菜单
Connect orxhestra agents to MCP tool servers using MCPClient and MCPToolAdapter.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build orxhestra agent trees from declarative YAML orx files. Covers full schema, models, tools, agents, runner, and server.
Expose orxhestra agents as A2A protocol endpoints or connect to remote A2A agents.
Add callbacks to orxhestra agents for logging, monitoring, and error handling. Covers model and tool callbacks.
Add planners to orxhestra agents for structured reasoning. Covers BasePlanner, PlanReActPlanner, and TaskPlanner.
Add dynamic skills to orxhestra agents. Covers Skill, InMemorySkillStore, and skill discovery/loading tools.
Stream events from orxhestra agents including token-by-token output, sub-agent events via AgentTool, and Runner streaming.
| name | mcp-integration |
| description | Connect orxhestra agents to MCP tool servers using MCPClient and MCPToolAdapter. |
Connect to any MCP-compatible tool server.
pip install orxhestra[mcp]
from orxhestra.integrations.mcp import MCPClient, MCPToolAdapter
client = MCPClient("http://localhost:8001/mcp")
adapter = MCPToolAdapter(client)
mcp_tools = await adapter.load_tools()
agent = LlmAgent(
name="MCPAgent",
model=model,
tools=mcp_tools,
instructions="Use the available tools to answer questions.",
)
Pass a FastMCP server object directly (no HTTP needed):
from fastmcp import FastMCP
server = FastMCP("TestServer")
@server.tool
def add(a: int, b: int) -> int:
"""Add two numbers."""
return a + b
client = MCPClient(server) # in-memory, no network
adapter = MCPToolAdapter(client)
tools = await adapter.load_tools()
MCPToolAdapter.load_tools() fetches the tool list from the MCP server and wraps each as a LangChain BaseTool.
tools:
weather:
mcp:
url: "http://localhost:8001/mcp"
local:
mcp:
server: "myapp.mcp_server.server" # dotted import to FastMCP instance