Sentry MCP server, with a policy gate.
Triage Sentry issues from Claude or Cursor through one audited endpoint. Gentkey proxies the official Sentry MCP server with scoped, revocable write access.
https://app.gentkey.com/mcpclaude.ai (web & mobile) · Claude Code · Cursor · any MCP clientWhat’s free, what needs a grant.
Reads: Sentry's tools ship write-gated until a curated read set lands; self-labeling isn't trusted.
Writes: Grant mcp-sentry.write and the connector opens; revoke it and the next call is denied.
Gentkey proxies the official Sentry MCP server (https://mcp.sentry.dev/mcp) — you get the vendor’s own tools, with custody, gating, and audit added in front.
| Grant | What it governs |
|---|---|
mcp-sentry.write | Every tool the official Sentry server exposes — triage actions and reads too, until a curated read set lands |
Connect once, use everywhere.
Sign in at gentkey.com, add Sentry (oauth), then point each client at your endpoint. Every client completes a standard OAuth flow and lands in your Gentkey — your connections, nobody else’s.
claude.ai (web & mobile)
- Settings → Connectors
- Add custom connector
- Paste
https://app.gentkey.com/mcpand finish the OAuth prompt
Claude Code
claude mcp add --transport http \
gentkey https://app.gentkey.com/mcpCursor
// .cursor/mcp.json
{
"mcpServers": {
"gentkey": { "url": "https://app.gentkey.com/mcp" }
}
}Things agents do with Sentry here.
- What are the top unresolved errors in production this week?
- Show me the stack trace for the most frequent new issue.
- Assign the checkout NullPointerException to me and mark it in progress.
- Which release introduced the spike in 500s?
Custody, gating, and audit — built in.
The model never sees a credential
Your Sentry token is encrypted at rest and injected server-side at call time. Your stored credential never enters a context window.
Writes need a grant
Anything that changes state needs a capability you granted explicitly — revoke it and the next call is denied.
A trail you can act on
Every decision is attributed to the agent that made it — allowed, denied, or denied by constraint.
Fair questions.
Which agent resolved that issue?
The audit log answers that by construction: every Sentry call through Gentkey is attributed to the agent that made it, with the tool, sanitized arguments, and the allow/deny verdict.
What happens when an agent calls a Sentry write tool it hasn't been granted?
The call is denied at the gateway — nothing reaches Sentry — and the denial is recorded in the audit log along with the grant that would have authorized it, so you can decide deliberately instead of finding out later.
Where are my credentials stored?
Encrypted at rest (AES-256-GCM) on Gentkey's server and injected server-side at call time. No credential you store with Gentkey ever enters a model's context window or an agent's config file.
Can I use this from claude.ai's free plan?
Yes — and it's the strongest case for a gateway: free claude.ai accounts currently get a single custom connector, so pointing that one slot at Gentkey puts every connector you've linked behind it.
How do I revoke an agent's access?
Revoke the grant (the next write is denied) or revoke the agent's tokens entirely in one click. Other agents and their grants are untouched — no shared key to rotate.
Is Gentkey affiliated with Sentry?
No. Gentkey is an independent MCP gateway. Trademarks belong to their owners; where an official Sentry MCP server exists, Gentkey proxies it and adds custody, gating, and audit on top.
Often connected together.
Cut Sentry a smaller key.
Sign in, connect Sentry, and grant your first scoped capability in under a minute.