TL;DR - What is MCP?
MCP (Model Context Protocol) is an open JSON-RPC 2.0 protocol (modelcontextprotocol.io) that lets frontier AI models—including Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro (compare tool-calling latencies on our LLM Benchmarks hub)—connect to external tools, databases, and enterprise systems. Think of it as “USB-C for AI”: a universal standard governed by the Linux Foundation Agentic AI Foundation (AAIF).
Key Takeaways
- Sub-10ms Local Execution & Streamable HTTP: Local
stdioMCP servers execute tool calls with 2ms to 8ms IPC overhead and 50MB to 65MB RAM per process, while remote enterprise deployments use the2025-11-25Streamable HTTP transport with OAuth 2.1 + PKCE (S256) and RFC 9728 Protected Resource Metadata (/.well-known/oauth-protected-resource). - Context Window Economics: Registering a standard 10-to-15-tool MCP server consumes 1,200 to 2,500 tokens of JSON Schema definitions; uncurated 5+ server setups can burn 15,000 to 30,000 tokens (
12% to 25%of a128Kcontext window) before the first user prompt unless mitigated with dynamic tool discovery. - Massive Open Ecosystem: Supported natively across Claude Desktop, Claude Code, ChatGPT, GitHub Copilot, Gemini, Cursor, and Windsurf, backed by 10,000+ community and official servers and 97 million+ monthly SDK downloads across
@modelcontextprotocol/sdkand PythonFastMCP. - Cross-Pillar Developer Workflow: Validate your
claude_desktop_config.jsonpayloads with our JSON Formatter & Validator and craft deterministic tool-calling system instructions using our AI Prompt Generator.
Quick Architecture Check: Do You Need Local stdio or Remote Streamable HTTP? (Click to Expand)
- Choose Local
stdio(npx/uvx/ Docker) when connecting desktop IDEs (Claude Desktop, Cursor, VS Code) to local source code, local SQLite/PostgreSQL instances, or personal API tokens with 0ms network hop latency. - Choose Remote Streamable HTTP when deploying shared organizational tools behind an enterprise API gateway with centralized OAuth 2.1 token validation, RBAC audit logging, and horizontal auto-scaling.
Example: With GitHub MCP, you can say “Create a pull request with all the changes we discussed” and Claude will actually do it - not just explain how.
The Problem: AI Assistants Are Isolated
You’ve probably experienced this frustration:
Without MCP:
You: "Can you review the code in my project?"
AI: "I'd love to! Please paste the code you'd like me to review."
You: *copies 500 lines from file 1*
You: *copies 300 lines from file 2*
You: *copies the package.json*
You: "Here's the code..."
AI: "Thanks! Now can you share the test files too?"
You: 😫AI assistants are incredibly powerful, but they’re isolated bubbles. They can’t see your files, access your databases, or interact with your tools. Every conversation starts from scratch. For more on AI capabilities, see the AI Agents guide.
This limitation forces you to:
- Copy-paste massive amounts of context
- Describe systems instead of showing them
- Manually execute every suggestion the AI makes
- Re-explain your project in every new conversation
MCP solves this problem.
Enter MCP: The Universal Connector
Model Context Protocol (MCP) is an open protocol introduced by Anthropic in November 2024 and now maintained by the Linux Foundation’s Agentic AI Foundation (as of December 2025). It has become the industry standard for AI tool integration, adopted by all major AI providers including OpenAI, Microsoft, and Google. For a complete timeline of how MCP and other AI technologies evolved throughout 2025, see our AI in 2025: Year in Review.
The “USB for AI” Analogy
Before USB, every device had its own proprietary connector:
- Printers needed printer cables
- Cameras needed camera cables
- Phones needed phone cables
USB created a universal standard. Now everything just works.
MCP does the same for AI:
- Before MCP: Every AI tool had its own integration system (ChatGPT plugins, Claude tools, etc.)
