The Model Context Protocol (MCP) is an open standard, released by Anthropic in November 2024, for connecting AI models to tools and data sources. For public websites, it means you can expose your site's functionality as typed, discoverable tools that AI agents can invoke — not just read.

What MCP adds beyond crawling

When an AI agent crawls your site, it reads HTML and infers what your product does. When it connects to an MCP server, it gets a machine-readable description of what your product can do: typed function signatures, parameter schemas, return type hints, and error contracts. The agent doesn't need to read your docs to understand how to call your API — the MCP manifest tells it directly.

The protocol uses a client-server model. The AI assistant (Claude, Cursor, GitHub Copilot, and others) is the client. Your MCP server exposes tools and resources. A tool is a callable function (search_docs(query: string)); a resource is a read-only context endpoint that returns structured content rather than raw HTML. Both are registered in the same manifest.

Tools vs. resources

The distinction matters for how you decide what to expose:

  • Tools suit interactive, stateful operations — search, form submission, transaction initiation, any action with side effects. They have typed inputs and outputs.

  • Resources suit read-only content access — pulling a product page, fetching API reference content, retrieving a changelog entry. They let agents get structured page content without rendering HTML.

For developer tool and API product sites, a search_docs tool is usually the highest-value starting point. For content-heavy sites, a resource endpoint for each major content section often provides more value than a tool.

Discovery: how agents find your MCP server

MCP servers can be discovered through several mechanisms. The emerging convention is a .well-known/mcp.json file at your canonical origin describing the server endpoint and available capabilities. Early MCP registries are also indexing public servers by domain, similar to how npm or PyPI index packages.

The most portable approach today is to document the MCP server endpoint in your /llms.txt file under a dedicated ## MCP section:

# example.com

> Example: the tool that does X.

## Tools
- [API Reference](https://example.com/docs/api)

## MCP
- [MCP Server](https://mcp.example.com) — typed tool access for AI agents

This works immediately with any agent that reads llms.txt before acting, without waiting for a registry to index your domain.

Practical steps for a public site

Getting an MCP server live is a four-step process. None of the steps require changes to your existing site architecture.

  1. Identify which of your site's tools or data an agent would want programmatic access to — search, content retrieval, and account-level read operations are the common starting points.

  2. Build an MCP server that exposes those surfaces as typed tools and resources. The MCP SDK (available for TypeScript and Python) handles the protocol wire format; you implement the handler functions.

  3. Document the MCP endpoint URL in your /llms.txt under ## MCP so agents that read the file can discover it without registry lookup.

  4. Register the server with an MCP registry if one covers your domain — this broadens discoverability to agents that use registry lookup rather than direct .well-known or llms.txt scanning.

Current adoption

As of 2025, MCP support is available in Claude, Cursor, GitHub Copilot, and a growing set of other agents. Public MCP server indexing is early but moving fast — the same inflection that happened with RSS readers in 2003 and REST APIs in 2010 is happening now for agent-accessible tool interfaces. Sites that expose a well-formed MCP server now have a head start on discoverability before registries become the default discovery layer.

Verify before shipping

isitready.dev checks for MCP discoverability signals including llms.txt tool references and .well-known MCP endpoint presence. Run the scan on your canonical origin to see where your site stands and what agents can discover today.