Collaboration
twocents.page
Share HTML pages and retrieve feedback notes with anchor text/selectors for easy application.
ENDPOINT 1
https://twocents.page/mcp
MCP server metadata
- Name
- twocents
- Version
- 1.0.0
Share HTML pages for human visual feedback. Call share_page with a self-contained HTML document to get a review link; give that link to people; call get_feedback with the room id to collect their annotations as markdown.
Known tools 2
share_pageShare a self-contained HTML page and get back a review link to send to people.
Potential side effectsget_feedbackFetch the reviewer notes for a page shared with share_page, as markdown grouped by page with the anchor text/selector for each note so you can locate and apply it.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.twocents]
url = "https://twocents.page/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"twocents": {
"type": "http",
"url": "https://twocents.page/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: twocents
Remote MCP URL: https://twocents.page/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"twocents": {
"url": "https://twocents.page/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"twocents": {
"type": "http",
"url": "https://twocents.page/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "twocents",
"transport": "streamable-http",
"url": "https://twocents.page/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.