wovo-mcp
Enables AI agents to deploy HTML pages and manage them (list, archive, move, rename) in a versioned library via MCP tools.
README
wovo
Deploy any HTML — from any AI tool or your terminal — to a versioned, shareable library. wovo is the CLI and MCP server for wovo.dev.
Every deploy snapshots a new version, returns a live URL, and files the page in your workspace library. Re-deploying the same slug never overwrites — it appends a version you can roll back to.
Install
Run it one-off with npx:
npx @gowovo/wovo deploy ./report.html
Or install globally and use the wovo command:
npm i -g @gowovo/wovo
wovo deploy ./report.html
Connect (recommended)
One command — it opens your browser to sign in, then wires up your AI tool. No token to copy.
npx @gowovo/wovo setup
From then on, just tell your agent "deploy this to Wovo" and the page lands in your library.
Manual auth (CI / headless)
When there's no browser (CI, a server), provide a deploy token from your workspace settings on wovo.dev via env, a config file, or --token:
export WOVO_TOKEN="wv_…"
export WOVO_WORKSPACE="my-workspace"
CLI
wovo setup # connect your AI tool: browser sign-in + skill + MCP + test deploy
# --scope project|user this project, or every project on this machine
# --behavior auto|ask|manual publish automatically, offer first, or only on request
wovo deploy <file|dir> # deploy one .html, or every .html under a folder
wovo list # list pages in the workspace
wovo pages archive <slug> # hide a page from the library (link still works)
wovo pages unarchive <slug> # restore an archived page
wovo pages move <slug> --space S # change a page's space
wovo pages rename <slug> <new> # change a page's path; old links redirect
wovo domains list # custom domains
wovo domains add <d> --page <slug> # link a domain (prints DNS records)
wovo domains status <d> # re-check DNS / verification
wovo domains remove <d> # unlink a domain
| Flag | Default | What it does |
|---|---|---|
--workspace W |
env WOVO_WORKSPACE, else resolved from the token |
Target workspace |
--space S |
top folder name | Group pages under a space |
--tool T |
cli |
Source-tool tag |
--slug S |
derived from path | Explicit slug (single-file deploys) |
--url U |
env WOVO_URL or https://wovo.dev |
Wovo base URL |
--token T |
env WOVO_TOKEN |
Deploy token |
Config resolution: CLI flags → ./wovo.json → env (WOVO_URL, WOVO_TOKEN, WOVO_WORKSPACE).
// wovo.json
{ "workspace": "my-workspace", "token": "wv_…", "space": "reports" }
Examples
WOVO_TOKEN=… wovo deploy ./report.html --workspace acme
wovo deploy ./site --workspace acme --tool claude-code
wovo list --workspace acme
MCP server
wovo also ships an MCP server (wovo-mcp) so AI agents can deploy and list pages as tools. Register it with Claude Code:
claude mcp add wovo \
--env WOVO_TOKEN=wv_… \
--env WOVO_WORKSPACE=my-workspace \
-- npx -y -p @gowovo/wovo wovo-mcp
Tools: wovo_deploy (inline html or a file path), wovo_list, wovo_pages_archive,
wovo_pages_unarchive, wovo_pages_move, wovo_pages_rename, wovo_domains_list,
wovo_domains_add, wovo_domains_remove, wovo_domains_status.
Requirements
Node.js >= 18 (uses the global fetch). Zero dependencies for the CLI; the MCP server uses @modelcontextprotocol/sdk and zod.
License
MIT © Shashank Jha
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.