Huddlekit

Read client feedback left on your website, with the screenshot, element selector, page URL and reply thread, then fix it in code, reply and resolve it.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Get Workspace: Returns the workspace this connection is pinned to, with project counts by type. Takes no arguments — the workspace is fixed at consent time and cannot be changed by the caller.
  • List Projects: Lists the projects in the connected workspace — websites, documents and web apps — most recently active first. Optionally filter to one type. Note that web apps are ordered by last upda
  • List Comments: Lists feedback comments on one project. Returns summaries without screenshots; use get_comment_context for the full detail of a single comment.

What data it sees

Do you need an account

No: the server works without sign-in

Read client feedback left on your website, with the screenshot, element selector, page URL and reply thread, then fix it in code, reply and resolve it. Clients pin comments on the live site with no account or extension; this server lets your agent list a project's open comments, open one with its screenshot as an image, and, with write access, reply, set status or priority, tag, assign and resolve. Read only by default, OAuth sign-in, no API key. Needs a Huddlekit Pro or Team plan.

How to connect

How to connect Huddlekit to Claude

The server address to paste into Claude settings:

https://huddlekit--huddlekit.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Huddlekit to ChatGPT

The server address to paste into ChatGPT settings:

https://huddlekit--huddlekit.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Huddlekit to Cursor

The server address to paste into Cursor settings:

https://huddlekit--huddlekit.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (8)

Raw names from tools/list. Only developers need these.

get_workspaceReturns the workspace this connection is pinned to, with project counts by type. Takes no arguments — the workspace is fixed at consent time and cannot be changed by the caller.
list_projectsLists the projects in the connected workspace — websites, documents and web apps — most recently active first. Optionally filter to one type. Note that web apps are ordered by last update rather than last feedback activity, which that table does not record.
list_commentsLists feedback comments on one project. Returns summaries without screenshots; use get_comment_context for the full detail of a single comment.
get_comment_contextEverything needed to act on one comment: text, status, page URL, element selector, viewport, the reply thread, and the screenshot as an image. The concrete requested change is often in the replies rather than the original comment.
update_comment_statusTriage one comment: set its status, priority, or resolved flag. Requires a write-approved connection. Sends no notifications — the notification and digest triggers fire on comment creation, not on updates. Omitting a field leaves it unchanged; pass priority "none" to clear a priority back to unset.
add_replyPost a reply into a comment thread as the connected user. Requires a write-approved connection. NOTE: this notifies the thread participants exactly as a human reply does, so replying to many comments at once sends many emails. To notify a specific teammate, write "@Their Display Name" in the text exactly as it appears in get_workspace().members — the mention is resolved and they are notified. Only members of the connected workspace can be mentioned; the response reports who was actually notified.
set_tagsReplace the tags on one comment. Pass the full set — an empty array clears them. Tag ids come from get_workspace; an agent cannot create new tags, only apply the ones the workspace already defines. Requires a write-approved connection.
assign_commentReplace the assignees on one comment. Pass the full set — an empty array unassigns everyone. Member ids come from get_workspace, which returns ids and roles but NOT names. Requires a write-approved connection.