Tools
Let AI applications perform actions through connected services.
MODEL CONTEXT PROTOCOL
MCP — Model Context Protocol
Connect AI to the tools and data it needs.
MCP is an open standard that lets AI applications connect to external tools, data sources, and services.
AI Apps
MCP
MCP Servers
What is MCP?
MCP (Model Context Protocol) is an open standard for connecting AI applications to external tools and data.
Instead of creating a separate integration for every AI application and service, MCP provides a common way for AI clients to discover and use capabilities exposed by MCP servers.
Resources
Give AI applications access to useful information and data.
Prompts
Provide reusable instructions and interaction patterns.
How MCP Works
AI Client
- Claude
- Cursor
- AI Agents
MCP Server
- Tools
- Resources
- Prompts
External Tools & Data
- GitHub · Notion · Slack
- Databases · Files · APIs
MCP for Claude
Claude can use MCP servers to connect to external tools, services, and data sources.
MCP Server
GitHub
Work with repositories, issues, and pull requests from Claude.
MCP Server
Notion
Connect Claude to pages and team knowledge bases.
MCP Server
Slack
Bring conversations and team messages into Claude workflows.
MCP Server
PostgreSQL
Query structured database data through an MCP server.
MCP Server
Google Drive
Give Claude access to connected files and documents.
MCP Server
Filesystem
Provide controlled access to local files for Claude.
Popular MCP Servers
Explore MCP servers that connect AI applications to useful tools and data.
GitHub
Work with repositories, issues, and code.
View MCP →Notion
Connect AI with pages and knowledge.
View MCP →Slack
Work with conversations and team messages.
View MCP →PostgreSQL
Connect AI applications to structured database data.
View MCP →Google Drive
Give AI access to connected files and documents.
View MCP →Filesystem
Provide controlled access to local files.
View MCP →MCP vs API
| API | MCP | |
|---|---|---|
| Main purpose | Application communication | AI-to-tools and data |
| Discovery | Usually application-specific | Standardized capability discovery |
| AI context | Not the main focus | Core concept |
| Integration | Custom integrations | Common protocol |
| Ecosystem | API-specific | MCP ecosystem |
MCP does not replace APIs. Instead, it provides a standardized way for AI applications to interact with tools and data.
Explore the MCP Ecosystem
Learn MCP
What is MCP?
Understand Model Context Protocol in 30 seconds.
Read →How does MCP work?
Learn about clients, servers, tools, and resources.
Read →How to use MCP with Claude?
Learn how Claude can connect to external tools.
Read →How to build an MCP server?
Understand the basics of building your own MCP integration.
Read →Frequently Asked Questions
What is MCP?
MCP stands for Model Context Protocol, an open standard for connecting AI applications with external tools and data.
What is Claude MCP?
Claude MCP refers to using Model Context Protocol to connect Claude with external tools, services, and data sources.
What is an MCP server?
An MCP server exposes tools, resources, or prompts that an MCP-compatible AI client can use.
Is MCP only for Claude?
No. MCP was introduced by Anthropic but has become an open ecosystem for connecting AI applications with tools and data.
What can MCP connect to?
MCP can connect AI applications to services such as GitHub, databases, files, communication tools, and other external systems.
Connect AI to More
Explore the tools, agents, and technologies shaping the next generation of AI.
Explore MEAGENT