đ« CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
Auto-update documentation after merge [skip ci]
camel-docs-bote6166175ab43
diff --git a/docs/key_modules/tools.md b/docs/key_modules/tools.mdindex 3e274c7b9..c3042e488 100644--- a/docs/key_modules/tools.md+++ b/docs/key_modules/tools.md@@ -28,7 +28,7 @@ A tool in CAMEL is just a <b>FunctionTool</b>âan interface any agent can call<Card title="Define a Custom Tool" icon="toolbox">You can easily create your own tools for any use case. Just write a Python function and wrap it using <b>FunctionTool</b>:-<CodeBlock language="python" title="add_tool.py">+```python add_tool.py lines icon="python"from camel.toolkits import FunctionTooldef add(a: int, b: int) -> int:@@ -36,7 +36,8 @@ def add(a: int, b: int) -> int:return a + badd_tool = FunctionTool(add)-</CodeBlock>+```+Inspect your toolâs propertiesâsuch as its name, description, and OpenAI-compatible schemaâusing built-in methods:<CodeGroup>@@ -58,35 +59,33 @@ Adds two numbers.</Card><Card title="Using Toolkits" icon="screwdriver-wrench">-Toolkits group related tools for specialized tasksâsearch, math, or automation. Use built-in toolkits or build your own.+Toolkits group related tools for specialized tasksâsearch, math, or automation. Use builtâin toolkits or build your own:-<CodeBlock language="python" title="toolkit_usage.py">+```python toolkit_usage.py lines icon="python"from camel.toolkits import SearchToolkittoolkit = SearchToolkit()-tools = toolkit.get_tools()-</CodeBlock>+tools = toolkit.get_tools()+```You can also wrap toolkit methods as individual FunctionTools:-<CodeBlock language="python" title="custom_tools.py">-from camel.toolkits import FunctionTool, SearchToolkit+```python custom_tools.py lines icon="python"+from camel.toolkits import FunctionTool, SearchToolkitgoogle_tool = FunctionTool(SearchToolkit().search_google)-wiki_tool = FunctionTool(SearchToolkit().search_wiki)-</CodeBlock>+wiki_tool = FunctionTool(SearchToolkit().search_wiki)+```</Card><Card title="Passing Tools to ChatAgent" icon="user-cog">You can enhance any <b>ChatAgent</b> with custom or toolkit-powered tools. Just pass the tools during initialization:-<CodeBlock language="python" title="chatagent_tools.py">+```python chatagent_tools.py lines icon="python"from camel.agents import ChatAgent-tool_agent = ChatAgent(tools=tools, # List of FunctionTools)-response = tool_agent.step("A query related to the tool you added")-</CodeBlock>+```</Card>## Built-in Toolkits@@ -152,42 +151,35 @@ MCP (Model Context Protocol) is a unified protocol for connecting LLMs with exte</Card><Card title="Expose a Toolkit as an MCP Server" icon="rocket">-Any CAMEL toolkit can run as an MCP server. Hereâs how you can start an ArXiv toolkit server from a script:+Any CAMEL toolkit can run as an MCP server. Example for ArxivToolkit:-<CodeGroup>-```python+```python arxiv_mcp_server.py lines icon="python"import argparseimport sys-from camel.toolkits import ArxivToolkitif __name__ == "__main__":parser = argparse.ArgumentParser(- description="Run Arxiv Toolkit with MCP server mode.",- usage=f"python {sys.argv[0]} [--mode MODE] [--timeout TIMEOUT]",+ description="Run Arxiv Toolkit in MCP server mode.",+ usage="python arxiv_mcp_server.py [--mode MODE] [--timeout TIMEOUT]")parser.add_argument("--mode",choices=["stdio", "sse", "streamable-http"],default="stdio",- help="MCP server mode (default: 'stdio')",+ help="MCP server mode (default: 'stdio')")parser.add_argument("--timeout",type=float,default=None,- help="Timeout for the MCP server (default: None)",+ help="Timeout in seconds (default: None)")-args = parser.parse_args()+toolkit = ArxivToolkit(timeout=args.timeout)toolkit.run_mcp_server(mode=args.mode)- ```-</CodeGroup>-Supported modes:-- <b>stdio</b>: Standard input/output (default)-- <b>sse</b>: Server-Sent Events-- <b>streamable-http</b>: Streamable HTTP+```</Card><Card title="MCP Server Configuration" icon="settings">diff --git a/docs/mcp/connecting_existing_mcp_tools.md b/docs/mcp/connecting_existing_mcp_tools.mdnew file mode 100644index 000000000..dbedbe952--- /dev/null+++ b/docs/mcp/connecting_existing_mcp_tools.md@@ -0,0 +1,155 @@+---+title: 'Connect to Existing MCP Tools in CAMEL ChatAgent'+description: 'How to plug any MCP protocol tool (like file systems, web APIs) into your CAMEL ChatAgent for seamless tool-using agents.'+icon: 'network'+---++## Overview++You can connect any Model Context Protocol (MCP) toolâlike the official filesystem serverâdirectly to your CAMEL ChatAgent.+This gives your agents natural language access to external filesystems, databases, or any MCP-compatible service.++<Info>+<strong>Use Case:</strong>+Let your agent list files or read documents by wiring up the official MCP Filesystem server as a toolâno code changes to the agent required!+</Info>++<Steps>+ <Step title="Install the MCP Tool Server">+ You can use any MCP-compatible tool.+ For this example, we'll use the <strong>official filesystem server</strong> from the Model Context Protocol community.