Sentry MCP server providing orgs, projects, and issues search via Model Context Protocol.
Sentry MCP server exists for a simple reason — assistants are far more useful when they can act on Sentry directly instead of describing what you should do. Sentry MCP server providing orgs, projects, and issues search via Model Context Protocol.
Sentry MCP server provides tools for working with Sentry organizations, projects, and issues directly from Claude Code, Code CLI, and other MCP clients.
Once Sentry is connected, these are the calls the assistant has available:
service_info — Status information: url, tokenPresent, timezone, readOnly, versionsentry_organizations — List organizations with pagination (cursor/perPage); brief mode by defaultsentry_projects — List projects in an organization; supports query, pagination, brief modesentry_issues — List issues with filters: query, environments, statsPeriod or since/until, project; pagination supportedsentry_issue_latest_event — Get latest event for an issue (brief summary by default)sentry_issues_latest_events_batch — Get latest events for multiple issues with safe concurrencysentry_issues_details_batch — Get issue details for multiple issues with safe concurrencyThe server ships on npm as @vitalyostanin/sentry-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need 2 environment variables: SENTRY_URL, SENTRY_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
SENTRY_URL — Sentry base URL - SENTRY_TOKEN — Sentry auth token (Bearer) - SENTRY_TIMEZONE — optional, defaults to Europe/Moscow - SENTRY_READ_ONLY — optional, defaults to true - SENTRY_HTTP_TIMEOUT_MS — optional request timeout in ms (default 10000)This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Sentry's toolset — service_info, sentry_organizations, sentry_projects and 4 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Sentry's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| service_info | Status information: url, tokenPresent, timezone, readOnly, version. |
| sentry_organizations | List organizations with pagination (cursor/perPage); brief mode by default. |
| sentry_projects | List projects in an organization; supports query, pagination, brief mode. |
| sentry_issues | List issues with filters: query, environments, statsPeriod or since/until, project; pagination supported. |
| sentry_issue_latest_event | Get latest event for an issue (brief summary by default). |
| sentry_issues_latest_events_batch | Get latest events for multiple issues with safe concurrency. |
| sentry_issues_details_batch | Get issue details for multiple issues with safe concurrency. |
## Configuration for Claude Code CLI
```json
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": ["-y", "@vitalyostanin/sentry-mcp@latest"],
"env": {
"SENTRY_URL": "https://sentry.example.com",
"SENTRY_TOKEN": "<token>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
SENTRY_URL — Sentry base URL - SENTRY_TOKEN — Sentry auth token (Bearer) - SENTRY_TIMEZONE — optional, defaults to Europe/Moscow - SENTRY_READ_ONLY — optional, defaults to true - SENTRY_HTTP_TIMEOUT_MS — optional request timeout in ms (default 10000)| Variable | Description | Required |
|---|---|---|
| SENTRY_URL | Endpoint or connection string the server talks to. | Yes |
| SENTRY_TOKEN | Credential the server authenticates with. | Yes |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.