sentry-mcp
by getsentry·★ 691·Score 53
MCP server for Sentry integration with LLMs, providing error tracking and debugging capabilities.
Overview
Sentry's MCP server is designed for human-in-the-loop coding agents, focusing on developer workflows and debugging use cases. It acts as middleware to the upstream Sentry API, optimized for coding assistants like Cursor and Claude Code. The server supports both remote and stdio transport modes, with AI-powered search tools requiring an LLM provider (OpenAI or Anthropic).
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this server when you're already using Sentry for error tracking and want to integrate it directly with AI coding assistants for debugging and issue resolution.
When NOT to choose this
Don't choose this if you're not using Sentry or need read/write access to your error tracking system beyond what Sentry provides.
Tools this server exposes
12 tools extracted from the READMEsearch_eventsSearch Sentry events using natural language
search_issuesSearch Sentry issues using natural language
create_issueCreate a new Sentry issue
get_issueRetrieve details of a specific Sentry issue
update_issueUpdate an existing Sentry issue
list_projectsList available Sentry projects
create_github_issueCreate a GitHub issue from a Sentry issue
query_postgresQuery PostgreSQL database with Sentry data
use_sentryGeneral purpose Sentry interaction tool
get_organizationGet details of a Sentry organization
get_teamGet details of a Sentry team
search_tracesSearch Sentry traces using natural language
Note: Inferred tool names from the documentation that mentions AI-powered search tools (search_events, search_issues) and other capabilities (create_issue, get_issue, etc.). Some tool names are mentioned in the context of functionality rather tha
Comparable tools
Installation
Installation
Claude Code Plugin
claude plugin marketplace add getsentry/sentry-mcp
claude plugin install sentry-mcp@sentry-mcpMCP Configuration
{
"mcpServers": {
"sentry": {
"command": "npx",
"args": ["@sentry/mcp-server"],
"env": {
"SENTRY_ACCESS_TOKEN": "your-token",
"EMBEDDED_AGENT_PROVIDER": "openai",
"OPENAI_API_KEY": "sk-..."
}
}
}
}FAQ
- What LLM providers are supported?
- OpenAI and Anthropic are supported for AI-powered search tools. You need to configure API keys for the provider you choose.
- Can I use this with self-hosted Sentry?
- Yes, use the stdio transport with the --host flag and provide your Sentry host URL. You may need to add --insecure-http for non-TLS deployments.
Compare sentry-mcp with
Last updated · Auto-generated from public README + GitHub signals.