component-workshop
Click on "Deploy 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., "@component-workshopwho owns component CM101A?"
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.
MCP Workshop
Build your first MCP server in 30 minutes.
What's inside
A tiny MCP server that serves synthetic embedded-flavored data — fake components (like CM101A) and fake NTC fault codes — plus a .vscode/mcp.json that hands it to GitHub Copilot Chat's Agent mode as a tool source. You'll add tools during the workshop and ask Copilot to use them.
Related MCP server: mcp-server
Quick start (in Codespaces)
Click Open in Codespaces above.
Wait ~90 seconds for the environment to build (
pip installruns automatically).Open the Chat panel on the right, set mode to Agent, click the tools icon — you should see two tools from
component-workshop.Ask Copilot:
who owns component CM101A?
Copilot picks
lookup_component, calls it, and answers.
That's the whole loop. The workshop tasks are edits to it — see HANDS_ON.md.
What's here
server.py— the MCP server, two working tools.vscode/mcp.json— registers the server with Copilot Chat's Agent modedata/— synthetic components and NTCsclient.py— optional stdio client, prints raw wire messages (no AI)HANDS_ON.md— the two workshop tasksCHEAT_SHEET.md— restarts, common errors, troubleshootingSOLUTION.md— peek only if Copilot stalls
The mental model
An MCP server is a toolbox with labeled drawers. Each tool is a drawer. The tool's description string is the label taped on it. The AI reads the labels to decide which drawer to open.
Your job as a tool author: write labels the AI can act on.
What you will build
See HANDS_ON.md.
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
An MCP server that provides Javelin Standalone Guardrails
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA simple demonstration MCP server that provides an echo tool and resource for learning how to build MCP servers. Serves as a starting point and template for creating custom MCP server implementations.1-
- AlicenseAqualityDmaintenanceA simple, extensible MCP server implementation for local use with tools like Copilot Chat, enabling context management and protocol-compliant communication.13MIT
- FlicenseNot gradedqualityDmaintenanceStarter scaffold for a workshop to build an MCP API testing server, intended to be extended through incremental steps.-
- AlicenseBqualityDmaintenanceA toy MCP server for exploring Model Context Protocol capabilities, including resources, tools, and prompts.1Apache 2.0