+ <br /><br />+ Install globally using npm:+ <br /><br />+ ```bash Terminal+ npm install -g @modelcontextprotocol/server-filesystem+ ```+ </Step>++ <Step title="Start the MCP Tool Server">+ Start the server in the directory you want to expose (e.g., your project root):+ <br /><br />+ ```bash Terminal+ npx -y @modelcontextprotocol/server-filesystem .+ ```+ This limits all file operations to the current directory.+ </Step>++ <Step title="Connect MCP Tool Server to CAMEL">+ Now, connect the MCP tool server to CAMEL using <code>MCPClient</code> or <code>MCPToolkit</code>.+ <br /><br />+ <strong>Direct Client Example (Async):</strong>+ ```python mcp_filesystem_client.py lines icon="python"+ import asyncio+ from camel.utils.mcp_client import MCPClient++ async def mcp_client_example():+ config = {+ "command": "npx",+ "args": ["-y", "@modelcontextprotocol/server-filesystem", "."],+ }+ async with MCPClient(config) as client:+ mcp_tools = await client.list_mcp_tools()+ print("Available MCP tools:", [tool.name for tool in mcp_tools.tools])+ call_tool_result = await client.call_tool(+ "list_directory", {"path": "."}+ )+ print("Directory Contents:")+ for i, item in enumerate(call_tool_result.content[0].text.split('\n')):+ if item.strip():+ print(f" {item}")+ if i >= 4:+ break++ asyncio.run(mcp_client_example())+ ```+ </Step>++ <Step title="Integrate with CAMEL ChatAgent">+ Add the tools exposed by the MCP server to your ChatAgent.+ <br /><br />+ <strong>Async Agent Integration:</strong>+ ```python mcp_agent_integration.py lines icon="python"+ import asyncio+ from pathlib import Path+ from camel.agents import ChatAgent+ from camel.models import ModelFactory+ from camel.toolkits import MCPToolkit+ from camel.types import ModelPlatformType, ModelType++ async def mcp_toolkit_example():+ config_path = Path(__file__).parent / "mcp_servers_config.json"+ async with MCPToolkit(config_path=str(config_path)) as mcp_toolkit:+ sys_msg = "You are a helpful assistant"+ model = ModelFactory.create(+ model_platform=ModelPlatformType.DEFAULT,+ model_type=ModelType.DEFAULT,+ )+ camel_agent = ChatAgent(+ system_message=sys_msg,+ model=model,+ tools=[*mcp_toolkit.get_tools()],+ )+ user_msg = "List 5 files in the project, using relative paths"+ response = await camel_agent.astep(user_msg)+ print(response.msgs[0].content)+ print(response.info['tool_calls'])++ asyncio.run(mcp_toolkit_example())+ ```+ <br />+ <strong>Config Example (<code>mcp_servers_config.json</code>):</strong>+ ```json mcp_servers_config.json lines icon="settings"+ {+ "mcpServers": {+ "filesystem": {+ "command": "npx",+ "args": [+ "-y",+ "@modelcontextprotocol/[email protected]",+ "."+ ]+ }+ },+ "mcpWebServers": {}+ }+ ```+ </Step>++ <Step title="Sync Version (Optional)">+ Use <code>step()</code> for synchronous execution:+ <br /><br />+ ```python mcp_agent_sync.py lines icon="python"+ from pathlib import Path+ from camel.agents import ChatAgent+ from camel.models import ModelFactory+ from camel.toolkits import MCPToolkit+ from camel.types import ModelPlatformType, ModelType++ def mcp_toolkit_example_sync():+ config_path = Path(__file__).parent / "mcp_servers_config.json"+ with MCPToolkit(config_path=str(config_path)) as mcp_toolkit:+ sys_msg = "You are a helpful assistant"+ model = ModelFactory.create(+ model_platform=ModelPlatformType.DEFAULT,+ model_type=ModelType.DEFAULT,+ )+ camel_agent = ChatAgent(+ system_message=sys_msg,+ model=model,+ tools=[*mcp_toolkit.get_tools()],+ )+ user_msg = "List 5 files in the project, using relative paths"+ response = camel_agent.step(user_msg)+ print(response.msgs[0].content)+ print(response.info['tool_calls'])++ mcp_toolkit_example_sync()+ ```+ </Step>+</Steps>++<Info>+That's it!+Your CAMEL agent can now leverage any external tool (filesystem, APIs, custom scripts) that supports MCP. Plug and play!+</Info>diff --git a/docs/mintlify/reference/camel.toolkits.human_toolkit.mdx b/docs/mintlify/reference/camel.toolkits.human_toolkit.mdxindex 1f4d4e6bf..f98ff5cab 100644--- a/docs/mintlify/reference/camel.toolkits.human_toolkit.mdx+++ b/docs/mintlify/reference/camel.toolkits.human_toolkit.mdx@@ -46,14 +46,14 @@ credentials, file paths).### send_message_to_user```python-def send_message_to_user(self, message: str) -> str:+def send_message_to_user(self, message: str):```Use this tool to send a tidy message to the user in one shortsentence.This one-way tool keeps the user informed about your progress,-decisions, or actions. It does not require a response from user.+decisions, or actions. It does not require a response.You should use it to:- Announce what you are about to do (e.g., "I will now search forpapers on GUI Agents.").@@ -66,6 +66,10 @@ papers.").- **message** (str): The tidy and informative message for the user.+**Returns:**++ str: Confirmation that the message was successfully sent.+<a id="camel.toolkits.human_toolkit.HumanToolkit.get_tools"></a>### get_tools