Skip to content
Docs

Connect your AI

View as MarkdownOpen in ClaudeOpen in ChatGPT

Connect once and your AI can publish docs, read them and keep their History, through the Dockito MCP server. It can never do more than you can, and only what you allow when you connect it.

Pick your tool:

Claude CodeTerminalPublish what Claude writes in your repo, and read your team's docs while it works.ClaudeAppTurn a chat into a doc with a link, or bring any doc into the conversation.ChatGPTAppPublish answers and plans as docs, and ask about any doc you can open.CursorOne clickPublish specs and notes from the agent, and pull docs in as context.VS CodeOne clickUse Dockito from Copilot's agent mode: publish, read and keep History.AntigravityEditorLet Antigravity's agents publish their plans and reports as docs.CodexTerminalPublish from Codex sessions, and read docs before it starts coding.Gemini CLITerminalPublish and read docs from Gemini CLI.Any MCP clientAnyAnything that speaks MCP over HTTP: sign in with OAuth or a token.

Connect Claude Code

Publish what Claude writes in your repo, and read your team's docs while it works.

  1. Add Dockito:

    claude mcp add --transport http dockito https://dockito.ai/mcp

  2. In Claude Code, run /mcp, choose dockito, then Authenticate.

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Add --scope user to have Dockito in every project.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Claude

Turn a chat into a doc with a link, or bring any doc into the conversation.

  1. Open Settings → Connectors and choose Add custom connector.

  2. Name it Dockito, paste the address and choose Connect:

    https://dockito.ai/mcp

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

  4. In a chat, turn Dockito on from the tools menu.

Custom connectors need a paid Claude plan. On Team and Enterprise, an owner may need to add it.

Then ask it: “Publish this to Dockito and give me the link.”

Connect ChatGPT

Publish answers and plans as docs, and ask about any doc you can open.

  1. Open Settings → Apps & Connectors → Advanced settings and turn on Developer mode.

  2. Back in Apps & Connectors, choose Create. Name it Dockito, paste the address and pick OAuth:

    https://dockito.ai/mcp

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

  4. In a chat, add Dockito from the + menu under Developer mode.

Developer mode is on paid ChatGPT plans. On Business and Enterprise, an admin may need to allow it.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Cursor

Publish specs and notes from the agent, and pull docs in as context.

Add to Cursor

  1. Choose Add to Cursor and confirm in Cursor.

  2. In Cursor Settings → MCP, choose Needs login next to dockito.

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Then ask it: “Publish this to Dockito and give me the link.”

Connect VS Code

Use Dockito from Copilot's agent mode: publish, read and keep History.

Add to VS Code

  1. Choose Add to VS Code and confirm Install in VS Code.

  2. Allow it to sign in to Dockito when it asks.

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Use Dockito from Copilot Chat in Agent mode.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Antigravity

Let Antigravity's agents publish their plans and reports as docs.

  1. In Dockito, open Account → Tokens and make a token, with Publish where it should write.

  2. In the agent panel, open the ⋯ menu → MCP Servers → Manage MCP Servers → View raw config.

  3. Add Dockito:

    {
  "mcpServers": {
    "dockito": {
      "serverUrl": "https://dockito.ai/mcp",
      "headers": {
        "Authorization": "Bearer dkt_…"
      }
    }
  }
}

  4. Save, then choose Refresh.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Codex

Publish from Codex sessions, and read docs before it starts coding.

  1. Add Dockito to ~/.codex/config.toml:

    [mcp_servers.dockito]
url = "https://dockito.ai/mcp"

  2. Sign in:

    codex mcp login dockito

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Gemini CLI

Publish and read docs from Gemini CLI.

  1. Add Dockito to ~/.gemini/settings.json:

    {
  "mcpServers": {
    "dockito": {
      "httpUrl": "https://dockito.ai/mcp"
    }
  }
}

  2. In Gemini CLI, run /mcp auth dockito.

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Then ask it: “Publish this to Dockito and give me the link.”

Connect Any MCP client

Anything that speaks MCP over HTTP: sign in with OAuth or a token.

  1. Add a remote (HTTP) MCP server with this address:

    https://dockito.ai/mcp

  2. If your client signs in with OAuth, it opens Dockito for you.

  3. Your browser opens Dockito. Choose what it may do in each workspace (View, Publish or Everything) and Approve.

Then ask it: “Publish this to Dockito and give me the link.”
Server addresshttps://dockito.ai/mcp

What to ask

Section titled “What to ask”

Your AI reads Dockito’s instructions when it connects, so plain words work:

  • “Publish this spec to Dockito and give me the link.”
  • “Put these notes in the Harbor project, in Meetings.”
  • “What changed in the Cedarline brief since Friday? Restore the version from before.”
  • “Save the current version of the proposal as Sent to the client.”

It’s told to ask where a doc goes rather than guess, and to keep docs private unless you ask for a public link. Deleting docs and sharing with people happen in the Dockito app, never through an AI.

More

Section titled “More”