- After MCP: Any AI tool can use any MCP server
| Architecture Layer | Role in the Protocol Stack | Connected Examples & Transports |
|---|---|---|
| 1. MCP Hosts (AI Applications) | User-facing AI chat apps, IDEs, and autonomous agent harnesses | Claude Desktop, Cursor, VS Code + Copilot/Continue, Windsurf, ChatGPT |
| 2. MCP Protocol Transport | Bidirectional JSON-RPC 2.0 message bus handling tools/list, tools/call, and resources/read | Local stdio pipes (2ms–8ms latency) or Remote Streamable HTTP (POST/GET with SSE) |
| 3. MCP Servers (Capability Providers) | Isolated processes or microservices exposing domain-specific tools, resources, and prompts | GitHub Server, PostgreSQL Server, Filesystem Server, Notion Server, Slack Server |
How It Works
MCP has three main components:
| Component | What It Is | Examples |
|---|---|---|
| MCP Hosts | AI applications that use MCP | Claude Desktop, Cursor, Windsurf |
| MCP Clients | Protocol handlers inside hosts | Built into the apps above |
| MCP Servers | Programs that expose capabilities | GitHub, Postgres, Filesystem servers |
When you configure an MCP server:
- Your AI tool (host) starts the MCP server
- The server tells the AI what tools are available
- The AI can now use those tools during conversations
The MCP Ecosystem
The MCP ecosystem has exploded since its launch, reaching 10,000+ active servers by December 2025. Here’s what’s available:
Official Reference Servers (by Agentic AI Foundation)
These are maintained by the Linux Foundation’s Agentic AI Foundation:
| Server | What It Does | Status |
|---|---|---|
| Filesystem | Read/write local files | Core |
| Git | Repository operations | Core |
| PostgreSQL | Database queries | Core |
| SQLite | Local database access | Core |
| Fetch | Web content retrieval | Core |
| Memory | Knowledge graph storage | Core |
| Puppeteer | Browser automation | Core |
| Time | Timezone conversions | Core |
Official Integrations (by Companies)
Major companies have built official MCP servers:
| Company | Server | What It Does |
|---|---|---|
| Microsoft | GitHub MCP | Manage repos, issues, PRs |
| Playwright | Playwright MCP | Browser automation |
| Atlassian | Atlassian MCP | Jira + Confluence |
| AWS | AWS MCP | Cloud services |
| Cloudflare | Cloudflare MCP | Workers, KV, R2 |
| Sentry | Sentry MCP | Error monitoring |
| MongoDB | MongoDB MCP | Document database |
| Notion | Notion MCP | Workspace management |
| Slack | Slack MCP | Team messaging |
Community Servers
The community has built 9,000+ additional servers for:
- Google Drive, Dropbox, OneDrive
- Airtable, Linear, Trello
- Discord, Telegram, WhatsApp
- Docker, Kubernetes
- Stripe, Shopify
- SAP, Oracle, Salesforce
- Custom enterprise integrations
- And thousands more…
MCP Clients (AI Tools That Support MCP)
| Tool | Type | MCP Support | Added |
|---|---|---|---|
| Claude Desktop | Chat App | ✓ Native | Nov 2024 |
| ChatGPT | Chat App | ✓ Native | Early 2025 |
| Microsoft Copilot | Chat/IDE | ✓ Native | Early 2025 |
| Gemini | Chat App | ✓ Native | Dec 2025 |
| Cursor | AI IDE | ✓ Native | Nov 2024 |
| Windsurf | AI IDE | ✓ Native | 2024 |
| VS Code + Continue | IDE Extension | ✓ Via extension | 2024 |
| Cline | VS Code Extension | ✓ Native | 2024 |
| Zed | Editor | ✓ Native | 2024 |
Real-World Use Cases
Let’s look at practical examples of what you can do with MCP:
Developer Workflow
MCP shines in development environments. For more on AI-powered coding, see the AI-Powered IDEs Comparison guide.
Without MCP:
You: "Review my authentication code"
AI: "Please paste the code..."
*You spend 5 minutes copying files*With MCP (Filesystem + Git + GitHub):
You: "Review the authentication code in src/auth/,
check git history for recent changes,
and create an issue for any security concerns"
AI: *reads files from src/auth/*
*checks git log for recent commits*
*analyzes code*
*creates GitHub issue #47: "Potential session fixation vulnerability"*
"I reviewed the authentication module. Found 2 issues:
1. Created GitHub Issue #47 for a session fixation risk
2. The password hashing uses an outdated algorithm
Here are my recommended fixes..."Data Analysis
With MCP (PostgreSQL + Filesystem):
You: "What were our top 10 products last month?
