Copilot Studio MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Copilot Studio MCP Serverecho 'hello'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Copilot Studio MCP Server
This is an example MCP server that can be used with Microsoft Copilot Studio.
It uses Python and the official MCP Python SDK, and provides the following two tools:
echo: Repeats the input sentence 3 timesmulti: Squares the input number
Technical Standards
Language: Python
SDK:
mcp[cli]Transport:
Streamable HTTPRecommended execution configuration:
stateless_http=True,json_response=True
Related MCP server: MCP FastAPI Tutorial Server
File Structure
.
├─ server.py
├─ pyproject.toml
├─ README.md
├─ CUSTOM_INSTRUCTIONS.md
└─ MCP_SERVER_REQUIREMENTS.mdRequirements
Python 3.10 or higher
Generative orchestrationmust be enabled to use MCP in Copilot Studio
Installation
Using uv
uv syncUsing pip
pip install "mcp[cli]>=1.9.0"Execution
python server.pyThe server runs using the MCP Streamable HTTP method.
The default path generally uses /mcp.
PowerShell Quick Start
You can run it with the script below in the project folder.
.\start_mcp_server.ps1Use the script below to stop it.
.\stop_mcp_server.ps1If .ps1 execution is blocked due to PowerShell execution policies, use the .cmd file below.
.\start_mcp_server.cmd
.\stop_mcp_server.cmdstart_mcp_server.cmd opens a new PowerShell window to run the server, so the MCP server remains active as long as that window is open.
Tool Descriptions
1. echo
Description: Returns the input sentence repeated exactly 3 times
Input:
{
"message": "안녕하세요"
}Output:
"안녕하세요 안녕하세요 안녕하세요"2. multi
Description: Returns the square of the input number
Input:
{
"number": 5
}Output:
25Copilot Studio Connection Overview
Open your agent in Copilot Studio.
Ensure
Generative orchestrationis enabled.Register the URL of this server in the MCP server addition screen.
After connecting, verify that the
echoandmultitools appear automatically.
Notes
Copilot Studio automatically reflects the tool names, descriptions, inputs, and outputs of the MCP server.
Copilot Studio supports
Streamable transport.SSE is not supported in Copilot Studio after August 2025.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA basic MCP server for deployment to Amazon Bedrock AgentCore Runtime, enabling tool integration via FastMCP with streamable HTTP transport.
- FlicenseNot gradedqualityCmaintenanceA basic MCP server demonstrating tool registration and SSE transport, enabling AI clients to call greeting, arithmetic, and time tools.
- FlicenseNot gradedqualityCmaintenanceA minimal MCP server offering a hello_world tool that returns a greeting and current UTC time via streamable HTTP.
- FlicenseNot gradedqualityCmaintenanceA model-agnostic MCP server exposing example tools (add1, multiply2, greet) for learning purposes, working with any LLM through stdio transport.
Related MCP Connectors
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sesme100/VSCode_Second_MCPFolder20260425'
If you have feedback or need assistance with the MCP directory API, please join our Discord server