Publish HTML from Claude Code, Cursor and Codex

01

What your assistant can do

• —Publish the HTML, Markdown, YAML or JSON your assistant just wrote, and get a link you can send to anyone.
• —Re-publish the same artifact and it becomes a new version behind the same link, with the old ones still readable.
• —Read the comments people pinned on the rendered page, and the JSON state they changed by using it.
• —Group work into projects, lay it out on a canvas, and record the decisions made about it.

02

Install it in your tool

Each config below is complete except for the token. Create an account and the connect wizard hands you the same block with a live token already in it — or paste a token from Dashboard → API access over havetml_your_token_here.

Name: HaveTML
Remote MCP server URL: https://havetml.com/api/mcp
OAuth Client ID: (leave blank)
OAuth Client Secret: (leave blank)

claude mcp add --transport http havetml https://havetml.com/api/mcp \
  --header "Authorization: Bearer havetml_your_token_here"

# ~/.codex/config.toml
[mcp_servers.havetml]
url = "https://havetml.com/api/mcp"
bearer_token_env_var = "HAVETML_TOKEN"

# then, in your shell profile:
export HAVETML_TOKEN="havetml_your_token_here"

{
  "mcpServers": {
    "havetml": {
      "url": "https://havetml.com/api/mcp",
      "headers": {
        "Authorization": "Bearer havetml_your_token_here"
      }
    }
  }
}

{
  "mcpServers": {
    "havetml": {
      "serverUrl": "https://havetml.com/api/mcp",
      "headers": {
        "Authorization": "Bearer havetml_your_token_here"
      }
    }
  }
}

{
  "mcpServers": {
    "havetml": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://havetml.com/api/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer havetml_your_token_here"
      }
    }
  }
}

{
  "mcpServers": {
    "havetml": {
      "url": "https://havetml.com/api/mcp",
      "headers": {
        "Authorization": "Bearer havetml_your_token_here"
      }
    }
  }
}

03

How it signs in

04

The 64 tools

24 read, 28 write, 12 that remove or replace something. Every one of them is annotated, so a client can tell them apart before it calls one.

upload_artifactwrite

Upload HTML, Markdown, YAML or JSON and get a permanent share link; re-uploading versions it.

get_artifactread

Read an artifact's JSON state, comments, annotations and metadata.

list_artifactsread

List your artifacts, optionally scoped to one project, folder or category.

search_skillsread

Search public skills — SKILL.md artifacts an agent can install and load.

set_artifact_visibilitywrite

Move an existing artifact between private, circle, unlisted and public.

create_encrypted_artifactwrite

Store an envelope encrypted on your own machine, so HaveTML holds only ciphertext.

create_projectwrite

Create a project — a shareable folder of artifacts with its own page.

list_projectsread

List your projects with their slugs, names and artifact counts.

set_project_default_visibilitywrite

Choose what new artifacts filed into a project inherit; moves nothing already in it.

add_commentwrite

Add a comment to an artifact, optionally pinned to a spot or threaded.

list_commentsread

List every comment on an artifact, including threaded replies.

invite_collaboratorwrite

Invite someone by email to view or edit one artifact.

list_collaboratorsread

List the people with access to an artifact.

revoke_collaboratordestructive

Revoke a collaborator's access to an artifact.

invite_project_memberwrite

Invite someone by email to a project; editors inherit edit access to its artifacts.

list_project_membersread

List the people with access to a project.

revoke_project_memberdestructive

Revoke a member's access to a project.

create_canvaswrite

Create a canvas: a board of cards, stickies and the connections between them.

get_canvasread

Read a canvas board: its nodes, edges, notes and comment threads.

update_canvasdestructive

Rename a board, rewrite its notes, or replace the nodes and edges on it.

add_canvas_nodewrite

Add one node to a canvas without touching what is already on it.

add_canvas_edgewrite

Draw an edge between two nodes already on a canvas.

list_eventsread

Poll for JSON-state updates and new comments on your artifacts.

register_webhookwrite

Register an HTTPS endpoint to receive signed artifact, comment and decision events.

