MCP stands for Model Context Protocol. It is an open standard that lets AI assistants like Claude, ChatGPT, and others connect to external tools and data sources. Without MCP, an AI assistant can only think and write. With MCP, it can actually do things — search the web, generate images, look up live data, and interact with other services.
MCP was created by Anthropic (the company behind Claude) and released as an open standard so that any AI assistant or tool provider can use it.
How does MCP work?
MCP works like a universal plug between your AI assistant and the tools it needs. Instead of each tool having its own setup process, MCP provides one standard way for tools to describe what they can do and for AI assistants to call them.
Here is what happens when you use an MCP tool:
- Your AI assistant connects to an MCP server (like ToolRouter).
- The server tells the assistant which tools are available and what each one does.
- When you ask the assistant to do something that needs a tool, it picks the right one and calls it.
- The tool runs and sends the result back to your conversation.
All of this happens inside your normal chat — you do not need to leave the conversation or open another app.
What is the difference between MCP and a regular API?
A regular API requires you to write code, manage authentication, and handle data formats yourself. MCP is designed for AI assistants, not developers. Your AI discovers available tools automatically, picks the right one for your request, and handles the technical details on its own.
With a service like ToolRouter, you connect once and get access to hundreds of tools without writing any code or managing any API keys.
What is an MCP server?
An MCP server is a service that provides tools to AI assistants through the MCP standard. When your AI connects to an MCP server, it receives a list of everything that server can do.
Some MCP servers offer a single tool. ToolRouter is a hosted MCP server that provides access to hundreds of tools through one connection — image generation, video creation, web search, competitor research, lead finding, SEO analysis, and more. Instead of connecting to dozens of separate MCP servers, you connect to ToolRouter once and everything is available.
What is a connector?
In Claude, MCP connections are called connectors. When you add ToolRouter as a connector in Claude, you are setting up an MCP connection. The word "connector" is just Claude's name for it — the technology underneath is MCP.
Adding a connector takes about 30 seconds: go to Settings, then Connectors, then Add custom connector, and enter the ToolRouter URL. Once added, every ToolRouter tool becomes available in your Claude conversations on web, desktop, and mobile.
See What is a Claude Connector? for a full guide, or jump straight to Connect to Claude for step-by-step setup.
What about Claude Code and the terminal?
In Claude Code (the terminal version of Claude), MCP servers are added with a command instead of a settings menu. You run one command and ToolRouter becomes available to Claude Code automatically:
claude mcp add toolrouter -- npx -y toolrouter-mcpThe result is the same — Claude Code can discover and call any tool in the catalog. The only difference is how you set it up: a settings menu in Claude, a terminal command in Claude Code.
See Connect to Claude Code for the full guide.
Is MCP safe?
MCP servers can only do what you allow them to do. When your AI assistant wants to call a tool, it asks for your permission first — you see exactly what it wants to do before anything happens.
With ToolRouter specifically, your data is not stored or logged. API keys you provide are used once for the tool call and then discarded. See our security policy for full details.
Which AI assistants support MCP?
MCP is supported by a growing number of AI assistants and development tools:
- Claude — via connectors (web, desktop, and mobile). Set up ToolRouter →
- Claude Code — via CLI command. Set up ToolRouter →
- ChatGPT — via custom MCP apps (requires Developer mode). Set up ToolRouter →
- Codex CLI — via MCP config. Set up ToolRouter →
- Microsoft Copilot — via Copilot Studio. Set up ToolRouter →
- Cursor — via MCP settings. Set up ToolRouter →
- Windsurf — via MCP settings. Set up ToolRouter →
- VS Code — via MCP settings. Set up ToolRouter →
- Cline — via MCP settings. Set up ToolRouter →
- Gemini CLI — via MCP config. Set up ToolRouter →
- OpenClaw — via MCP config. Set up ToolRouter →
What tools can I use through MCP?
With ToolRouter's MCP server, your AI assistant gets access to hundreds of tools across categories like:
- Image generation — create product photos, marketing visuals, and art using 50+ AI models
- Video generation — produce UGC-style videos, product demos, and social content
- Web search — find current information from across the internet
- Competitor research — analyse competitors, their ads, their traffic, and their strategy
- Lead finding — find contact details, company data, and enrichment for sales
- SEO analysis — audit websites, check rankings, research keywords
- Data and charts — generate charts, look up stock prices, currency rates, and weather
- Music and audio — generate music tracks, sound effects, and voice audio
New tools are added every week. See the full tool catalog to browse everything available.
How do I get started?
The fastest way to start using MCP tools is to add ToolRouter to whichever AI assistant you already use. No account needed — ToolRouter auto-provisions on first use.
- Using Claude? Add ToolRouter as a connector →
- Using ChatGPT? Add ToolRouter as an MCP app →
- Using Claude Code? Run one command →
- Using something else? See all setup guides →