{"path":"/guide/getting-started/connect-agent/first-steps","content":{"title":"Check that your Everything connection works","summary":"Confirm your AI assistant actually read a public page, then try browsing and comparing related ideas.","breadcrumbs":"[All topics](/guide) / [About Everything](/topics/about-everything) / [Getting started](/guide/getting-started) / [Connect your agent](/guide/getting-started/connect-agent)","body":"Your AI assistant should be able to **read an actual Everything page** before you rely on its answers. A connection listed in settings is only the first step.\n\n## 1. Find Everything in your agent\n\nOpen your agent's list of MCP servers, tools or connectors. Look for **Everything**. Depending on the client, you may need to enable it for this conversation.\n\nTypical public tools are `get_page`, `list_pages`, `search_pages` and `get_related_pages`. Some clients also expose a `public_status` check.\n\n## 2. Ask for one specific article\n\nCopy this into your assistant:\n\n> Use the Everything MCP `get_page` tool to read `/topics/software-and-agents`. Give me the actual title and link to one collection mentioned on that page.\n\nThe answer should name **Software & Agents** and link to **Beyond the Application**. Inspect the tool call if your client shows it. A plausible answer with no tool call is not proof the connection is working.\n\n## 3. Follow the argument\n\nThen ask:\n\n> Read `/beyond-the-application`. What are its four main essays? Recommend a reading order, and link each title.\n\nCompare the response with the [collection page](/beyond-the-application).\n\n## 4. Explore on your own terms\n\nTry:\n\n> Search Everything for dynamically generated interfaces. Read the most relevant article, show the URL, and explain how it relates to the disaggregation of software.\n\nOr ask your agent to browse related pages, explain unfamiliar terminology, or contrast the text with other sources. You can ask it to distinguish the author's claims from the assistant's own interpretation.\n\n## What successful access means\n\nVisitors can read and search **published content**, but not edit or delete it. No Everything account is required. An agent might list tool names it cannot actually use; that does not change visitor permissions.\n\nSearch indexes may lag newly published pages. If you already know a URL, reading that page directly is the best check.\n\nFor errors, see [Troubleshooting](/guide/getting-started/connect-agent/troubleshooting). For how a public tool request is handled, see [Access and privacy](/guide/getting-started/connect-agent/access-and-privacy).\n\n[Choose your AI client](/guide/getting-started/connect-agent) · [Browse the wiki](/guide)","navigation":"[Connect your agent](/guide/getting-started/connect-agent) · [First tests](/guide/getting-started/connect-agent/first-steps)","related":[{"title":"Choose your AI client","url":"/guide/getting-started/connect-agent"},{"title":"Access and privacy","url":"/guide/getting-started/connect-agent/access-and-privacy"},{"title":"Troubleshooting","url":"/guide/getting-started/connect-agent/troubleshooting"}]}}