MCP server

MCP server

Your coding agent has never seen production.
Now it can.

Your coding agent has never seen production.
Now it can.

Rollbarโ€™s MCP server gives Cursor, Claude Code, VS Code, Codex, or Copilot your errors, deploys, replays, and team comments, and lets your agent comment back. You stop copying error details between tabs.

Rollbarโ€™s MCP server gives Cursor, Claude Code, VS Code, Codex, or Copilot your errors, deploys, replays, and team comments, and lets your agent comment back. You stop copying error details between tabs.

Open source under the MIT license. Free plan included.

Open source under the MIT license. Free plan included.

Example PR created by Rollbar Resolve, describing the identified problem and the recommended code changes.

What your agent can do

Everything Rollbar knows about production is
one question away.

A flowchart, with an error either leading to: Auto-fix based on rules, Fix on demand, or Keep in error list.

Query errors and get full context

Your agent pulls any itemโ€™s stack trace, request parameters, telemetry, and occurrence count, right from your IDE or terminal.

Check what shipped and what broke

Your agent sees recent deploys and ties errors to the release that introduced them.

Isolated environment, test cases, and PR with complete description in a single package.
A flowchart showing Resolve Agent's feedback loop, highlighting self-learning and code revision as possible feedback outcomes.

Find the noisiest problems

Your agent lists the top items from the last 24 hours, filtered by status, level, or search query, and triages them for you.

See what the user did

Your agent reads the replay and traces the userโ€™s clicks to the failure.

Settings representing how Resolve can be customized.
A flowchart, with an error either leading to: Auto-fix based on rules, Fix on demand, or Keep in error list.

Join your teamโ€™s conversation on the error

Your agent reads what your team already tried, then posts its findings as a comment on the item, so everyone sees its work in the same place.

Setup

Set up in
under two minutes.

The server runs locally through your AI tool, with nothing to host.

1.

1.

Get your Rollbar access token

Get your Rollbar access token

Use any Rollbar access token: account, project, or personal. The setup docs walk you through it.

2.

2.

Add the config block

Add the config block

Add one block to the MCP config file in Claude Code, Codex CLI, Cursor, GitHub Copilot CLI, Junie, or VS Code. The docs have the block for each.

{
  "mcpServers": {
    "rollbar": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@rollbar/mcp-server@latest"],
      "env": {
        "ROLLBAR_ACCESS_TOKEN": "<your access token>"
      }
    }
  }
}

3.

3.

Start asking questions

Start asking questions

Restart your editor and ask your agent about your production errors. It now has direct access to your Rollbar project data.

Why it matters

Your agent read every line of your code and still
missed the bug.

Coding agents reason well about code and poorly about production. They cannot see which errors are live, which deploy caused them, or what your team already learned. The MCP server gives them that context.

Detect

Detect

Rollbar already groups your errors and tracks your deploys.

Diagnose

Diagnose

Your agent pulls stack traces, telemetry, and deploy history directly, so you copy nothing.

Fix

Fix

The fix it suggests is grounded in the real error, the userโ€™s path, and the deploy.

How it runs

Built for engineers who read the setup before they trust it.

This is Rollbarโ€™s official server, open source under the MIT license.

View on GitHub โ†’

Runs on your machine.
Your AI tool launches it as a local process.

Installs in one line in your toolโ€™s MCP config.

Uses your Rollbar access token.

Real scenarios

Paste one of these prompts and watch what
your agent does.

Check Rollbar for new critical errors in production since the last deploy. For the one with the most occurrences, pull the full item details and suggest a fix.

Your agent calls get-deployments to find the latest release, pulls the top critical error, and comes back with a diagnosis tied to the stack trace and a code change.

Show me the top 10 unresolved errors in production and group them by likely root cause.

Your agent gets the top items and pulls details for each. You get a prioritized summary without opening the dashboard.

Fetch the replay for Rollbar item 7842 and tell me where the bug is.

Your agent lines up the userโ€™s path with the stack trace to find where the bug starts.

Is the error from this morningโ€™s deploy fixed?

Your agent checks occurrences since the deploy and tells you whether the error is still live.

Works with your tools

It works with any tool that speaks the
Model Context Protocol.

Cursor

MCP settings

Claude Code

.mcp.json

VS Code

.vscode/mcp.json

Codex CLI

~/.codex/config.toml

Copilot

~/.copilot/mcp-config.json

Any MCP client

npx -y @rollbar/mcp-server

What data does it send to my AI tool?

What data does it send to my AI tool?

How is this different from Rollbar Resolve?

How is this different from Rollbar Resolve?

Does it support multiple Rollbar projects?

Does it support multiple Rollbar projects?

Get started

Give your agent
production context.

Plans start at $0, with a 14-day free trial.