Export to a CSV on my desktop."
AI: *queries database*
*writes file to ~/Desktop/top_products.csv*
"Done! I found the top 10 products by revenue:
1. Widget Pro - $45,230
2. Gadget Plus - $38,100
...
Exported to your Desktop as 'top_products.csv'"Productivity
With MCP (Notion + Slack):
You: "Summarize what happened in #engineering today
and add action items to my Notion task database"
AI: *reads Slack channel*
*creates Notion tasks*
"Here's today's summary from #engineering:
- Deployed v2.3.1 to production
- Discussed new auth system
I added 3 action items to your Notion:
✅ Review PR #892
✅ Schedule security audit
✅ Update documentation"Research
With MCP (Fetch + Memory):
You: "Research the latest trends in AI agents.
Remember what you find for future reference."
AI: *fetches articles from web*
*stores in knowledge graph*
"I researched AI agent trends and saved key findings:
- Multi-agent systems are trending
- Tool use is the fastest growing capability
- MCP adoption is accelerating
I've stored this in memory. Ask me about AI agents
anytime and I'll remember this context."For more on research techniques with AI, see the RAG, Embeddings & Vector Databases guide.
Getting Started with MCP
Ready to try MCP? Here’s a quick start:
Step 1: Choose Your MCP Client
Pick an AI tool that supports MCP:
| If You Want… | Use This |
|---|---|
| General chat + tools | Claude Desktop |
| AI-powered coding | Cursor or Windsurf |
| VS Code integration | Continue or Cline extension |
Step 2: Configure Your First MCP Server
Here’s how to add the Filesystem MCP server to Claude Desktop:
1. Find your config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
2. Add this configuration:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/yourname/projects"
]
}
}
}3. Restart Claude Desktop
4. Test it:
You: "What files are in my projects folder?"
Claude: "I can see the following files and folders..."Step 3: Add More Servers
Once you’re comfortable, add more servers:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"]
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
}
},
"postgres": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb"]
}
}
}Next Article: How to Install and Configure MCP Servers - Complete setup guide for Claude, Cursor, VS Code, and more.
Security Best Practices
MCP is designed with security in mind, but you should still follow best practices:
✓ Do’s
| Practice | Why |
|---|---|
| Grant minimal access | Only allow directories/resources you need |
| Use read-only when possible | Filesystem MCP supports read-only Docker bind mounts |
| Review server permissions | Understand what each server can do |
| Keep servers updated | Run npx to always get latest versions |
| Use official servers first | They’re audited and maintained |
✗ Don’ts
| Practice | Risk |
|---|---|
| Don’t grant home directory | Exposes all your files |
| Don’t share config files | May contain API keys |
| Don’t use unverified servers | Could be malicious |
| Don’t ignore permission prompts | Servers ask for reason |
For more on responsible AI usage, see the Understanding AI Safety, Ethics, and Limitations guide.
How MCP Security Works
| Security Boundary | Permitted Operations | Blocked by Default |
|---|---|---|
| Host Process (Claude Desktop / Cursor) | Spawns local MCP server process and mediates user human-in-the-loop tool approval prompts | Unapproved destructive tool execution without user consent |
| Sandboxed MCP Server Process | Accesses only explicitly passed CLI directories (e.g., /Users/me/projects canonicalized via fs.realpathSync) or scoped env API tokens | Arbitrary parent directory traversal (../), symlink escapes (patched in CVE-2025-53109), and unmounted system files |
| Host OS & External Network | Outbound HTTPS calls only from servers explicitly designed for API/web access (e.g., GitHub, Fetch) | Unauthorized access to ~/.ssh, system keychain, or unconfigured local databases |
Key security features:
- Local execution: Servers run on your machine, not in the cloud
- Sandboxed access: Only resources you explicitly allow
- No network by default: Most servers don’t make external calls
- Transparent operation: You can inspect server source code
MCP vs. Other Approaches
How does MCP compare to other AI integration approaches?
