Skip to main content
Glama

twocents

Server Details

Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
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

A4.6/5.0

Scored across 4 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness4/5

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 tools
get_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.

share_pageShare a page for visual feedbackAInspect

Share a page or document and get back a review link to send to people. Pass "html" for a self-contained page, or "markdown" for a plan, spec, PR description or report — markdown is rendered to a styled, readable document for you, so prefer it whenever the thing you want a human to approve is prose rather than a built page. Reviewers open the link and pin notes directly on it — no login or install. Call again with the same room id to update the page; connected reviewers see the update live. Use get_feedback to collect the notes. Rooms are sticky per project: if the project has a .twocents/state.json, pass its room id instead of creating a new room, so the review link stays stable across sessions.

Inputs: html, path, room, source, +3 more.

share_pagesShare a whole set of pages in one requestAInspect

Publish a multi-page set — an entry page plus the pages it links to — into one room as a single atomic operation. Either the whole set lands or nothing changes, so a reviewer never opens a page whose links point at pages that were never stored. Use this instead of calling share_page N times whenever you have more than one page. Note the ceiling: a room is a review set, not a host — it holds 200 pages and 6 MB total. For a large generated corpus, share the entry points a human would actually read and link out to the rest; nobody pins notes on four hundred pages. If the pages are already files on disk, prefer the uploader — it reads them from the folder instead of making you emit every byte: curl -fsSL /agent.mjs -o .twocents/agent.mjs && FBL_ROOM= node .twocents/agent.mjs --publish

Inputs: pages (required), room, entry, prune, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Local-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.
      1
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables 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 npm
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables 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 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.