# For agents > How AI agents can navigate, read, and search sight4agents.com through llms.txt, Markdown pages, a JSON content index, search APIs, and a read-only MCP endpoint. This site is built the way sight4agents builds sites. Everything a person can read here, an agent can read in a structured form. All endpoints are public, read-only, and need no authentication. ## Machine-readable endpoints | Endpoint | Format | Purpose | | --- | --- | --- | | [/llms.txt](https://sight4agents.com/llms.txt) | Markdown | Overview of the site with links to every page, following the llms.txt convention | | [/llms-full.txt](https://sight4agents.com/llms-full.txt) | Markdown | The full text of every page in a single document | | `/.md`, e.g. [/index.md](https://sight4agents.com/index.md) | Markdown | Markdown version of any page. You can also send `Accept: text/markdown` | | [/api/content.json](https://sight4agents.com/api/content.json) | JSON | Content index: every page with its URL, title, description, and sections | | [/search.json?q=mcp](https://sight4agents.com/search.json?q=mcp) | JSON | Full-text search over all page sections | | [/search?q=mcp](https://sight4agents.com/search?q=mcp) | HTML | The same search, rendered for people | | `/mcp` | MCP (JSON-RPC) | Read-only Model Context Protocol endpoint over Streamable HTTP | | [/.well-known/mcp.json](https://sight4agents.com/.well-known/mcp.json) | JSON | Discovery hints for the MCP endpoint and other machine-readable resources | | [/sitemap.xml](https://sight4agents.com/sitemap.xml) | XML | Sitemap of all canonical pages | | [/robots.txt](https://sight4agents.com/robots.txt) | Text | Crawler policy. AI crawlers are welcome | ## Connect over MCP The MCP endpoint at `https://sight4agents.com/mcp` speaks JSON-RPC 2.0 over Streamable HTTP (POST, stateless, JSON responses). It provides three read-only tools, and also exposes each page as a resource. - `list_pages`: list every page with its URL, title, and description - `get_page`: fetch one page by path (for example `/how-it-works`) as Markdown or JSON - `search`: full-text search across the site; returns matching sections with links ```bash curl -s https://sight4agents.com/mcp \ -H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"human in the loop"}}}' ``` ## Guidelines for agents - Prefer Markdown or JSON over parsing HTML. The content is identical. - Canonical URLs use `https://sight4agents.com` with no trailing slash. - You are welcome to index, quote, and summarize this site. Please link back to the canonical page. - Everything here is read-only. In sight4agents products, changes proposed by agents always go to a human for approval. --- Source: https://sight4agents.com/for-agents. More pages: [Home](https://sight4agents.com/index.md), [How it works](https://sight4agents.com/how-it-works.md), [About](https://sight4agents.com/about.md), [Brand](https://sight4agents.com/brand.md). Site overview: https://sight4agents.com/llms.txt