Your AI tools, the same knowledge your people trust.

Whether it is a support bot, Claude, ChatGPT, Cursor or Copilot, your AI tools answer from the same approved, current knowledge your help center publishes, on your own AI plan. Where you allow it, they can propose edits that go through the same review as everyone else's.

Quick start

There is nothing to install or run. Your workspace gives you a ready-to-use connection URL and setup snippets for each AI tool. Developers can still copy the technical configuration below when they need it.

Cursor

Add to ~/.cursor/mcp.json
{
  "mcpServers": {
    "interactivedox-docs": {
      "url": "https://agent-id.interactivedox.com/mcp/portal"
    }
  }
}

Claude Code

One command in your terminal
claude mcp add --transport http interactivedox-docs \
  https://agent-id.interactivedox.com/mcp/portal

Claude Desktop

Add to claude_desktop_config.json
{
  "mcpServers": {
    "interactivedox-docs": {
      "url": "https://agent-id.interactivedox.com/mcp/portal"
    }
  }
}

ChatGPT

Settings, then Connectors, then Add MCP server
Name:  interactivedox-docs
URL:   https://agent-id.interactivedox.com/mcp/portal
connect a portal

From a portal to an answered question.

Step by step: share the portal with your AI tool, paste the connection details it gives you, and ask a question. The answer comes from your published documentation, with a link to every page it used.

The portal overview for “mcp-connector” in InteractiveDox: Draft and Setup Complete, three pages, one version, no readers, the all-versions table showing v1.0.0 as the default draft, and the inherited default approval workflow.

Start from a portal you already have: its pages, its versions, and the approval workflow it inherits.

Read and search, no key required

Anything a visitor to your published portal can read, an agent can read too.

  • portal_list_pagesPublic

    List a portal's navigation: every page, group and tab with slug, title, type and parent. The starting point for understanding a portal's structure.

  • portal_read_pagePublic

    Read one page's content and details.

  • portal_searchPublic

    Search across one portal so an AI tool can find the right answer.

Edits follow the same review rules

Editing tools require a workspace API key, passed as Authorization: Bearer ata_…. Every edit is tracked in the portal's history, so AI changes can be reviewed and traced like team changes.

  • portal_create_pageAPI key

    Create a page, group, or tab in the portal.

  • portal_save_pageAPI key

    Update one page's content and keep search current.

  • portal_update_nodeAPI key

    Update page settings like title, icon, visibility, and description.

  • portal_move_nodeAPI key

    Move, rename, or reorder a page in the portal.

  • portal_delete_pageAPI key

    Delete a page while keeping the surrounding page tree organized.

AI tools reading your guidance get the same current answers as your customers. That is the point: one approved place for both people and machines to learn from.

AI access questions, answered.

What is the InteractiveDox MCP server?

It is how the AI tools you already use get the same approved, current answers your people get, instead of guessing from old or scattered sources. MCP is the industry standard behind the connection; your engineers will recognise it.

Do read tools require an API key?

Reading what your published portal shows needs no key. Making changes does, and every change is tracked and reviewed like a person's.

Why does MCP matter for documentation?

Because an AI tool is only as good as what it reads. Pointed at your published knowledge, it gives the answer you approved, with the page it came from.

Can agents update documentation through MCP?

Only if you allow it. Their proposed changes go through the same review as anyone else's before they become current.

Which clients can connect?

Cursor, Claude, ChatGPT, Copilot, your own agents and internal support bots.