XferOps Sentry

ReviewAudited by ClawScan on May 10, 2026.

Overview

This is a coherent Sentry investigation skill with no malicious behavior shown, but it requires a Sentry API token and runs an external npm MCP server.

Before installing, verify that you trust @sentry/mcp-server, consider pinning its version, use the narrowest Sentry token that works, and secure any token stored in MCP config or Secrets Manager. The artifacts do not show destructive or hidden behavior.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A compromised or changed npm package could run with local user permissions and receive the configured Sentry token.

Why it was flagged

The setup runs an external npm MCP server without a pinned version. This is central to the stated purpose, but package provenance and future version changes are outside the reviewed artifact.

Skill content
npx -y @sentry/mcp-server --skills=inspect,triage
Recommendation

Install only from a trusted npm source, pin a known-good version if possible, and review the package before giving it credentials.

What this means

The agent/MCP server can query Sentry data available to the token, which may include production incident details and user data in events.

Why it was flagged

The skill requires delegated Sentry account access. This is expected for querying Sentry, but the token can expose whatever organizations, projects, issues, and events it is allowed to read.

Skill content
Set `SENTRY_ACCESS_TOKEN` to a Sentry User Auth Token with API access.
Recommendation

Use a least-privilege Sentry token limited to the needed organization/projects, rotate it regularly, and avoid placing broad personal tokens in shared configs.

What this means

Sensitive Sentry issue or event details may be brought into agent context or AI-assisted triage outputs.

Why it was flagged

The skill routes Sentry access through an MCP server exposed to the agent. This is the intended integration, but the artifact does not describe detailed data-boundary or redaction behavior for issue/event contents.

Skill content
"mcpServers": { "sentry": { "command": "npx", "args": ["-y", "@sentry/mcp-server", "--skills=inspect,triage"], "env": { "SENTRY_ACCESS_TOKEN": "your-token-here" } } }
Recommendation

Confirm the MCP server’s privacy behavior, avoid querying unnecessary sensitive events, and redact secrets or personal data before sharing outputs.