Sentry connector for AI agents

CALL ANY TOOL

List and inspect issues, pull stack traces and events, and resolve or assign errors, each call scoped to the authenticated engineer's project access.

sentrymcp_analyze_issue_with_seer

Analyze issue with seer

Use Sentry's Seer AI to analyze a production error and get root cause analysis with specific code fixes. Provides file locations, line numbers, and concrete fix recommendations. Results are cached — subsequent calls return instantly.

Parameters

Name

Type

Required

Description

instruction

string

Optional

Optional custom instruction for the AI analysis, to focus on specific aspects of the issue.

issueId

string

Optional

The Issue ID. Example: 'PROJECT-1Z43'. Required if issueUrl is not provided.

issueUrl

string

Optional

Full URL to the Sentry issue. Example: 'https://my-org.sentry.io/issues/PROJECT-1Z43'. Use instead of organizationSlug + issueId.

organizationSlug

string

Optional

The organization's slug. Use the find_organizations tool to list available organizations.

regionUrl

string

Optional

The region URL for the organization. For sentry.io, typically 'https://us.sentry.io'. Omit for self-hosted.

sentrymcp_execute_sentry_tool

Execute sentry tool

sentrymcp_find_organizations

Find organizations

sentrymcp_find_projects

Find projects

sentrymcp_get_sentry_resource

Get sentry resource

sentrymcp_search_events

Search events

sentrymcp_search_issues

Search issues

sentrymcp_search_sentry_tools

Search sentry tools

sentrymcp_update_issue

Update issue

Build your Agent

The same per-user auth pattern wires into every agent framework.

import { ScalekitClient } from "@scalekit-sdk/node";
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["sentrymcp"], toolNames: ["sentry_issues_list", "sentry_issue_get", "sentry_events_list"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm: new ChatOpenAI({ model: "gpt-4o" }), tools });
await agent.invoke({ messages: [{ role: "user", content: "Triage unresolved payments errors" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const openai = new OpenAI();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["sentrymcp"], toolNames: ["sentry_issues_list", "sentry_issue_get", "sentry_events_list"] },
  pageSize: 100,
});

const res = await openai.responses.create({
  model: "gpt-4o",
  input: "Show top unresolved errors in payments",
  tools,
});

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const anthropic = new Anthropic();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["sentrymcp"], toolNames: ["sentry_issues_list", "sentry_issue_get", "sentry_events_list"] },
  pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  tools,
  messages: [{ role: "user", content: "Resolve the checkout NullPointer issue" }],
});

import { LlmAgent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["sentrymcp"], toolNames: ["sentry_issues_list", "sentry_issue_get", "sentry_events_list"] },
  pageSize: 100,
});

const agent = new LlmAgent({ name: "sentry_agent", model: "gemini-2.0-flash", tools });
await agent.run("List new issues in the latest release");

Try these prompts

Paste any prompt into your agent to start working Sentry issues.

Triage & resolve

Copy the prompt

Copied

What are the top unresolved errors in the payments service this week?

Copy the prompt

Copied

Resolve the checkout NullPointer issue and assign it to me.

Copy the prompt

Copied

Ignore the noisy rate-limit 429 issue in the api project.

Investigate

Copy the prompt

Copied

Pull the latest stack trace for issue PROJ-1421.

Copy the prompt

Copied

Show me events for the TimeoutError over the last 24 hours.

Copy the prompt

Copied

Which release introduced the checkout regression?

Report & recall

Copy the prompt

Copied

List all projects I have access to.

Copy the prompt

Copied

Summarise new issues since the last deploy.

Copy the prompt

Copied

How many events did the payments timeout error get this week?

SEE HOW AUTH WORKS

The engineer authorises Sentry once. Every later agent call uses their token with project scope enforced.

1

Authorize

Your user connects

Sentry MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Sentry MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Sentry MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Sentry MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other monitoring connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Test other agents

See the same per-user auth pattern across other monitoring connectors.

ENGINEERING

DevOps assistant agent

Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.

ENGINEERING

Engineering standup agent

Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.

ENGINEERING

Slack triage agent

Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.

ENGINEERING

Auto-release notes agent

Group merged GitHub PRs into structured release notes, publish the page to Notion, and announce the release in Slack.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Sentry token looks fine in a demo. In production every resolve and assign logs as one service account, so you lose track of who acted. Scalekit resolves the real engineer's credential per call.

// shared token
resolve → monitoring_bot

// scalekit
resolve → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Sentry today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Sentry as the user or as a shared key?

As the user. Scalekit resolves the authenticated engineer's own Sentry credential at request time, so every issue read, resolve, and assignment is attributed to them in Sentry's audit log rather than a shared monitoring bot.

Where is the Sentry token stored?

In an AES-256 encrypted vault, namespaced per tenant. Tokens are fetched only at the moment of a tool call, refreshed automatically before expiry, and revocable from a single dashboard, never exposed to the model or the prompt.

Can I limit what the agent is allowed to do in Sentry?

Yes. Pass a toolNames filter to listScopedTools to expose only the actions you want, for example read-only issue listing without resolve or delete. Scalekit also runs a scope check before each API call.

What happens when a user revokes Sentry access?

The credential is invalidated at the next tool call, which fails closed rather than falling back to a shared token. Other users are unaffected, and the revocation is recorded in the audit trail.

Can the agent modify production issues, or only read them?

That is your choice. Expose only sentry_issues_list and sentry_issue_get for a read-only triage agent, or add sentry_issue_update to let it resolve and assign. The write scope is enforced per user, so an engineer can only change issues in projects they already own.

Sentry MCP

Tools your monitoring agent reaches for on Sentry, scoped per user.