | Call multiple other tools in parallel. | | browser | `browser = LocalChromiumBrowser(); agent = Agent(tools=[browser.browser])` | Web scraping, automated testing, form filling, web automation tasks | | diagram | `agent.tool.diagram(diagram_type="cloud", nodes=[{"id": "s3", "type": "S3"}], edges=[])` | Create AWS cloud architecture diagrams, network diagrams, graphs, and UML diagrams (all 14 types) | | rss | `agent.tool.rss(action="subscribe", url="https://example.com/feed.xml", feed_id="tech_news")` | Manage RSS feeds: subscribe, fetch, read, search, and update content from various sources | | use_computer | `agent.tool.use_computer(action="click", x=100, y=200, app_name="Chrome") ` | Desktop automation, GUI interaction, screen capture | | search_video | `agent.tool.search_video(query="people discussing AI")` | Semantic video search using TwelveLabs' Marengo model | | chat_video | `agent.tool.chat_video(prompt="What are the main topics?", video_id="video_123")` | Interactive video analysis using TwelveLabs' Pegasus model | | mongodb_memory | `agent.tool.mongodb_memory(action="record", content="User prefers vegetarian pizza", connection_string="mongodb+srv://...", database_name="memories")` | Store and retrieve memories using MongoDB Atlas with semantic search via AWS Bedrock Titan embeddings | | elasticsearch_memory | `agent.tool.elasticsearch_memory(action="record", content="User prefers dark mode", cloud_id="...", api_key="...")` | Store and retrieve memories using Elasticsearch with semantic search via AWS Bedrock Titan embeddings | \* *These tools do not work on windows* ## 💻 Usage Examples ### File Operations ```python from strands import Agent from strands_tools import file_read, file_write, editor agent = Agent(tools=[file_read, file_write, editor]) agent.tool.file_read(path="config.json") agent.tool.file_write(path="output.txt", content="Hello, world!") agent.tool.editor(command="view", path="script.py") ``` ### Dynamic MCP Client Integration ⚠️ **SECURITY WARNING**: The Dynamic MCP Client allows agents to autonomously connect to external MCP servers and load remote tools at runtime. This poses significant security risks as agents can potentially connect to malicious servers and execute untrusted code. Use with extreme caution in production environments. This tool is different from the static MCP server implementation in the Strands SDK (see [MCP Tools Documentation](https://github.com/strands-agents/docs/blob/main/docs/user-guide/concepts/tools/mcp-tools.md)) which uses pre-configured, trusted MCP servers. ```python from strands import Agent from strands_tools import mcp_client agent = Agent(tools=[mcp_client]) # Connect to a custom MCP server via stdio agent.tool.mcp_client( action="connect", connection_id="my_tools", transport="stdio", command="python", args=["my_mcp_server.py"] ) # List available tools on the server tools = agent.tool.mcp_client( action="list_tools", connection_id="my_tools" ) # Call a tool from the MCP server result = agent.tool.mcp_client( action="call_tool", connection_id="my_tools", tool_name="calculate", tool_args={"x": 10, "y": 20} ) # Connect to a SSE-based server agent.tool.mcp_client( action="connect", connection_id="web_server", transport="sse", server_url="http://localhost:8080/sse" ) # Connect to a streamable HTTP server agent.tool.mcp_client( action="connect", connection_id="http_server", transport="streamable_http", server_url="https://api.example.com/mcp", headers={"Authorization": "Bearer token"}, timeout=60 ) # Load MCP tools into agent's registry for direct access # ⚠️ WARNING: This loads external tools directly into the agent agent.tool.mcp_client( action="load_tools", connection_id="my_tools" ) # Now you can call MCP tools directly as: agent.tool.calculate(x=10, y=20) ``` ### Shell Commands *Note: `shell` does not work on Win … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [strands-agents](https://github.com/strands-agents) - **Source:** [strands-agents/tools](https://github.com/strands-agents/tools) - **License:** Apache-2.0 - **Homepage:** https://strandsagents.com Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-strands-agents-tools - Seller: https://agentstack.voostack.com/s/strands-agents - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.