AgentArmorHQ
Sign in

toolkit

MCP server · GitHub · ★ 949 · graded 2026-10-23Source linked

Agentic tooling for Sentry

No outside reports on file

This connector gives an AI direct access to your Sentry account and all error data stored there; treat the connection like giving access to production logs, and only enable it with restrictive permissions and careful monitoring.

Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Toolkit helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsRequires API key or tokenREVIEW
  • Package sourceGitHub (getsentry/toolkit)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/getsentry/toolkit ↗

All setup options ↓

Check this skillWatch it in my stackCompareAdd to allowlistREADME badgeView project

About Toolkit

This is a connector that links AI agents to Sentry, a tool used by developers to track and fix software errors. It likely lets AI assistants read error reports, manage Sentry projects, and possibly trigger actions within Sentry's system.

Who it’s for

Developers and teams using Sentry for error monitoring who want to automate tasks or let AI agents help analyze crashes and bugs. It's designed to work with AI systems that support MCP (Model Context Protocol), like Claude.

Alternatives

  • Datadog monitoring connector: Similar error tracking but for the Datadog platform
  • New Relic MCP server: Error and performance monitoring via New Relic's API
  • Generic logging connectors: General-purpose tools that link AI agents to logs without Sentry lock-in

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for installation and configuration steps. The repository is at https://github.com/getsentry/toolkit (opens external site); check there for MCP server setup instructions specific to your environment.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100
GitHub stars
949
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

  • Sentry account access: The connector needs credentials to connect to your Sentry account and can read sensitive error data, stack traces, and user information captured in crash reports
  • Broad error visibility: An AI agent gets access to all errors and logs your system sends to Sentry, which might include passwords, API keys, or personal data accidentally logged
  • Action execution: If the connector allows actions, a compromised agent could create false alerts, delete error data, or modify project settings
  • Malicious context injection: Attackers could craft error messages that trick the AI into executing unintended commands when processing logs
  • Credential leakage: If API tokens are stored insecurely or logged, they could be exposed to other systems or users

How to lower the risk

Least-privilege permissions

  • Create a Sentry API token with read-only access if possible
  • Limit the token to specific Sentry organizations or projects, not all of them

Network isolation

  • Run the MCP connector on a dedicated machine or container with limited network access
  • Block outbound traffic except to Sentry's official endpoints

Monitoring

  • Log all requests the connector makes to Sentry
  • Set up alerts if unusual volumes of data are read or actions are triggered

Red flags to watch for

  • Unexpected API calls or large data exports from Sentry
  • Errors or logs appearing that match attacker-controlled input
  • The connector requesting higher permission levels than initially granted

Questions

How do I install Toolkit?

Toolkit does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/getsentry/toolkit.

Are there security reports about Toolkit?

No reports found for this package in our research (last checked 2026-10-29). Toolkit currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include sentry account access, broad error visibility, action execution.

Is Toolkit actively maintained?

Toolkit has 949 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/getsentry/toolkit before pinning it in production.

What are alternatives to Toolkit?

Notable alternatives to Toolkit include Datadog monitoring connector (Similar error tracking but for the Datadog platform), New Relic MCP server (Error and performance monitoring via New Relic's API), Generic logging connectors (General-purpose tools that link AI agents to logs without Sentry lock-in). You can also compare Toolkit side by side with other MCP servers in the Related tools section on this page.

Community questions about Toolkit

README badge and team notes

Maintain or use Toolkit? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Toolkit

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Toolkit](https://agentarmorhq.com/api/badge/getsentry-toolkit)](https://agentarmorhq.com/skills/getsentry-toolkit)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/getsentry-toolkit"><img src="https://agentarmorhq.com/api/badge/getsentry-toolkit" alt="AgentArmorHQ Risk Grade for Toolkit" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "getsentry-toolkit"

Share with your security lead

Need sign-off to use toolkit? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: toolkit
- **Listing URL:** https://agentarmorhq.com/skills/getsentry-toolkit
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 949 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (getsentry/toolkit)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/getsentry/toolkit
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
getsentry
Source code
github.com/getsentry/toolkit
Est. context load
~1.2k tokens / turn (~7 tool schemas, 0.57% of 200k context)
Popularity
949 GitHub stars
Last updated
2026-10-29
Last graded
2026-10-23

Community

Discussions for Toolkit

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Toolkit helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude