# Sentry for AI agents. Managed auth, ready-made tools.

> Triage errors in your users' Sentry organizations: list issues, read stack traces, and resolve or assign them.

- Page: https://www.agent200.com/tools/sentry/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `sentry`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-15

## Instructions for AI agents

Connector: Sentry, through Agent200. In code: "sentry".
What it does: Triage errors in your users' Sentry organizations: list issues, read stack traces, and resolve or assign them.
Page: https://www.agent200.com/tools/sentry/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Sentry's own page, through the authorization link Agent200 returns. Never ask a user for a Sentry password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: sentry_list_projects, sentry_list_issues, sentry_get_issue, sentry_get_latest_event. Write tools: sentry_update_issue. Name "sentry" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/sentry/framework/claude/
   https://www.agent200.com/tools/sentry/framework/chatgpt/
   https://www.agent200.com/tools/sentry/framework/claude-code/
   https://www.agent200.com/tools/sentry/framework/muse/
   https://www.agent200.com/tools/sentry/framework/grok-bot/
   https://www.agent200.com/tools/sentry/framework/openai-dots/
   https://www.agent200.com/tools/sentry/framework/claude-duet/
   https://www.agent200.com/tools/sentry/framework/hermes-agent/
   https://www.agent200.com/tools/sentry/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Sentry connector, your agent triages errors in each user's own Sentry organization through Agent200: it lists new issues, reads the stack trace of the latest event and resolves, ignores or assigns issues. Every user connects their own account through managed OAuth.

Sentry is an application monitoring service that groups errors and performance problems into issues, with the stack traces and context needed to fix them.

## Sentry tools

- **List projects** (`sentry_list_projects`, read): List the projects in an organization.
- **List issues** (`sentry_list_issues`, read): List a project's issues, filtered by a search query and time range.
- **Get an issue** (`sentry_get_issue`, read): Read an issue's details, status and event counts.
- **Get the latest event** (`sentry_get_latest_event`, read): Read the most recent event of an issue, with its stack trace and tags.
- **Update an issue** (`sentry_update_issue`, write): Resolve, ignore or assign an issue.

## Limits you can set

**Turn single tools on or off.** Let your agent read issues and events, and switch off `sentry_update_issue` if it should report but never change an issue's status.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Sentry

Each end user authorizes their own Sentry account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Sentry account, once.
const connection = await agent200
  .user("user_123")
  .connect("sentry");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Sentry tools

Name the user, the model and the tools. The model decides which Sentry tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "What are the top unresolved errors in the API project this week",
    tools: ["sentry"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Sentry's own page. You never see or store their Sentry password.

**What access is requested.** Sentry lists the scopes on its consent screen, such as reading projects and events, and writing to issues when the agent updates them. The agent sees only the organizations and projects that user can already open.

## Example requests

- "What are the top unresolved errors in the API project this week"
- "Show me the stack trace for the latest checkout crash"
- "Assign the TypeError in the web app to me"
- "Resolve the issues fixed in today's release"

## Guides: Sentry with your AI framework

- [Sentry + Claude](https://www.agent200.com/tools/sentry/framework/claude.md): Connect Sentry to Claude through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Sentry + ChatGPT](https://www.agent200.com/tools/sentry/framework/chatgpt.md): ChatGPT cannot send an API key to a custom MCP server, so this guide builds Sentry into your own agent with OpenAI's models and the Agent200 SDK.
- [Sentry + Claude Code](https://www.agent200.com/tools/sentry/framework/claude-code.md): Have Claude Code build a Sentry agent with the Agent200 SDK: managed OAuth, ready-made tools and one API key.
- [Sentry + Muse](https://www.agent200.com/tools/sentry/framework/muse.md): Connect Sentry to Muse through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Sentry + Grok Bot](https://www.agent200.com/tools/sentry/framework/grok-bot.md): Connect Sentry to Grok Bot through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Sentry + OpenAI Dots](https://www.agent200.com/tools/sentry/framework/openai-dots.md): Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Sentry agent with OpenAI's models and the Agent200 SDK.
- [Sentry + Claude Duet](https://www.agent200.com/tools/sentry/framework/claude-duet.md): Connect Sentry to Claude Duet through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Sentry + Hermes Agent](https://www.agent200.com/tools/sentry/framework/hermes-agent.md): Connect Sentry to Hermes Agent through Agent200's MCP server: managed OAuth, ready-made tools and one API key.
- [Sentry + OpenClaw](https://www.agent200.com/tools/sentry/framework/openclaw.md): Connect Sentry to OpenClaw through Agent200's MCP server: managed OAuth, ready-made tools and one API key.

## FAQ

### Who handles the Sentry OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Sentry.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Sentry connection, never another user's. It cannot reach anything the user or Sentry has not authorized.

### Can I limit what my agent can do in Sentry?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [GitHub](https://www.agent200.com/tools/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/tools/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/tools/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/tools/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
