MCP

Overview
Jam MCP (Model Context Protocol) lets your developer tools and AI agents open a Jam recording and automatically load its data into context (video, user events, console logs, errors and network requests). As a developer, you’ll debug faster without hand-typing steps to reproduce, copy-pasting stack traces, or screen-sharing.
Your AI models and agents can use Jam’s MCP server to access your Jam recordings and their data in a simple and secure way.
Paste an existing Jam link into supported MCP clients like VS Code, Cursor, Windsurf, or Claude Code, and the Jam's context appears right where you’re working.
Prerequisites
1. Configure
2. Getting Started
Once you have configured your MCP:
Copy one or multiple Jam links
Prompt your agent and paste the Jam link. See our prompt tips and examples below
Authenticate your IDE with Jam
Approve any of the tool requests the agent makes
3. Available Features in Jam MCP
Tools
getDetails
Get a quick snapshot of the Jam. Who made it, what happened, and which other tools to try next.
getConsoleLogs
Grab the console logs from the Jam
getNetworkRequests
List every web request from the Jam as JSON, trimmed to the essentials for fast debugging.
getScreenshot
Get every screenshot from a screenshot Jam so you can inspect
getUserEvents
Read each click, input and page navigation change in plain language.
analyzeVideo
Analyzes Jam video recordings to extract insights, detect issues, and provide structured feedback.
4. Tips
Prompting tips:
Use Jam MCP to help with bug analysis, product feedback, and give agents context to debug issues.
Be as specific as you would with another engineer for the best results
Start with small features or bug fixes, tell your Agent to propose a plan using Jam MCP, and verify its plan before moving on to suggested edits
5. Examples
Examples of how the team at Jam uses Jam MCP:

Tomasz (Product Engineer) Uses Jam MCP to debug issues, by providing the context of a bug to Cursor, to ship a fix.
Review this Jam <Jam Link Placeholder> and analyze the problem, cross-reference it with the existing codebase, and prepare a detailed plan for implementation.

Frits (Product Manager) let’s Claude review and analyze customer Jams to spot common issues and patterns. Claude turns the findings into neatly grouped Linear tickets.
Analyze these Jams, perform root-cause analysis, and organize them into efficient work packages to minimize engineers’ context switching; create Linear tickets from the analysis.
<Jam Link Placeholder>

Martin (Product Designer) records product and design feedback with the Jam extension. Jam MCP provides the context for Claude Code to plan and ship a ready-to-review PR with the implemented Feedback.
I recorded product feedback in a Jam. Create an implementation plan for the changes requested in this Jam:
<Jam Link Placeholder>
6. Feedback
Got an idea that would make Jam MCP faster, smarter or more useful? Drop it in the form below (30 seconds, tops).
FAQ
Last updated
Was this helpful?