mcp_server_integration
Scaffolds a custom MCP server with placeholder resources and tools, enabling developers to practice setting up MCP configuration, environment variables, and server implementation.
README
MCP Server Integration — Build Exercise
Scaffold for the CCA-F prep exercise from 2.4 MCP Server Integration.
Nothing here is solved — every task below has a TODO for you to fill in.
Task checklist
- [ ] 1. Project-level config — .mcp.json has a
githubserver entry (command/args). Swap it for whichever community server you want, if not GitHub. - [ ] 2. Env var expansion — the
githubentry references${GITHUB_TOKEN}instead of a hardcoded credential. Copy .env.example to.envand fill in a real token. - [ ] 3. User-level config — not created here on purpose, since
~/.claude.jsonlives outside the project and is personal to your machine. Template and steps: docs/user-level-config.md. - [ ] 4. Expose an MCP resource — src/server.ts has a
stub
catalogue://TODOresource. Replace it with a real content catalogue (e.g. a DB schema or docs hierarchy) with a proper URI, name, description, and mimeType. - [ ] 5. Enhance tool descriptions — same file,
example_toolhas a placeholder description. Write 3-5 sentences covering capability, output, use case, and how it compares to a built-in alternative.
Setup
npm install
npm run dev # starts the stdio server directly
npm run inspect # opens MCP Inspector against the server for manual testing
Layout
.mcp.json Task 1 & 2 — project-level server config
.env.example Task 2 — template for the secret .mcp.json expands
docs/user-level-config.md Task 3 — template + steps for ~/.claude.json
src/server.ts Task 4 & 5 — custom MCP server with resource/tool stubs
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.