
Mandatory init variables	"name": The name of the tool "server_info": Information about the MCP server to connect to
API reference	Tools
GitHub link	https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/mcp

Overview

MCPTool is a Tool that allows Haystack to communicate with external tools and services using the Model Context Protocol (MCP). MCP is an open protocol that standardizes how applications provide context to LLMs, similar to how USB-C provides a standardized way to connect devices.

The MCPTool supports multiple transport options:

SSE (Server-Sent Events) for connecting to HTTP servers
StdIO for direct execution of local programs

Learn more about the MCP protocol and its architecture at the official MCP website.

Parameters

name is mandatory and specifies the name of the tool.
server_info is mandatory and needs to be either an SSEServerInfo or StdioServerInfo object that contains connection information.
description is optional and provides context to the LLM about what the tool does.

Usage

Install the MCP-Haystack integration to use the MCPTool:

pip install mcp-haystack

With SSE Transport

You can create an MCPTool that connects to an external HTTP server using SSE transport:

from haystack_integrations.components.tools.mcp import MCPTool, SSEServerInfo

# Create an MCP tool that connects to an HTTP server
server_info = SSEServerInfo(base_url="http://localhost:8000")
tool = MCPTool(name="my_tool", server_info=server_info)

# Use the tool
result = tool.invoke(param1="value1", param2="value2")

With StdIO Transport

You can also create an MCPTool that executes a local program directly and connects to it via stdio transport:

from haystack_integrations.components.tools.mcp import MCPTool, StdioServerInfo

# Create an MCP tool that uses stdio transport
server_info = StdioServerInfo(command="uvx", args=["mcp-server-time", "--local-timezone=Europe/Berlin"])
tool = MCPTool(name="time_tool", server_info=server_info)

# Get the current time in New York
result = tool.invoke(timezone="America/New_York")

In a pipeline

You can integrate an MCPTool into a pipeline with a ChatGenerator and a ToolInvoker:

from haystack import Pipeline
from haystack.components.converters import OutputAdapter
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.tools import ToolInvoker
from haystack.dataclasses import ChatMessage

from haystack_integrations.tools.mcp.mcp_tool import MCPTool, StdioServerInfo


time_tool = MCPTool(
    name="get_current_time",
    server_info=StdioServerInfo(command="uvx", args=["mcp-server-time", "--local-timezone=Europe/Berlin"]),
)
pipeline = Pipeline()
pipeline.add_component("llm", OpenAIChatGenerator(model="gpt-4o-mini", tools=[time_tool]))
pipeline.add_component("tool_invoker", ToolInvoker(tools=[time_tool]))
pipeline.add_component(
    "adapter",
    OutputAdapter(
        template="{{ initial_msg + initial_tool_messages + tool_messages }}",
        output_type=list[ChatMessage],
        unsafe=True,
    ),
)
pipeline.add_component("response_llm", OpenAIChatGenerator(model="gpt-4o-mini"))
pipeline.connect("llm.replies", "tool_invoker.messages")
pipeline.connect("llm.replies", "adapter.initial_tool_messages")
pipeline.connect("tool_invoker.tool_messages", "adapter.tool_messages")
pipeline.connect("adapter.output", "response_llm.messages")

user_input = "What is the time in New York? Be brief."  # can be any city
user_input_msg = ChatMessage.from_user(text=user_input)

result = pipeline.run({"llm": {"messages": [user_input_msg]}, "adapter": {"initial_msg": [user_input_msg]}})

print(result["response_llm"]["replies"][0].text)
# The current time in New York is 1:57 PM.