What is Sentry?
Sentry is a dev & code tool. With OSP.net, your AI agent connects to it directly so it can act on your behalf instead of just answering questions about it.
What your OSP agent can do with Sentry
- Search and read issues, events and stack traces
- Summarize what broke, where and how often
- Look across projects and releases your token can see
How to connect Sentry
- In Sentry, open Settings → Account → API → Auth Tokens and create a new token. sentry.io → Auth Tokens
- Grant at minimum these scopes (add event:write only if you want the agent resolving/assigning issues):
- Copy the token, paste it here and Connect. Sentry's docs cover the agent toolset. Sentry Docs: Sentry MCP
Security: Stack traces can contain user data from your apps — scope the token to the orgs/projects you're comfortable exposing to the agent. Revoke any time from the same page.
Who uses Sentry with OSP
These roles commonly connect Sentry to their OSP agent:
Related dev & code integrations
Frequently asked questions
- Can OSP.net connect to Sentry?
- Yes. Sentry is a native OSP.net integration — you bring your own Sentry key or token, paste it in your dashboard, and your agent restarts live.
- What can my OSP agent do with Sentry?
- Your agent investigates errors and performance issues straight from your Sentry projects. Specifically: Search and read issues, events and stack traces; Summarize what broke, where and how often; Look across projects and releases your token can see.
- Is Sentry a native integration or via the gateway?
- Sentry is a native, baked-in integration. You connect it with your own credentials, which are stored in an encrypted vault and injected only at runtime.
- Is my Sentry data secure with OSP.net?
- Yes. Your Sentry credentials live in an encrypted secrets vault, are injected only at container runtime, and are never written to disk in plaintext or used to train any model. Each customer runs in a fully isolated instance.