| Feature | MCP | Legacy Plugins | Custom APIs |
|---|---|---|---|
| Universal | ✓ All major AI tools | ✗ Platform-specific | ✗ Build each |
| Local execution | ✓ Your machine | ✗ Cloud-only | Depends |
| Open source | ✓ Linux Foundation | ✗ Proprietary | Depends |
| Privacy | ✓ Data stays local | ✗ Sent to cloud | Depends |
| Customizable | ✓ Build your own | ✗ Limited | ✓ Full control |
| Ecosystem | ✓ 10,000+ servers | Deprecated | N/A |
| Industry adoption | ✓ OpenAI/MS/Google | Legacy | N/A |
Bottom line: MCP has become the industry standard, supported by all major AI providers. It gives you the flexibility of custom APIs with the ease of configuration, while keeping your data secure.
Recent Major Updates (2025)
MCP has evolved significantly since launch:
December 2025: Linux Foundation Donation
- Agentic AI Foundation formed under Linux Foundation
- Founding supporters: OpenAI, Microsoft, Google, AWS, Anthropic, Block, Cloudflare
- Open governance: Ensures MCP remains neutral and community-driven
- Mission: Prevent fragmentation, accelerate innovation in agentic AI
November 2025: Major Protocol Update
- Task-based workflows: Track long-running operations
- Streamlined OAuth: URL-based client registration
- Asynchronous operations: Better handling of slow tools
- 🆔 Server identity: Improved security and authentication
- Official extensions: Standardized extension mechanism
New Features in Claude
- 75+ MCP connectors in Claude’s directory
- Tool Search: Find tools across many connected servers
- Programmatic Tool Calling: Optimized for large-scale deployments
What’s Coming
- Managed remote MCP servers (Google Cloud already offers this)
- Visual configuration tools
- Mobile app support
- Enterprise SSO and audit logging
Next Steps
Ready to dive deeper? Here’s your learning path:
Beginner Path
- ✓ You are here: Introduction to MCP
- → Next: Install & Configure MCP Servers
- → Then: Filesystem MCP Guide
- → Then: GitHub MCP Guide
Developer Path
- ✓ You are here: Introduction to MCP
- → Next: Build Your First MCP Server
- → Then: PostgreSQL MCP Guide
- → Then: Best MCP Combinations
Power User Path
- ✓ You are here: Introduction to MCP
- → Next: GitHub MCP Guide
- → Then: Notion MCP Guide
- → Then: Memory MCP Guide
Quick Reference
Essential Commands
# Run any MCP server with npx (no install needed)
npx -y @modelcontextprotocol/server-filesystem /path/to/allow
# Test MCP servers with Inspector
npx @modelcontextprotocol/inspector
# Check Node.js version (v18+ required)
node --versionConfig File Locations
| Platform | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%/Claude/claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Popular MCP Servers
| Server | Package | Use Case |
|---|---|---|
| Filesystem | @modelcontextprotocol/server-filesystem | Read/write files |
| GitHub | @modelcontextprotocol/server-github | Manage repos, issues, PRs |
| PostgreSQL | @modelcontextprotocol/server-postgres | Query databases |
| Playwright | @playwright/mcp | Browser automation |
| Memory | @modelcontextprotocol/server-memory | Persistent knowledge |
Resources
Summary
MCP (Model Context Protocol) has become the industry standard for AI integrations:
- ✓ Universal standard adopted by OpenAI, Microsoft, Google, and Anthropic
- ✓ 10,000+ servers for every use case imaginable
- ✓ Linux Foundation governance ensures openness and neutrality
- ✓ Secure by design with local execution
- ✓ Easy to use with simple JSON configuration
- ✓ Free and open source forever
The days of copy-pasting context into AI chats are coming to an end. With MCP, your AI assistant becomes a true partner that can access your tools, data, and workflows directly.
Next: Learn how to Install and Configure MCP Servers →
Have questions about MCP? Found an issue with this guide? Contact us or join the MCP community on Discord.
With the core architecture of MCP explained in this foundational MCP tutorial, you are ready to install your first server and build multi-tool agent workflows.