About Ollav
Ollav is a hosted service for teams and AI agents to review HTML prototypes together. MCP clients can publish pages, retrieve element-specific feedback, and update a shared link while retaining comments.
Key features
- 01Publish HTML prototypes as shareable links
- 02Pin comments to page elements
- 03Read review threads and comments
- 04Publish versions at the same URL
- 05Manage comment status and replies
Use cases
- 01Collect feedback on a prototype from a team
- 02Revise a page using element-pinned comments
- 03Keep review history while publishing updates
MCP support
Ollav exposes a hosted Streamable HTTP MCP server at `https://app.ollav.app/mcp`. MCP clients can share HTML, retrieve reviews and comments, and publish updated versions.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://app.ollav.app/mcpclaude mcp add --transport http app-ollav-ollav https://app.ollav.app/mcp{"mcpServers":{"app-ollav-ollav":{"type":"http","url":"https://app.ollav.app/mcp"}}}Open in Cursor{"servers":{"app-ollav-ollav":{"type":"http","url":"https://app.ollav.app/mcp"}}}Open in VS Code{"mcpServers":{"app-ollav-ollav":{"type":"http","url":"https://app.ollav.app/mcp"}}}{"mcpServers":{"app-ollav-ollav":{"serverUrl":"https://app.ollav.app/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://app.ollav.app/mcpAuth requiredTools
Details
From the project READMEOllav 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.
- Endpoint (Streamable HTTP):
https://app.ollav.app/mcp - API keys: https://app.ollav.app/keys (
ol_test_...for a sandbox,ol_live_...for real work) - Full docs: https://ollav.app/docs/mcp · Quickstart: https://ollav.app/docs/agents
- MCP Registry:
app.ollav/ollav
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:
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):
{
"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
codex mcp add ollav --url https://app.ollav.app/mcp --bearer-token-env-var OLLAV_API_KEY
Or in ~/.codex/config.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
| Tool | What it does |
|---|---|
share_html | Publish an HTML file and get a link people can comment on |
publish_new_version | Update something already shared: same URL, comments kept |
list_documents | Find documents shared earlier |
get_document | Metadata, share URL and version history |
get_review | Open feedback threads as Markdown + JSON, with a polling cursor |
get_comments | Every comment, resolved ones too |
add_comment | Pin a comment to an element, or reply |
resolve_comment | Mark a thread done (or reopen it) |
react_to_comment | Acknowledge a comment with an emoji |
delete_comment | Delete a comment and its replies |
export_data | Signed 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.