Get started

New Relic for AI agents

New Relic is an observability platform that lets engineering teams monitor applications, infrastructure, and customer experience from a single dashboard. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect New RelicSee the 159 actions ↓
DevOps and monitoringAPI keyMCP + RESTnewrelic.com
AUDIT LOG · NEW RELICPOLICY: acme-support
09:41:07 · claude · u_8f2read
new_relic.list_monitors
List Synthetic Monitors✓ allowed · 212ms
09:41:08 · claude · u_8f2read
new_relic.query_error
Query Error✓ allowed · 164ms
09:41:09 · claude · u_8f2write
new_relic.create_user
Create User✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
new_relic.delete_entity
Delete Entity✕ blocked · policy: deny
EVERY NEW RELIC CALL, ON THE RECORD
01 · USE CASES

What agents do in New Relic.

01

Check an alert policy's conditions

Look up what conditions and channels are attached to an alert policy before an on-call review, read-only.

02

Mark a deployment

Create a deployment marker so dashboards show when a release went out.

03

Approve before creating an alert condition

Require approval before creating a new alert condition, since it changes what pages the on-call team.

02 · ACTIONS

159 New Relic actions, graded by risk.

Every New Relic action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

41

Look things up. Allowed by default.

  • new_relic.query_error
    Query Error
  • new_relic.list_monitors
    List Synthetic Monitors
  • new_relic.list_locations
    List Synthetic Monitor Locations
  • new_relic.search_entities
    Search Entities
  • new_relic.get_applications
    Get Applications
  • new_relic.get_lookup_table
    Get Lookup Table
  • new_relic.list_deployments
    List Deployments
  • new_relic.get_synth_monitor
    Get Synthetic Monitor
  • new_relic.get_alert_channels
    Get Alert Channels
  • new_relic.get_alert_policies
    Get Alert Policies
  • new_relic.list_lookup_tables
    List Lookup Tables
  • new_relic.get_app_metric_data
    Get App Metric Data
  • new_relic.get_infra_condition
    Get Infrastructure Alert Condition
  • new_relic.get_alert_conditions
    Get Alert Conditions
  • new_relic.list_nrql_conditions
    List NRQL Alert Conditions
  • new_relic.get_app_metrics_names
    Get Application Metrics Names
+ 25 MORE

write

83

Create and change things. Allow, or ask the user first.

  • new_relic.create_user
    Create User
  • new_relic.send_events
    Send Events
  • new_relic.send_traces
    Send Traces
  • new_relic.update_user
    Update User
  • new_relic.create_monitor
    Create Synthetic Monitor
  • new_relic.update_account
    Update Account
  • new_relic.update_workflow
    Update AI Workflow
  • new_relic.update_workload
    Update Workload
  • new_relic.create_dashboard
    Create Dashboard
  • new_relic.update_dashboard
    Update Dashboard
  • new_relic.add_tags_to_entity
    Add Tags to Entity
  • new_relic.create_ai_workflow
    Create AI Workflow
  • new_relic.create_alert_policy
    Create Alert Policy
  • new_relic.create_lookup_table
    Create Lookup Table
  • new_relic.update_alert_policy
    Update Alert Policy
  • new_relic.update_lookup_table
    Update Lookup Table
+ 67 MORE

destructive

35

Delete, cancel or archive. Ask first, or deny outright.

  • new_relic.delete_entity
    Delete Entity
  • new_relic.delete_monitor
    Delete synthetic monitor
  • new_relic.delete_workload
    Delete Workload
  • new_relic.delete_dashboard
    Delete Dashboard
  • new_relic.delete_alert_policy
    Delete alert policy
  • new_relic.delete_lookup_table
    Delete Lookup Table
  • new_relic.delete_alert_channel
    Delete Alert Channel
  • new_relic.delete_nrql_condition
    Delete NRQL Condition
  • new_relic.delete_policy_channel
    Remove channel from policy
  • new_relic.delete_api_access_keys
    Delete API Access Keys
  • new_relic.delete_infra_condition
    Delete Infrastructure Alert Condition
  • new_relic.delete_alerts_condition
    Delete alerts condition
  • new_relic.remove_entity_condition
    Remove Entity from Alert Condition
  • new_relic.delete_agent_application
    Delete Agent Application
  • new_relic.delete_secure_credential
    Delete Secure Credential
  • new_relic.delete_data_partition_rule
    Delete Data Partition Rule
+ 19 MORE
03 · HOW IT WORKS

New Relic in three steps.

  1. 01Your users connect New RelicThey add their New Relic api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create User” can wait for the user, and “delete Entity” can be denied outright.
  3. 03Any agent can actYour agent calls New Relic through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('new_relic', {
  read: 'allow',
  write: 'ask',        // create_user
  destructive: 'deny',  // delete_entity
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How New Relic connects.

Users add their New Relic api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same New Relic connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use New Relic from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More devops and monitoring apps.

PagerDuty368 actionsServiceNow171 actionsGrafana Cloud118 actionsBetter Stack117 actionsDatadog65 actionsMezmo36 actionsStatuscake30 actionsInstatus15 actions
ALL DEVOPS AND MONITORING APPS →
07 · FAQ

New Relic and Arc0, answered.

Q01

Can I use New Relic with Claude, ChatGPT or Cursor?

Yes. Connect New Relic to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the New Relic actions you allow.

Q02

How do users connect New Relic?

Users add their New Relic api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which New Relic actions can my agent take?

159 in total: 41 read, 83 write and 35 destructive, such as “create User”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in New Relic?

Yes. Actions like “delete Entity” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call New Relic too?

Yes. The same New Relic connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug New Relic into your agent.

Your users connect New Relic once, under your brand. Your agent gets 159 actions behind your policies, with every call on the record.

Connect New RelicBrowse all apps →

Free to build · MCP + REST · Audit log on every plan