Sentry MCP server
Last verified: 2026-09
List and inspect Sentry issues.
Official reference Developer tools Needs a secret Claude Desktop, Cursor, Windsurf, Claude Code, VS Code
What it does
Lists and inspects Sentry issues for an org you authenticate. Read-only enough for 'what broke in prod'; an org-wide token still sees every project.
It sits in Developer tools: Split this category in two.
Good for
- List recent issues on a project you already know is noisy.
- Open one issue and read the stack trace in the chat.
- Ask 'what broke after the last deploy' with Sentry as the source.
- Keep the token read-only so the model cannot resolve or delete issues.
Tools
- list issues / get issue — Inspect errors and event data.
Config (Claude Desktop / Cursor / Windsurf)
Paste the JSON below. Same mcpServers shape. Replace placeholder paths and secrets.
Windows paths look like C:\\Users\\you\\project, not /path/to.
Host-side steps →
Claude Desktop
| OS | Config file |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json
(usually C:\Users\<you>\AppData\Roaming\Claude\) |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Cursor
| Scope | macOS / Linux | Windows |
|---|---|---|
| This project | .cursor/mcp.json in the repo root | |
| This user | ~/.cursor/mcp.json |
%USERPROFILE%\.cursor\mcp.json |
Windsurf
| OS | Config file |
|---|---|
| macOS / Linux | ~/.codeium/windsurf/mcp_config.json |
| Windows | %USERPROFILE%\.codeium\windsurf\mcp_config.json |
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sentry"
],
"env": {
"SENTRY_AUTH_TOKEN": "...",
"SENTRY_ORG": "your-org"
}
}
}
}
Windsurf remote MCP: use serverUrl instead of url if the block below is HTTP.
One-liner: npx -y @modelcontextprotocol/server-sentry
Secrets it wants: SENTRY_AUTH_TOKEN, SENTRY_ORG
How to get started
- Create an auth token with event:read on one project if you can.
- Set SENTRY_AUTH_TOKEN and SENTRY_ORG.
- Ask for the newest unresolved issue.
Access risk
Issue payloads can contain user data, tokens, and request bodies. Treat the token as prod access.
When to skip it
Skip it if you are not debugging production errors in that chat.
Vs alternatives
| Server | Official? | Needs a secret? | Best for |
|---|---|---|---|
| Sentry | Yes | Yes | List and inspect Sentry issues. |
| Datadog | No | Yes | Metrics, logs, and monitors. |
| PostHog | No | Yes | Events and insights from PostHog. |
More in Developer tools
FAQ
Which token?
A Sentry auth token scoped to one org/project, issue read. Full org admin is unnecessary.
Can it mark issues resolved?
If the token allows writes. Start read-only.
Sentry or Datadog?
Sentry is application errors. Datadog is infra/metrics/logs. Different questions.
Official?
Anthropic reference server talking to Sentry's API.