New Relic MCP server
18 operations0 webhooks
Read New Relic applications and metrics, search entities, list alert issues, manage alert policies and NRQL alert conditions, record deployment markers, and run NRQL queries through NerdGraph.
Try New Relic with your agent
Connect New Relic, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in New Relic on my account, then run one read-only example and show me the result.
New Relic tools and triggers
Tools are what your agent can do in New Relic through Corsair's MCP server. Triggers are the New Relic events a routine can start from.
Alerts
- ConditionsRead-only
List the APM, browser and mobile conditions in one policy; external service, synthetic and NRQL conditions are separate endpoints and are not covered
alerts.conditions
- Create Nrql ConditionWrite
Add a static NRQL alert condition to a policy: the query, thresholds and how long they must hold
alerts.createNrqlCondition
- Create PolicyWrite
Create an alert policy and choose whether incidents roll up per policy, per condition, or per condition and signal
alerts.createPolicy
- Delete Nrql ConditionDestructive
Delete a NRQL alert condition; New Relic has no restore call
alerts.deleteNrqlCondition
- Delete PolicyDestructive
Delete an alert policy and the conditions attached to it; New Relic has no restore call
alerts.deletePolicy
- Nrql ConditionsRead-only
List the static NRQL conditions in one policy, with their query, thresholds and signal settings
alerts.nrqlConditions
- PoliciesRead-only
List alert policies with their incident rollup preference
alerts.policies
- Update Nrql ConditionWrite
Replace a NRQL condition, e.g. to enable it or move its threshold; send the whole condition, since a partial body is refused
alerts.updateNrqlCondition
- Update PolicyWrite
Rename an alert policy or change how its incidents roll up; both fields are sent, since New Relic replaces the policy
alerts.updatePolicy
Applications
- GetRead-only
Read one application by id with the same health, reporting and summary block
applications.get
- ListRead-only
List applications with their health colour, whether they are reporting, and the summary metrics the UI shows
applications.list
Entities
- GetRead-only
Read up to 25 entities by GUID with their type, reporting state, alert severity and tags
entities.get
- SearchRead-only
Search monitored entities (services, hosts, browser apps, dashboards, monitors, alert conditions) with a filter such as type = 'APPLICATION'
entities.search
Accounts
- ListRead-only
List the accounts this key can reach, with the ids NRQL and issues take
accounts.list
Change Tracking
- Create DeploymentDestructive
Record a deployment marker (version, commit, changelog) on an entity; markers cannot be deleted
changeTracking.createDeployment
Issues
- ListRead-only
List alert issues for an account, filtered by state, priority, entity or time window
issues.list
Metrics
- GetRead-only
Read metric timeslices for an application over a time window, or one averaged value per metric with summarize
metrics.get
Query
- NrqlRead-only
Run a NRQL query against one account through NerdGraph and return its rows and the time window New Relic actually ran over
query.nrql
Connect New Relic to Claude, ChatGPT or Cursor
- 1
Connect New Relic in Corsair
Add your New Relic API key once in Corsair. Corsair stores the credential encrypted and makes the New Relic API calls for your agent, so it never goes into a prompt or a config file. Connect New Relic
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs New Relic. On a ChatGPT personal plan, connect New Relic here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, New Relic's read and write operations run right away and its 3 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/newrelic, add the New Relic plugin, and connect with an API key. Then call methods like corsair.newrelic.api.accounts.list() from your app. Corsair keeps each tenant isolated.
Yes. New Relic requires an API key from your New Relic account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit New Relic, GitHub, Notion, Stripe, and the rest. Trigger New Relic from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for read New Relic applications and metrics, search entities, list alert issues, manage alert policies and NRQL alert conditions, record deployment markers, and run NRQL queries through NerdGraph. Common builds include sync jobs, admin tooling, and agents that call New Relic APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per New Relic API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/newrelic in the open repo. When New Relic ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your New Relic data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store New Relic data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put New Relic on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 3 destructive New Relic operations. You can change a link's mode at hub.corsair.dev/me.