Connect Sentry with Unblocked to link errors to the code that caused them

Sentry adds exception and event evidence from production to the code history Unblocked already understands. An agent can use the selected project’s issue context to investigate where a failure appears, then follow related code and pull-request evidence toward the likely change.

Error context is reconciled with your code, pull requests, and discussions, so an investigation can trace an error to the change that introduced it — accelerating root-cause analysis.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Windsurf, GitHub Copilot, Codex — can pull this context through a single Unblocked MCP server connection.

What you get

• Issues, errors, and events — Unblocked references the Sentry issues, errors, and events from the projects you select and cites the issue it used.
• Error-to-code tracing — Because Sentry data sits alongside your code and pull requests, investigations connect an error to the change that likely introduced it.
• Read-only, project-scoped connection — A read-only auth token connects your organization; you choose exactly which projects Unblocked indexes.
• Cross-source synthesis — Sentry issues are combined with your code, pull requests, Datadog signals, and Slack threads into a single knowledge graph.

Need screenshots or troubleshooting?This is a concise connection summary. Follow the complete setup guide ↗

Prerequisites

• An Unblocked account (free to start).
• A Sentry user auth token with read-only scopes. Self-hosted Sentry is not supported.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Sentry to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Incident Management select Sentry.
2. In Sentry, create a user auth token with the read-only scopes org:read, project:read, issue:read, and event:read.
3. Paste the token into Unblocked and select your Sentry organization.
4. Select the projects to index and click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS, one command auto-detects and configures your supported agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, VS Code):

The install script supports macOS only. On Windows or Linux, add the server manually using the configuration below, or follow the manual install guide ↗.

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Sentry context, connect Sentry to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Sentry data, searching issues, errors, events alongside your other connected sources and returning cited results through these tools:

• context_researchMulti-source research across your Sentry issues, errors, and events, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the Sentry issue it used.
• context_get_urlsFetches the full content behind a Sentry issue URL your agent encounters — plus GitHub, Jira, Datadog, Slack, and more.

Questions you (or your agent) can ask Unblocked about your Sentry data:

• What code change introduced this Sentry error?
• Which release is associated with the spike in this issue?
• What is the most frequent unresolved error in the API project?
• Which pull request is most likely responsible for this exception?