Tools
UnclaimedA set of tools that gives agents powerful capabilities.
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'tools' -- 'uvx' 'strands-agents-tools'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
38 of 38 tools
Documented tools (38)
From project documentation. A server handshake does not verify each tool’s description or behavior.
a2a_client
provider = A2AClientToolProvider(knownagenturls=["http://localhost:9000"]); agent = Agent(tools=provider.tools)
agent_core_memory
agent.tool.agentcorememory(action="record", content="Hello, I like vegetarian food")
agent_graph
agent.tool.agentgraph(agents=["agent1", "agent2"], connections=[{"from": "agent1", "to": "agent2"}])
bright_data
agent.tool.brightdata(action="scrapeasmarkdown", url="https://example.com")
browser
browser = LocalChromiumBrowser(); agent = Agent(tools=[browser.browser])
chat_video
agent.tool.chatvideo(prompt="What are the main topics?", videoid="video123")
code_interpreter
codeinterpreter = AgentCoreCodeInterpreter(region="us-west-2"); agent = Agent(tools=[codeinterpreter.codeinterpreter])
elasticsearch_memory
agent.tool.elasticsearchmemory(action="record", content="User prefers dark mode")
exa_get_contents
agent.tool.exagetcontents(urls=["https://example.com/article"], text=True, summary={"query": "key points"})
exa_search
agent.tool.exasearch(query="Best project management tools", text=True)
file_read
agent.tool.fileread(path="path/to/file.txt")
file_write
agent.tool.filewrite(path="path/to/file.txt", content="file content")
generate_image
agent.tool.generateimage(prompt="A sunset over mountains")
generate_image_stability
agent.tool.generateimagestability(prompt="A tranquil pool")
graph
agent.tool.graph(action="create", graphid="pipeline", topology={"nodes": [...], "edges": [...]})
handoff_to_user
agent.tool.handofftouser(message="Please confirm action", breakoutofloop=False)
http_request
agent.tool.httprequest(method="GET", url="https://api.example.com/data")
image_reader
agent.tool.imagereader(imagepath="path/to/image.jpg")
journal
agent.tool.journal(action="write", content="Today's progress notes")
load_tool
agent.tool.loadtool(path="path/to/customtool.py", name="customtool")
mcp_client
agent.tool.mcpclient(action="connect", connectionid="myserver", transport="stdio", command="python", args=["server.py"])
mem0_memory
agent.tool.mem0memory(action="store", content="Remember I like to play tennis")
mongodb_memory
agent.tool.mongodbmemory(action="record", content="User prefers vegetarian pizza")
nova_reels
agent.tool.novareels(action="create", text="A cinematic shot of mountains", s3bucket="my-bucket")
python_repl
agent.tool.pythonrepl(code="import pandas as pd\ndf = pd.readcsv('data.csv')\nprint(df.head())")
search_video
agent.tool.searchvideo(query="people discussing AI")
speak
agent.tool.speak(text="Operation completed successfully", style="green", mode="polly")
stop
agent.tool.stop(message="Process terminated by user request")
swarm
agent.tool.swarm(task="Analyze this problem", swarmsize=3, coordinationpattern="collaborative")
tavily_crawl
agent.tool.tavilycrawl(url="www.tavily.com", maxdepth=2, instructions="Find API docs")
tavily_extract
agent.tool.tavilyextract(urls=["www.tavily.com"], extractdepth="advanced")
tavily_map
agent.tool.tavilymap(url="www.tavily.com", maxdepth=2, instructions="Find all pages")
tavily_search
agent.tool.tavilysearch(query="What is artificial intelligence?", searchdepth="advanced")
use_agent
agent.tool.useagent(prompt="Analyze this code", systemprompt="You are a code analyst.", modelprovider="bedrock")
use_aws
agent.tool.useaws(servicename="s3", operationname="listbuckets", parameters={}, region="us-west-2")
use_computer
agent.tool.usecomputer(action="click", x=100, y=200, appname="Chrome")
use_llm
agent.tool.usellm(prompt="Analyze this data", systemprompt="You are a data analyst")
workflow
agent.tool.workflow(action="create", name="datapipeline", steps=[{"tool": "fileread"}, {"tool": "pythonrepl"}])
Tool change history
FAQ
Questions about Tools MCP Server
- How do I connect Tools MCP Server to Claude?
- Run `claude mcp add tools -- uvx strands-agents-tools` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is Tools MCP Server free?
- The listed licence is Apache-2.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Tools MCP Server do?
- Tools MCP Server documents 38 tools to the agent, including a2a_client, agent_core_memory, agent_graph. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.