mcpField
T
twocents

twocents

VerifiedFeaturedRemote
twocents.pageProductivity0Updated 7w ago
RepositoryVisit website

About twocents

twocents is a remote MCP server for AI agents to collect visual feedback on HTML pages. Reviewers add anchored notes through a link, and agents can retrieve them to locate changes.

Key features

  1. 01Share self-contained HTML pages
  2. 02Pin notes on page elements
  3. 03Update review rooms live
  4. 04Retrieve notes as Markdown
  5. 05Collapse previously handled notes

Use cases

  1. 01Collect visual review of a page
  2. 02Locate requested edits by selector
  3. 03Share page updates with reviewers

MCP support

Exposes the `share_page` and `get_feedback` tools to MCP clients through the remote server at `https://twocents.page/mcp`.

#feedback#review#human-in-the-loop#collaboration#html#design#presentation

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://twocents.page/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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.

Tools

2
ParameterTypeRequiredDescription
htmlstringNoA complete, self-contained HTML document (inline CSS/JS/images — no local file references, they will 404 for reviewers). Max ~120 KB.
markdownstringNoMarkdown to render as a document, instead of "html". Use this for plans, specs, PR descriptions, summaries — anything you want a human to read and approve before you act. Pass exactly one of html or markdown. Max ~120 KB.
roomstringNoRoom id from a previous share_page call, to update that page. Omit to create a new room.
pathstringNoFor multi-page sets: the filename this content lives at in the room (e.g. "about.html" or "plan.md"). Defaults to "index.html", the page reviewers land on. Share the other files into the same room id and link between them with plain relative hrefs — formats can be mixed freely, so a plan.md may link to a demo.html and back.
sourcestringNoWhere this content came from, for whoever reads the feedback later — a project path like "DROPS.md" or "public/p/foo/index.html", or a note like "drafted in this conversation, not yet a file". You are the only one who knows this: twocents receives HTML, never a path, so if you omit it a future session gets reviewer notes with nothing to point them at the right file. get_feedback echoes it back verbatim.

Details

From the project README

twocents — human feedback for AI agents (MCP server)

A remote MCP server, live at https://twocents.page/mcp. Connect it and your AI agent can send any HTML page to real people for visual review — and read their pinned notes back. No auth, no API key, no install for reviewers.

Tools

  • share_page — send a self-contained HTML document, get back a review link. Anyone who opens it can pin notes directly on the page — no login, works on any device. Call again with the same room id and connected reviewers see the update live.
  • get_feedback — the pinned notes, returned as markdown with the anchor text/selector for each note so your agent can find and fix the exact spot. Pass the optional handled array (note ids already decided in earlier sessions) and those collapse to one line each, so the response leads with what's new.

Config

{
  "mcpServers": {
    "twocents": {
      "url": "https://twocents.page/mcp"
    }
  }
}

Connect

Claude Code

claude mcp add --transport http twocents https://twocents.page/mcp

Claude.ai (web or desktop) — Settings → Connectors → Add custom connector → paste https://twocents.page/mcp

Cursor or any MCP client — use the config block above (an HTTP MCP server; no auth, no API key).

The loop

Ask your agent to "share this page for feedback" → send the link to anyone → they pin notes on the live page → ask your agent to "get the feedback" and apply it. The whole review cycle without leaving your editor.

What's in this repo

The complete server source: mcp.js — a zero-dependency Streamable HTTP (stateless) JSON-RPC handler, ~300 lines. It runs inside a Cloudflare Worker and stores pages/notes in a Durable Object per review room (env.ROOMS); the Worker, relay, and reviewer UI live in the main (private) twocents.page codebase. server.json is the MCP registry manifest (page.twocents/twocents).

Privacy model: a room id is an unguessable capability — knowing it is the permission to read/write that room. Review links are excluded from search indexing.

See it in action

Every page in our interactive explainer library has a live review room — open one and pin a note. Or get feedback on your own work.

Comments

Markdown supported

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.