Sentry MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 6 Jun 2026.
MCP server for Sentry — error tracking, issues, releases, events, and projects for AI assistants.
The author archived this repository on GitHub, meaning it is no longer maintained.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sentry-mcp-server -e 'SENTRY_AUTH_TOKEN=<SENTRY_AUTH_TOKEN>' -- npx -y sentry-mcp-server
{
"mcpServers": {
"sentry-mcp-server": {
"command": "npx",
"args": [
"-y",
"sentry-mcp-server"
],
"env": {
"SENTRY_AUTH_TOKEN": "<SENTRY_AUTH_TOKEN>"
}
}
}
}
[mcp_servers.sentry-mcp-server]
command = "npx"
args = ["-y", "sentry-mcp-server"]
env = { SENTRY_AUTH_TOKEN = "<SENTRY_AUTH_TOKEN>" }
{
"mcpServers": {
"sentry-mcp-server": {
"command": "npx",
"args": [
"-y",
"sentry-mcp-server"
],
"env": {
"SENTRY_AUTH_TOKEN": "<SENTRY_AUTH_TOKEN>"
}
}
}
}
{
"servers": {
"sentry-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sentry-mcp-server"
],
"env": {
"SENTRY_AUTH_TOKEN": "<SENTRY_AUTH_TOKEN>"
}
}
}
}
Put your own value in place of
<SENTRY_AUTH_TOKEN> (Sentry auth token from Settings → Auth Tokens. Needs org:read, project:read, event:read, issue:read, issue:write scopes).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
SENTRY_BASE_URL (Sentry API base URL. Defaults to https://sentry.io/api/0/. Override for self-hosted Sentry).
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
Organizations, projects, releases, and issues through the Sentry API.
MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
Build, run and monitor Integrate.io ETL and Reverse ETL pipelines from AI assistants.
MCP server for Ordali memory: SQLite-backed project memory and governance traces.
MCP server for diagnosing Apache Spark event-log performance issues and comparing runs.
MCP server — read-only log access for AI assistants, without giving AI shell access.
Scout Monitoring data for AI assistants: slow endpoints, traces, N+1 queries, and errors.
Answers built from our own checks of this server.