Release Radar MCP server

Correlate GitHub releases with Sentry issues and PagerDuty incidents. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.

Claude claude.ai · Desktop

  1. Open Customize → Connectors, then click + Add → Add custom connector.
  2. Enter the name Release Radar and this URL, then click Add:
    https://release-radar.usefulapi.io/mcp
  3. Claude opens the login page: enter your GitHub Personal Access Token (required).
  4. In a chat, click + → Connectors and turn on Release Radar.

Team and Enterprise: an Owner adds the connector for the organization first.

Claude Code

Run this command, then run /mcp in Claude Code to log in:

claude mcp add --transport http release-radar https://release-radar.usefulapi.io/mcp

Cursor

Add to Cursor or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "release-radar": {
      "url": "https://release-radar.usefulapi.io/mcp"
    }
  }
}

VS Code

Add to VS Code or add this to .vscode/mcp.json:

{
  "servers": {
    "release-radar": {
      "type": "http",
      "url": "https://release-radar.usefulapi.io/mcp"
    }
  }
}

Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.

live9 toolsFree 100 tool calls / monthPro $9/mo · $90/yr

Before you connect

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.

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.

Example prompts

Turn on the Release Radar connector, then ask in plain words. The AI picks the tools.

Tools 9

ToolTypeWhat it does
whats_broken_since_last_deploywrite
What's broken since the last deploy?
COMPOSITE. Finds the latest GitHub deployment/release for a repo, then queries Sentry for unresolved issues SINCE that deploy's timestamp (the deploy time drives the Sentry window), then looks up who's currently on-call in PagerDuty — and synthesizes one situational-awareness object. Degrades gracefully: if Sentry or PagerDuty creds are absent it returns what it can plus a note. GitHub is required (it's the anchor).
incident_snapshotwrite
Current incident snapshot
COMPOSITE. A right-now on-call picture: top unresolved Sentry issues + active (triggered/acknowledged) PagerDuty incidents + who's currently on-call, fused into one snapshot with a human summary. Each service degrades independently if its creds are missing.
oncall_handoffwrite
On-call handoff briefing
COMPOSITE. A start-of-shift briefing for whoever is currently on call, fusing all three services: (a) PagerDuty current on-call + any active (triggered/acknowledged) incidents they're inheriting, (b) the GitHub deployment/release that most recently shipped (what's live), and (c) Sentry's top unresolved errors. Correlates them into one object — including a heads-up when a fresh deploy coincides with active incidents (a likely culprit). Degrades gracefully: every service is optional; whatever's unconfigured or failing is named in `notes` and the briefing still returns. Never crashes.
github_latest_deploywrite
Latest GitHub deploy/release
Low-level building block: the latest GitHub deployment for a repo (falls back to the latest release), returning sha + timestamp. Used internally by whats_broken_since_last_deploy. GitHub: GET /repos/{owner}/{repo}/deployments.
sentry_recent_issueswrite
Recent unresolved Sentry issues
Low-level building block: unresolved Sentry issues over a relative window. Sentry: GET /api/0/projects/{org}/{project}/issues/?query=is:unresolved.
release_radar_usage_statusmeta
Usage status (free-tier meter)
Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter.
release_radar_request_featuremeta
Request a missing feature
Tell usefulapi that the user needs something the Release Radar tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter.
release_radar_upgrademeta
Upgrade to Pro (unlimited)
Subscribe to the Pro plan for UNLIMITED Release Radar tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter.
release_radar_cancel_subscriptionmeta
Cancel the Pro subscription
Cancel the caller's Release Radar Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run release_radar_upgrade later to undo the cancel before the period ends. Does not count against the meter.

Pricing

PlanPriceLimit
Free$0100 tool calls / month
Pro$9/mo · $90/yrUnlimited

Pro covers this Release Radar server only. Subscribe with release_radar_upgrade (it returns a Stripe Checkout link). Cancel any time with release_radar_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running release_radar_upgrade before then undoes the cancel. Or write to [email protected].

FAQ

Is this an official Release Radar product?

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.

What do I need to connect?

The login page asks for your GitHub Personal Access Token (required). See Before you connect for where to find it.

Do I put my Release Radar key or an Authorization header in the client config?

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.

How do you keep my Release Radar credentials?

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.

Can the AI change my Release Radar data?

Yes, if you approve it. 5 of the 5 Release Radar tools can create or change data. The other 0 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.

What does it cost?

The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Release Radar server only. Run release_radar_usage_status to see how many calls you used.

How do I subscribe or cancel?

Ask the AI to run release_radar_upgrade: it returns a Stripe Checkout link. To cancel, run release_radar_cancel_subscription. Pro continues to the end of the paid period.

What if a Release Radar tool that I need is missing?

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.

Which AI clients can I use?

Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, 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.

More Developer Tools & Infrastructure MCP servers

AblyApiFlashbunny.netCivoCodecovCodemagicCrowdinDepotdeSECDNSimpleDubEstuary FlowExoscaleGeoapifyHetzner CloudHypertuneInngestKindeKinstaKisiKnackLaravel ForgeLocalazyMapTilerNorthflankNS1packagecloudRunCloudScalingoSpinupWPSvixTailscaleTrigger.devUnkeyUpCloudWakaTimeWeblate

All Developer Tools & Infrastructure servers →