twocents
Server Details
Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- twocents-page/twocents-mcp
- GitHub Stars
- 0
- Server Listing
- twocents
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a sharply distinct purpose: publish (share_page/share_pages), read (get_feedback), and close the loop (resolve_feedback). The only near-overlap is share_page vs share_pages, and the description explicitly resolves it ('use this instead of calling share_page N times whenever you have more than one page'). An agent can select correctly without hesitation.
All four tools follow a clean verb_noun snake_case pattern: get_feedback, resolve_feedback, share_page, share_pages. The singular/plural distinction maps directly onto the single-page vs multi-page semantics, so the naming is both consistent and informative, with no mixed conventions.
Four tools cover a tight, complete review loop—publish, collect, resolve—plus a batch variant for multi-page sets, so every tool earns its place with no redundancy. Nothing feels padded or missing at the count level.
The core lifecycle is fully covered: create (share_page/share_pages), read (get_feedback), and update/resolve (resolve_feedback with reopen via resolved:false). Minor gaps remain—there is no tool to list or manage existing rooms, and large corpora require a documented out-of-band curl uploader rather than an MCP tool.
Available Tools
4 toolsget_feedbackGet reviewer feedback for a shared pageAInspect
Fetch the reviewer notes for a page shared with share_page, as markdown grouped by page. Each note carries the anchored text, the element and its markup as the reviewer saw it, so you can locate and apply it; each page heading carries a URL to read the whole page back, so you never have to guess which file it is. Show your human each new note and apply only the ones they approve. Pass the note ids already decided in earlier sessions as "handled" to see only what is new.
Inputs: room (required), handled.
resolve_feedbackMark reviewer notes as addressedAInspect
Mark notes resolved once you have actually applied them. This is what closes the loop: the note leaves the active list for every later get_feedback, and the reviewer who wrote it sees it marked resolved on the page — live, if they have it open — instead of finding their old note sitting next to content you already fixed. Pass "what" you changed; that sentence is shown to the reviewer, so write it for them, not for the log. Requires the creatorKey that share_page returned when the room was created — the review link alone cannot resolve, or any reader could clear feedback that was not theirs. Nothing is deleted: call again with resolved:false to reopen a note.
Inputs: ids (required), room (required), creatorKey (required), by, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Comment on AI-generated webpages; feedback flows back to your coding agent. Free, MIT, local-first.
Agents publish self-contained HTML to a stable review link, with page-level feedback and revoke.
Share HTML and Markdown files from AI agents within your company, with versions and comments.
MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to publish HTML artifacts for human review, receive anchored feedback, and iterate until approval.2-
- AlicenseNot gradedqualityCmaintenanceLocal-first HTML review workspace for AI coding agents, enabling direct text and formatting edits, element comments, area annotations, and slide-aware review with durable agent handoffs.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to publish work mid-task so a real human reviewer can open it, pin comments to the exact elements that are off, and return a verdict. The agent then iterates on that feedback until the work is approved, giving you human judgment on things like design taste, wording, and confusing pages.38 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to publish work mid-task for real human review, collect pinned comments and verdicts, and iterate until the output is approved. It supports second opinions and human judgment on artifacts such as sites, videos, and text.38 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.