In a nutshell
MCP stands for โModel Context Protocolโ โ a protocol for providing additional context and capabilities to AI models.
How it works
flowchart LR
subgraph Host["๐ค AI Host (VS Code / Copilot CLI, etc.)"]
APP[Copilot]
CL1[MCP Client]
CL2[MCP Client]
CL3[MCP Client]
CL4[MCP Client]
CL5[MCP Client]
end
subgraph MCP["๐ MCP Layer (1 Client โ 1 Server)"]
SLs[Work IQ MCP Server]
JRs[GitHub MCP Server]
FSs[Playwright MCP Server]
PWs[Context7 MCP Server]
APIs[Salesforce MCP Server]
end
subgraph Tools["๐ ๏ธ External Tools"]
SL[Work IQ]
JR[GitHub]
FS[Playwright]
PW[Context7]
API[Salesforce]
end
APP --- CL1
APP --- CL2
APP --- CL3
APP --- CL4
APP --- CL5
CL1 <-->|stdio| SLs
CL2 <-->|HTTP| JRs
CL3 <-->|stdio| FSs
CL4 <-->|stdio| PWs
CL5 <-->|stdio| APIs
SLs <-->|API| SL
JRs <-->|API| JR
FSs <-->|API| FS
PWs <-->|API| PW
APIs <-->|API| API
classDef host fill:#0a0e27,stroke:#00f0ff,color:#00f0ff,stroke-width:2px
classDef proto fill:#1a0a2e,stroke:#ffb000,color:#ffb000,stroke-width:2px
classDef tool fill:#0a1a14,stroke:#9bbc0f,color:#9bbc0f,stroke-width:2px
class APP,CL1,CL2,CL3,CL4,CL5 host
class SLs,JRs,FSs,PWs,APIs proto
class SL,JR,FS,PW,API tool
The AI Host (VS Code, Copilot CLI, etc.) contains multiple MCP Clients internally, each maintaining a 1 Client โ 1 Server one-to-one connection. A Client/Server pair is added for each external tool you want to use. Because the protocol is fixed, adding a new Server is all it takes for every editor and agent to gain new capabilities.
Why does it matter?
Three values MCP brings:
- ๐งฉ Extensibility: Make Copilot a single entry point for operating any external tool.
- Read and write requirements (Jira)
- Create designs (Figma)
- Generate and print 3D designs (Blender + 3D printer)
- Check and edit email and calendar (Work IQ)
- Connect to internal databases for analysis
- ๐ Workflow integration: No more custom glue code between individual tools โ Copilot acts as a hub spanning multiple systems.
- ๐ Broad ecosystem support: MCP is an open protocol that is rapidly becoming the de facto standard. AI assistants, development tools like Visual Studio, and many other applications already support MCP โ build once, connect anywhere. Perfectly suited for coding integrations.
Where does it run?
There are two ways to run an MCP server.
- With the stdio method, VS Code launches the MCP server as a child process on your local machine.
- With the HTTP method (SSE / streamable-http), the MCP server runs in the cloud or on a remote server, and VS Code simply connects as a client.
Choose based on your use case and security requirements.
npm execConfiguration in VS Code
When installing an MCP server from the Marketplace in VS Code, you can choose between two scopes:
Installโ Added to your personal settings file (User Settings)Install Workspaceโ Added to the repository settings file (.vscode/mcp.json)
.vscode/mcp.json
โธ Shared with repo
Included in Git, so the whole team shares the same MCP setup. When a member clones the repo, VS Code asks "Would you like to enable it?".
User Settings
โธ Your machine only
For personal use or when you want the same setup across all projects. Not included in Git.
- ๐ Mac๏ผ
~/.config/Code/User/settings.json - ๐ช Windows๏ผ
%APPDATA%\Code\User\settings.json
Getting started with Copilot CLI
# Add an MCP server
copilot mcp add <server-name>
# List existing servers
copilot mcp list
The GitHub official MCP server is connected out of the box. AI can operate Issues, PRs, Actions, and Code search just like running gh commands.
modelcontextprotocol/registry hosts many official and community-built servers (filesystem / postgres / slack / puppeteer / playwright / Figmaโฆ).