list_webhooksread

List your webhooks with their scope, events and last delivery status.

delete_webhookdestructive

Stop delivering to a webhook and drop its pending deliveries.

create_decisionwrite

Open a decision on an artifact: a question that needs resolving.

list_decisionsread

List the decisions on an artifact, with their assignees.

get_decisionread

Read one decision by id, with its full detail and assignees.

assign_decisionwrite

Record who should decide an open decision, by user id or email.

revoke_assignmentdestructive

Remove an assignee from a decision; the decision stays open.

decide_decisionwrite

Set a decision's outcome and rationale, locking the record permanently.

supersede_decisiondestructive

Replace a decided decision with a new one; the original stays readable and locked.

update_decisionwrite

Change an open decision's title or context.

delete_decisiondestructive

Delete a decision that has not been decided yet.

list_templatesread

Browse ready-to-copy templates: working artifacts with their state and starter prompt.

get_templateread

Read one template's starter prompt, demo state and demo link before building from it.

use_templatewrite

Copy a template's demo into your account as a private artifact you can edit.

set_artifact_custom_slugwrite

Give a public artifact a readable /f/ path, or release one, without renaming it.

add_relationwrite

Draw a typed link between two artifacts, such as supersedes or depends on.

list_relationsread

List the typed links between your artifacts, for one artifact or one project.

remove_relationdestructive

Delete one artifact relation by id; neither artifact is touched.

get_artifact_contentread

Read an artifact's source for the current version or an earlier one.

update_artifact_jsondestructive

Change an artifact's live JSON state without a new version; replace mode drops keys.

list_mediaread

List the images, fonts and stylesheets stored with an artifact, and media quota used.

remove_mediadestructive

Delete one stored media file from an artifact and free its quota.

list_notesread

Read the notes written beside an artifact.

add_notewrite

Append a note to an artifact's notes, keeping what is already there.

update_notesdestructive

Replace an artifact's notes with new markdown, discarding what was there.

propose_canvas_layoutread

Work out a tidier layout for a board and return it without moving anything.

create_folderwrite

Create a folder inside a project to group artifacts; visibility is unchanged.

list_foldersread

List every folder in a project with its path and artifact count.

move_artifactwrite

Move an artifact into a folder or back to the project root.

rename_folderwrite

Rename a folder; artifact URLs are unaffected.

move_folderwrite

Move a folder, with its contents, under another folder or to the top level.

delete_folderdestructive

Delete a folder; its artifacts and subfolders move up one level.

get_projectread

Read a project's name, description, counts and pinned design system.

set_project_design_systemwrite

Pin an artifact as a project's design system, or unpin it.

propose_folder_organiseread

Work out a folder structure for a project and return it for approval; writes nothing.

apply_folder_organisewrite

Apply an approved folder proposal; refuses if the project changed since.

undo_folder_organisewrite

Reverse an applied folder organise using the undo plan from its reply.

list_connectionsread

List the remote MCP servers connected to your account; credentials are never included.

list_connected_toolsread

List the tools the owner has enabled on one connection; disabled tools cannot be called.

call_connected_toolwrite

Run one tool on a connected MCP server; the reply comes back fenced as untrusted data.

Parameters and full descriptions are in the MCP README, and in server-card.json if you would rather read it as JSON.

05

Limits, and what stays private

• Private by default. A new artifact opens for you and the people you invite, and for nobody else — the link alone does nothing. Your assistant has to be asked before it makes one link-readable.
• 50 MB per artifact on HaveTML, but this MCP endpoint runs on Vercel, which rejects request bodies over 4.5 MB. Anything bigger goes up from the dashboard.
• Encrypted files stay encrypted. A remote tool cannot do zero-knowledge encryption, so the encrypted path encrypts on your machine and sends HaveTML only ciphertext. It holds no key.
• Free for everyone. MCP is not a paid feature and nothing here consults billing.

06

Read the detail

• Full MCP README — Every tool, its read or write label, and the connect config for each client.
• server-card.json — The machine-readable card: endpoint, transport, auth and tool list.
• HaveTML docs — The REST API, tokens and the Chrome extension alongside MCP.