How to Connect Sentry to an AI Agent
Auth setup
1. Go to Sentry > Settings > Auth Tokens. 2. Create token with scopes: org:read, project:read, project:write, team:read, team:write, event:write. 3. Run: npx @sentry/mcp-server@latest --access-token=YOUR_TOKEN. 4. For Claude Code: set SENTRY_ACCESS_TOKEN in env, then claude mcp add sentry -- npx @sentry/mcp-server@latest.
Key facts
| Base URL | https://unknown |
|---|
| Auth | User Auth Token with specific scopes (org:read, project:read, project:write, team:read, team:write, event:write). OAuth also supported for development. Token passed via --access-token CLI flag or SENTRY_ACCESS_TOKEN environment variable. |
|---|
| Request body | application/json |
|---|
| Rate limit | Follows Sentry API rate limits: varies by endpoint. Most endpoints: 40 requests/second per org. Search operations use LLM internally so may be slower. Monitor X-Sentry-Rate-Limit-Remaining headers. |
|---|
Key endpoints
| Method | Path | Description |
|---|
tool | search_issues | AI-powered search for Sentry issues using natural language |
tool | search_events | AI-powered search for error events |
tool | get_issue_details | Get detailed info about a specific issue |
tool | manage_alerts | Create and configure alert rules |
tool | manage_projects | List and manage Sentry projects and teams |
tool | trace_analysis | Analyze performance traces and transactions |
Quickstart
# Claude Code setup:
claude mcp add sentry -- npx @sentry/mcp-server@latest --access-token=YOUR_SENTRY_TOKEN
# Or via env var:
export SENTRY_ACCESS_TOKEN=sntrys_YOUR_TOKEN
export EMBEDDED_AGENT_PROVIDER=anthropic
claude mcp add sentry -- npx @sentry/mcp-server@latest
# Then ask Claude: 'Show me the top unresolved errors in my project'
Agent pitfalls & tips
- [object Object]
- [object Object]
- [object Object]
- [object Object]
- [object Object]
- [object Object]
- [object Object]
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-06-08. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is Sentry's AEO score?
▼
Sentry has an AEO score of 0.60 and is rated BBB (Basic agent connectivity available). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is Sentry AI-agent-ready?
▼
Sentry is currently connectable for AI agent use. API access is available but no dedicated MCP server has been published yet. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does Sentry compare to other DevOps services?
▼
In the DevOps category, Sentry is rated BBB. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how Sentry compares.
How can I integrate Sentry with an AI agent?
▼
The fastest way to integrate Sentry with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with Sentry?
▼
User Auth Token with specific scopes (org:read, project:read, project:write, team:read, team:write, event:write). OAuth also supported for development. Token passed via --access-token CLI flag or SENTRY_ACCESS_TOKEN environment variable. Setup: 1. Go to Sentry > Settings > Auth Tokens. 2. Create token with scopes: org:read, project:read, project:write, team:read, team:write, event:write. 3. Run: npx @sentry/mcp-server@latest --access-token=YOUR_TOKEN. 4. For Claude Code: set SENTRY_ACCESS_TOKEN in env, then claude mcp add sentry -- npx @sentry/mcp-server@latest.
What are Sentry's API rate limits?
▼
Follows Sentry API rate limits: varies by endpoint. Most endpoints: 40 requests/second per org. Search operations use LLM internally so may be slower. Monitor X-Sentry-Rate-Limit-Remaining headers.