workflow
agent.tool.workflow(action="create", name="datapipeline", steps=[{"tool": "fileread"}, {"tool": "pythonrepl"}])
How to use it
workflow is exposed by the Tools MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the workflow tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Tools
pip install strands-agents-toolsOther tools in Tools (37)
provider = A2AClientToolProvider(knownagenturls=["http://localhost:9000"]); agent = Agent(tools=provider.tools)
agent.tool.agentcorememory(action="record", content="Hello, I like vegetarian food")
agent.tool.agentgraph(agents=["agent1", "agent2"], connections=[{"from": "agent1", "to": "agent2"}])
agent.tool.brightdata(action="scrapeasmarkdown", url="https://example.com")
browser = LocalChromiumBrowser(); agent = Agent(tools=[browser.browser])
agent.tool.chatvideo(prompt="What are the main topics?", videoid="video123")
codeinterpreter = AgentCoreCodeInterpreter(region="us-west-2"); agent = Agent(tools=[codeinterpreter.codeinterpreter])
agent.tool.elasticsearchmemory(action="record", content="User prefers dark mode")
agent.tool.exagetcontents(urls=["https://example.com/article"], text=True, summary={"query": "key points"})
agent.tool.exasearch(query="Best project management tools", text=True)
agent.tool.fileread(path="path/to/file.txt")
agent.tool.filewrite(path="path/to/file.txt", content="file content")
agent.tool.generateimage(prompt="A sunset over mountains")
agent.tool.generateimagestability(prompt="A tranquil pool")
agent.tool.graph(action="create", graphid="pipeline", topology={"nodes": [...], "edges": [...]})
agent.tool.handofftouser(message="Please confirm action", breakoutofloop=False)
agent.tool.httprequest(method="GET", url="https://api.example.com/data")
agent.tool.imagereader(imagepath="path/to/image.jpg")
agent.tool.journal(action="write", content="Today's progress notes")
agent.tool.loadtool(path="path/to/customtool.py", name="customtool")
agent.tool.mcpclient(action="connect", connectionid="myserver", transport="stdio", command="python", args=["server.py"])
agent.tool.mem0memory(action="store", content="Remember I like to play tennis")
agent.tool.mongodbmemory(action="record", content="User prefers vegetarian pizza")
agent.tool.novareels(action="create", text="A cinematic shot of mountains", s3bucket="my-bucket")
agent.tool.pythonrepl(code="import pandas as pd\ndf = pd.readcsv('data.csv')\nprint(df.head())")
agent.tool.searchvideo(query="people discussing AI")
agent.tool.speak(text="Operation completed successfully", style="green", mode="polly")
agent.tool.stop(message="Process terminated by user request")
agent.tool.swarm(task="Analyze this problem", swarmsize=3, coordinationpattern="collaborative")
agent.tool.tavilycrawl(url="www.tavily.com", maxdepth=2, instructions="Find API docs")
agent.tool.tavilyextract(urls=["www.tavily.com"], extractdepth="advanced")
agent.tool.tavilymap(url="www.tavily.com", maxdepth=2, instructions="Find all pages")
agent.tool.tavilysearch(query="What is artificial intelligence?", searchdepth="advanced")
agent.tool.useagent(prompt="Analyze this code", systemprompt="You are a code analyst.", modelprovider="bedrock")
agent.tool.useaws(servicename="s3", operationname="listbuckets", parameters={}, region="us-west-2")
agent.tool.usecomputer(action="click", x=100, y=200, appname="Chrome")
agent.tool.usellm(prompt="Analyze this data", systemprompt="You are a data analyst")