Comment on the page.
Your agent makes the change.
A guide for Claude Code, Cursor, and Codex. Pin feedback to real elements, connect your agent over MCP, and let it read, fix, and reply.
Why your agent needs the element
A screenshot makes your agent guess which button you mean. A pinthread comment names it. Each thread carries:
- The page URL
- The element’s selector and visible text
- The comment position or selected area
- Every reply, so the agent sees what the team agreed
Page: /pricing
Target: #annual-plan-button
Element text: Choose plan
Maya: Make it clear this is billed annually.
Alex: Keep the monthly equivalent visible too.01 · Add pinthread to your site
Sign up free, create a project, and paste one script tag into your shared layout. The install guide has the steps for each framework.
<script src="https://pinthread.dev/embed.js"
data-project="YOUR_PROJECT_KEY" defer></script>02 · Create an agent token
Open your project in the dashboard and choose Agent access. A read token lists and reads threads. A write token can also reply, start, resolve, and reopen threads. Store it as PINTHREAD_TOKEN, never in your repository.
03 · Connect your agent
pinthread is a remote MCP server at https://pinthread.dev/mcp. The token decides which project the agent sees.
Claude Code
claude mcp add --transport http pinthread https://pinthread.dev/mcp \
--header "Authorization: Bearer $PINTHREAD_TOKEN"Run it in your project with PINTHREAD_TOKEN set to your agent token.
Cursor
{
"mcpServers": {
"pinthread": {
"url": "https://pinthread.dev/mcp",
"headers": { "Authorization": "Bearer ${env:PINTHREAD_TOKEN}" }
}
}
}Save it as .cursor/mcp.json in your project.
Codex
[mcp_servers.pinthread]
url = "https://pinthread.dev/mcp"
bearer_token_env_var = "PINTHREAD_TOKEN"Add it to ~/.codex/config.toml. Codex reads the token from PINTHREAD_TOKEN.
Other MCP clients work too. The MCP server reference covers every client, token scope, and tool.
04 · Tell your agent how to work
Add this to your AGENTS.md or CLAUDE.md, so every session follows the same steps:
When I mention pinthread comments, use the pinthread MCP tools. List the open threads, read each one with get_thread, then make the change and check it. Reply with what you changed. Resolve a thread only when you are confident the fix is complete. If a comment is a question or needs a decision, reply and leave it open.05 · Run the loop
- A reviewer pins a comment on the element that needs to change.
- You ask your agent to fix the open pinthread comments.
- The agent calls
list_threads, thenget_threadfor each one. - It edits your code and checks the change.
- With a write token, it replies with what it changed and resolves the thread. A question stays open for you.
To react to new feedback as it arrives, the agent can call list_events. The tool list has every tool.
Guides for each agent
No MCP? Copy the comments
Open the expanded drawer and choose Copy all comments for agent. Paste the result into any agent that can read text. Resolved threads stay out of the prompt.
Signed project webhooks
Project owners can configure an HTTPS receiver through /project/webhook?project=_pinthread&workspace=KEY with their dashboard session. Use POST to configure the URL, GET to read its delivery log, DELETE to remove it, and POST with &test=1 to send a test event.
Created, updated, and resolved threads and new replies carry an HMAC-SHA256 signature and timestamp. The preferred payload field is type. Existing consumers keep the legacy kind and event header. Deliveries retry up to five times. The Node server encrypts secrets using a dedicated PINTHREAD_WEBHOOK_KEY and blocks private-address targets and redirects.
Questions
Which agents work with pinthread?
Any MCP client that supports streamable HTTP. This guide covers Claude Code, Cursor, and Codex. Other agents can take the copied comments as a prompt.
Can the agent change more than I want?
A read token can only list and read threads. Give the agent a write token only when it should reply to, start, resolve, or reopen threads.
Does pinthread run the agent or change my code?
No. pinthread gives your agent the context. Your agent edits your repository. pinthread does not run an agent, upload your repository, or change your code.
Answers to common feedback questions
- Annotate disabled buttonsSelect disabled buttons without activating them. Pin a website comment to the control and give its context to your coding agent.
- Comment on a modalKeep an open dialog or drawer available while you annotate it. Pin feedback to its content and share the thread with your coding agent.
- Claude Code visual feedbackConnect Claude Code to website comments with MCP. Give it the page, selected element, and team discussion without pasting a screenshot.
- Cursor visual feedback over MCPConnect Cursor to pinned website comments over MCP. Let your coding agent read element context, replies, and the requested change.
- Share feedback with a teamShare element-anchored feedback with reviewers and coding agents. Keep replies together so the team can agree before a change is resolved.
- Stop page clicks while annotatingPrevent an annotation click from triggering the page control underneath it. Select the element, write feedback, and keep the page action unchanged.
Guides per agent and use case
- Design QACompare the implemented page with the designer's intent.
- Visual bug reportsGive the engineer a page, element and reproduction steps.
- For Claude CodeAdd the server with one claude mcp add command.
- For CursorAdd the server in .cursor/mcp.json.
- For CodexAdd the server in config.toml or with codex mcp add.
Comparing tools
See how pinthread compares with Agentation, Agentation (feature by feature), Vercel comments, Marker.io, BugHerd, Userback, Pastel, Ruttl, React Grab, Feedbucket, or read all alternatives.