Welcome to Dockito

Every doc gets a short link that always shows its latest version. Publish from wherever you work, and share it with your team or the world. Dockito never calls an AI itself: you bring your own.

Use the appDrop a Markdown or HTML file and get a link to share.→Connect your AILet Claude, ChatGPT or Cursor publish and read docs for you.→Use the terminalPublish files and whole folders with one command.→

Connect your AI

Pick your tool. It takes about a minute, and your AI can only do what you allow.

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.

CommandToken

1. Add Dockito:

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

   Copy

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.

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

2. Add Dockito with it:

   claude mcp add --transport http dockito https://dockito.ai/mcp \
     --header "Authorization: Bearer dkt_…"

   Copy

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

   Copy

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

   Copy

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.

One clickConfig fileToken

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.

1. Add Dockito to ~/.cursor/mcp.json:

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

   Copy

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.

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

2. Add Dockito to ~/.cursor/mcp.json with it:

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

   Copy

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.

One clickConfig file

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.

1. Add Dockito to .vscode/mcp.json in your project:

   {
     "servers": {
       "dockito": {
         "type": "http",
         "url": "https://dockito.ai/mcp"
       }
     }
   }

   Copy

2. Choose Start above the server, and allow it to sign in.

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_…"
         }
       }
     }
   }

   Copy

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"

   Copy

2. Sign in:

   codex mcp login dockito

   Copy

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"
       }
     }
   }

   Copy

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.

Sign inToken

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

   https://dockito.ai/mcp

   Copy

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.

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

2. Add the address, and send the token as a header:

   https://dockito.ai/mcp
   Authorization: Bearer dkt_…

   Copy

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

Server addresshttps://dockito.ai/mcpCopy

Learn the basics

Workspaces and rolesYour space, your team, and who can do what.Projects and foldersGroup docs, two folders deep.Markdown and HTMLWhat each kind of doc looks like, and its link.HistoryEvery change kept for a while; saved points kept for good.Sharing and accessWho can open what, and public links.Tokens and accessWhat your AI and the CLI may do, per workspace.

For AI agents

Every page here is also plain Markdown: add .md to its address, or use Copy page. The whole set is at /llms.txt and /llms-full.txt.