Ollav

app.ollavPublished by ollav.appOfficial publisherv1.1.0Updated Oct 29, 2026

Share HTML prototypes as live links; read element-pinned review comments; publish new versions.

Overview

AI-generated overview

Ollav is a hosted MCP server that lets an assistant share HTML prototypes as live links, read element-pinned review comments, and publish new versions.

What you can do
  • Share and version HTML documents: publish a file as a commentable link, update it at the same URL, list and inspect documents with their version history
  • Read review feedback: fetch open threads as Markdown and JSON with a polling cursor, or pull every comment including resolved ones
  • Write review feedback: pin a comment to a specific element, reply, resolve or reopen threads, react with an emoji, delete comments
  • Export account data as a signed ZIP download link
When to use it
Useful when a team reviews HTML prototypes or pages and wants an agent to take part in the loop: share the page, collect pinned feedback, edit, and republish. Fits design and front-end review workflows where comments must stay attached to specific elements.
Requirements
Remote Streamable HTTP endpoint at app.ollav.app/mcp; nothing to run locally. Authentication is required: OAuth sign-in with workspace selection, or an API key sent as an Authorization bearer header (OLLAV_API_KEY in client configs). Keys are created in the Ollav account, with separate sandbox and live keys. Clients that only support local stdio servers need a bridge such as mcp-remote.
Before you install
The API key is a bearer credential granting access to the workspace's documents and comments; keep it in an environment variable rather than in shared config. Live keys act on real work, so prefer sandbox keys while testing. The assistant can publish new versions at existing URLs, add, resolve and delete comments, and generate a signed export link to all account data, so review changes before approving. Shared links and comments are visible to the people you send them to.

Installation

In SourceWeft

  1. Open Ollav in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.ollav%2Follav/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "ollav": {
      "type": "http",
      "url": "https://app.ollav.app/mcp"
    }
  }
}

README

Ollav MCP

Ollav is where humans and AI agents review HTML together. Your agent shares a prototype as a live link, your team pins comments to the exact element they mean, and the agent reads those comments, fixes the page and publishes the next version at the same URL.

This repo holds Ollav's Claude Code plugin and MCP setup. The server itself is hosted: there is nothing to run.

Claude Code

Install the plugin (the MCP server plus a skill that tells Claude when to use Ollav):

/plugin marketplace add ollav-app/ollav-mcp/plugin install ollav@ollav

Set OLLAV_API_KEY in your environment first. Or add just the MCP server:

bash
claude mcp add --transport http ollav https://app.ollav.app/mcp --header "Authorization: Bearer $OLLAV_API_KEY"

Check it: claude mcp list shows ollav as connected.

Claude.ai and Claude Desktop

Settings → Connectors → Add custom connector. Name: Ollav, URL: https://app.ollav.app/mcp. Claude signs you in with OAuth and you pick the workspace it may use.

Cursor

~/.cursor/mcp.json (or .cursor/mcp.json in a project):

json
{  "mcpServers": {    "ollav": {      "url": "https://app.ollav.app/mcp",      "headers": { "Authorization": "Bearer ${env:OLLAV_API_KEY}" }    }  }}

ChatGPT

Settings → Apps & Connectors → Create (developer mode). Name: Ollav, MCP server URL: https://app.ollav.app/mcp, Authentication: OAuth. Attach an HTML file and say "share this on Ollav".

OpenAI Codex CLI

bash
codex mcp add ollav --url https://app.ollav.app/mcp --bearer-token-env-var OLLAV_API_KEY

Or in ~/.codex/config.toml:

toml
[mcp_servers.ollav]url = "https://app.ollav.app/mcp"bearer_token_env_var = "OLLAV_API_KEY"

Any other MCP client

Point it at https://app.ollav.app/mcp and send Authorization: Bearer <key>. Clients that only run local stdio servers can bridge with npx -y mcp-remote https://app.ollav.app/mcp --header "Authorization: Bearer $OLLAV_API_KEY".

Tools

ToolWhat it does
share_htmlPublish an HTML file and get a link people can comment on
publish_new_versionUpdate something already shared: same URL, comments kept
list_documentsFind documents shared earlier
get_documentMetadata, share URL and version history
get_reviewOpen feedback threads as Markdown + JSON, with a polling cursor
get_commentsEvery comment, resolved ones too
add_commentPin a comment to an element, or reply
resolve_commentMark a thread done (or reopen it)
react_to_commentAcknowledge a comment with an emoji
delete_commentDelete a comment and its replies
export_dataSigned link to a ZIP of your data

The loop

share_html → people comment → get_review → edit → publish_new_version → resolve_comment.

License

MIT. This repo holds configuration only; use of the hosted service is covered by Ollav's terms at https://ollav.app.

Source: README.md at commit bb560f3

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.1.0LatestOct 29, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts