MCP Use Case

How Brad Feld plugged Marker.io into the operating system of his company

Company

Intensity Magic

AI client

Claude Code

Location

Colorado, USA

Employees

Industry

Software Engineering

Website

Intensity Magic

Ready to set up Marker.io MCP?

Learn more

Challenge

Running multiple products with user signal in three different systems: Linear, Help Scout, and Marker.io. Each is useful on its own, but recurring issues only become obvious when you look across all three.

Solution

Brad connected Marker.io's MCP server into CompanyOS — the markdown-based "operating layer" that lets him run his company through Claude Code.

Results

Marker.io bug reports flow into Linear and into Brad's Claude Code workflow automatically

One skill now triages Marker.io visual bug reports, surfacing recurring issues

The problem they were solving

Brad runs and ships multiple products with a co-founder Daniel Feld. User feedback and bug reports arrive across three different surfaces: Linear tickets, Help Scout conversations, and Marker.io bug reports. Each with its own format and its own dashboard. Pulling that signal together by hand is exactly the kind of work CompanyOS is designed to eliminate: the entire premise of his setup is that Claude Code, not a human, should be the layer that reaches into every tool.

‍

What they built

Brad wired Marker.io's MCP server directly into CompanyOS (his Claude Code-based operating layer) so visual bug reports flow into the same AI-driven workflows that handle the rest of the business.

Marker.io bug reports auto-route into Linear, with no manual ticket creation
The co-feedback skill pulls Marker.io reports alongside Linear tickets and Help Scout conversations, then aggregates them into thematic patterns for product decisions
Marker.io is one of 13 MCP servers connected into the Claude Code workflow: bug reporting and feature enhancement are queried on-demand whenever Claude needs visual context for a fix
Authentication via Bearer token (PAT-style), chosen specifically because API keys survive Claude Code updates (Brad's stated architectural preference)

‍

Where they are now

Marker.io is one of 13 MCP servers wired into Brad's Claude Code configuration. Bug reports flow into his Linear process automatically. When his workflow needs context from Marker.io, Claude Code queries it directly through the MCP server without separate dashboard or manual hand-off. The co-feedback skill aggregates Marker.io reports alongside Linear and Help Scout into thematic patterns that feed product decisions across his portfolio.

‍

Why this is worth stealing

‍Bug reports become AI-readable. Marker.io captures the visual + console + network state in a structured form. Once that's behind an MCP server, an AI agent can consume it the same way a developer would.
Cross-tool pattern analysis beats single-tool triage. Aggregating Marker.io with Linear and Help Scout in one skill means recurring issues surface across surfaces, not just within one of them.‍
MCP turns "another tool to check" into "a system Claude already uses." The integration removes the context-switch tax: the data is there when the workflow needs it, and stays out of the way otherwise.

‍

For more details read Brad's blog "Adventures in Claude"

"Aggregate user feedback from Linear tickets, Marker.io visual bug reports, and Help Scout conversations into patterns. Categorize by theme, identify recurring issues, and produce summaries for product decisions."

Brad Feld

Founder, Intensity Magic

Get started now

Free 15-day trial • No credit card required • Cancel anytime

Start free trial

Talk to sales

Frequently Asked Questions

What is MCP?

Model Context Protocol. It's an open standard that lets AI agents connect to external tools and data. The Marker.io MCP server makes your bug reports available to any MCP-compatible agent.

What is Marker.io?

Marker.io is a website feedback tool, bug reporting, UAT, and annotation tool for websites. It’s the best way to gather feedback and bug reports with screenshots, annotations, and advanced technical metadata. It also integrates perfectly with Jira, Trello, ClickUp, Asana (and more).

Which AI agents work with it?

Claude (Desktop and Code), Cursor, Windsurf, and any other client that supports MCP.

What can the agent access?

Everything captured in a Marker.io bug report: screenshots, URL, console logs, network requests, browser and OS details, and user description.

Do I need to be a developer to set it up?

You need to be comfortable running a setup command in your AI client. Our setup guide walks through it step by step. Most users are up and running in under 5 minutes.

Is it secure?

Yes. The MCP server uses your Marker.io credentials and only exposes data from projects you have access to. Nothing is shared outside your workspace.

Is it included in my plan?

Yes, the MCP server is available to all Marker.io customers at no extra cost.

Can the AI agent fix bugs on its own?

The agent can read reports, draft responses, and open pull requests. You decide how much autonomy to give it. Most teams keep a human in the loop for the final review.