Correlate GitHub releases with Sentry issues and PagerDuty incidents. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.
Turn on the Release Radar connector, then ask in plain words. The AI picks the tools.
For on-call engineers and DevOps teams who ship from GitHub and watch errors in Sentry and incidents in PagerDuty.
The AI finds the latest GitHub deployment or release of a repo, lists the unresolved Sentry issues since that time, and names who is on call in PagerDuty.
The AI combines the top unresolved Sentry issues, the triggered and acknowledged PagerDuty incidents and the current on-call person into one short summary.
The AI shows who is on call, the active incidents they inherit, what is live from the latest GitHub deploy and the top Sentry errors. It warns when a fresh deploy and active incidents come at the same time.
The AI reads the latest GitHub deployment of a repo, or the latest release if there is none, with its commit sha and time.
The AI lists the unresolved issues of a Sentry project in a recent time window, so you can see which errors are new or still open.
The login page asks for your GitHub Personal Access Token (required).
Optional: Sentry auth token, Sentry organisation, Sentry project and PagerDuty API token.
GitHub is required. Sentry and PagerDuty are optional — leave them blank to skip those tools. Your tokens are used only to call the APIs on your behalf and to derive a private account id.
Team and Enterprise: an Owner adds the connector for the organization first.
No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"release-radar": {
"url": "https://release-radar.usefulapi.io/mcp"
}
}
} Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"release-radar": {
"type": "http",
"url": "https://release-radar.usefulapi.io/mcp"
}
}
} Run these commands. The second one opens the login page:
Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your GitHub Personal Access Token (required). If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo · $90/yr | 10,000 tool calls / month |
| Pro+ | $39/mo · $390/yr | 100,000 tool calls / month |
Each paid plan covers this Release Radar server only. Ask your AI to run release_radar_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with release_radar_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with release_radar_upgrade before then undoes the cancel. Or write to [email protected].
release_radar_whats_broken_since_last_deployrelease_radar_incident_snapshotrelease_radar_oncall_handoffrelease_radar_github_latest_deployrelease_radar_sentry_recent_issuesrelease_radar_usage_statusrelease_radar_request_featurerelease_radar_upgraderelease_radar_cancel_subscriptionFind what broke since the last deploy. Get a snapshot of what is on fire now. Prepare an on-call handoff briefing. Check when the latest deploy went out. List recent unresolved Sentry issues. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Release Radar. The server calls the Release Radar API with your own Release Radar access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your GitHub Personal Access Token (required). See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your GitHub Personal Access Token (required). If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Release Radar API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Release Radar.
All 5 Release Radar tools are marked read-only.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this Release Radar server only. Cancel any time: your paid plan then runs to the end of the paid period. Run release_radar_usage_status to see how many calls you used.
Ask the AI to run release_radar_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run release_radar_cancel_subscription. Your paid plan continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with release_radar_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.