MCP Connector

Integrate Semantic Kernel with MCP Servers

Semantic Kernel MCP integration includes eight Python example files demonstrating agent, plugin, and sampling patterns with Model Context Protocol.

Works with azure ai

70
Spark score
out of 100
Updated last month
Source checked Aug 6, 2026
Version dotnet-1.78.0
Models

Add to Favorites

Why it matters

Connect Semantic Kernel applications to Model Context Protocol (MCP) servers, enabling agents and plugins to interact with external data sources and services.

Outcomes

What it gets done

01

Integrate MCP servers with Semantic Kernel agents.

02

Develop and deploy MCP plugins for Semantic Kernel.

03

Sample data from MCP servers for agent use.

04

Connect to local and Azure AI MCP servers.

Source

Get it from source

Spark does not host a copy of it.

Open source

Reports

Agent outcome reports

No reports yet

Overview

Semantic Kernel - Mcp

Semantic Kernel MCP integration includes eight Python example files: agent_with_http_mcp_plugin.py, agent_with_mcp_agent.py, agent_with_mcp_plugin.py, agent_with_mcp_sampling.py, azure_ai_agent_with_local_server.py, azure_ai_agent_with_mcp_plugin.py, local_agent_with_local_server.py, and mcp_as_plugin.py. The file names suggest patterns involving MCP servers, agents, plugins, and sampling. Use this when working with Semantic Kernel and Model Context Protocol and you want to examine example implementations. The file names suggest patterns for local servers, HTTP connections, Azure AI agents, plugins, and sampling workflows.

What it does

Semantic Kernel MCP integration provides a collection of eight Python example files related to Model Context Protocol (MCP) integration. The examples include files named agent_with_http_mcp_plugin.py, agent_with_mcp_agent.py, agent_with_mcp_plugin.py, agent_with_mcp_sampling.py, azure_ai_agent_with_local_server.py, azure_ai_agent_with_mcp_plugin.py, local_agent_with_local_server.py, and mcp_as_plugin.py.

When to use - and when NOT to

Use this integration when you are working with Semantic Kernel and Model Context Protocol and want to examine example implementations. The file names suggest patterns involving agents, plugins, local servers, Azure AI agents, HTTP connections, and sampling.

Do not use this if you are working with a different AI framework outside the Semantic Kernel ecosystem, as these examples are specifically designed for Semantic Kernel's agent architecture. Avoid this if you need production-ready libraries rather than sample code demonstrating integration patterns.

Inputs and outputs

The source material lists eight example files without detailed descriptions of their inputs and outputs.

Who it's for

This integration is for Python developers working with Semantic Kernel and Model Context Protocol who want to examine example implementations. The eight example files suggest different patterns and architectural approaches.

Source README

Model Context Protocol (MCP) integration: MCP servers, agents, plugins, and sampling

Examples (8 files):

  • agent_with_http_mcp_plugin.py
  • agent_with_mcp_agent.py
  • agent_with_mcp_plugin.py
  • agent_with_mcp_sampling.py
  • azure_ai_agent_with_local_server.py
  • azure_ai_agent_with_mcp_plugin.py
  • local_agent_with_local_server.py
  • mcp_as_plugin.py

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.