New Relic MCP integration for AI agents.
Connect AI agents to New Relic through 28 structured actions, including execute nrql query, create alert policy, and delete alert policy. Review authenticati…
- ACTION CONTRACTS
- 28
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the New Relic integration exposes
The New Relic Agent App exposes 28 provider-backed actions for developer tools work. Its current contract lets an authorized agent execute an nrql query against a specific new relic account and return the query results and metadata, create a new relic alert policy using the rest alerts api, and delete a new relic alert policy using the rest alerts api. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected New Relic account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real New Relic capabilities.
Showing 12 of 28 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
execute_nrql_queryREADExecute an NRQL query against a specific New Relic account and return the query results and metadata.
INPUTS: accountId / query / timeout / asyncExecution
create_alert_policyWRITECreate a New Relic alert policy using the REST alerts API.
INPUTS: name / incidentPreference
delete_alert_policyHIGH IMPACTDelete a New Relic alert policy using the REST alerts API.
INPUTS: policyId
create_dashboardWRITECreate a New Relic dashboard with pages and widgets using NerdGraph.
INPUTS: accountId / name / description / permissions / pages
create_dashboard_snapshot_urlWRITEGenerate a snapshot URL for a New Relic dashboard page GUID.
INPUTS: guid
create_deployment_markerWRITECreate a New Relic change-tracking deployment marker for an entity GUID using NerdGraph.
INPUTS: entityGuid / version / user / commit / groupId
create_nrql_conditionWRITECreate a static or baseline NRQL alert condition for a policy using the REST alerts API.
INPUTS: policyId / nrqlCondition
create_secure_credentialWRITECreate a New Relic synthetic secure credential using NerdGraph.
INPUTS: accountId / key / value / description
create_synthetics_simple_monitorWRITECreate a New Relic ping monitor by using the syntheticsCreateSimpleMonitor mutation.
INPUTS: accountId / name / uri / period / status
delete_dashboardHIGH IMPACTDelete a New Relic dashboard by its entity GUID.
INPUTS: guid
delete_nrql_conditionHIGH IMPACTDelete a New Relic NRQL alert condition using the REST alerts API.
INPUTS: conditionId
delete_secure_credentialHIGH IMPACTDelete a New Relic synthetic secure credential using NerdGraph.
INPUTS: accountId / key
INPUT CONTRACTS
Know what the action needs before it runs.
execute_nrql_query
accountIdREQUIRED- The account ID to query.
queryREQUIRED- The NRQL query string.
timeoutOPTIONAL- The query timeout in seconds.
asyncExecutionOPTIONAL- Whether to request asynchronous execution.
create_alert_policy
nameREQUIRED- The alert policy name.
incidentPreferenceOPTIONAL- The incident preference for the new policy.
delete_alert_policy
policyIdREQUIRED- A string or numeric value returned by New Relic.
create_dashboard
accountIdREQUIRED- The account ID that will own the dashboard.
nameREQUIRED- The dashboard name.
descriptionOPTIONAL- The optional dashboard description.
permissionsREQUIRED- The dashboard permission setting.
pagesREQUIRED- Dashboard page definitions.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Execute Nrql Query
Execute an NRQL query against a specific New Relic account and return the query results and metadata. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
execute_nrql_queryControl Create Alert Policy
Create a New Relic alert policy using the REST alerts API. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_alert_policyVerify with Create Alert Policy
Create a New Relic alert policy using the REST alerts API. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
create_alert_policySAFETY BOUNDARY
Operate New Relic with explicit limits
- Authorize New Relic with API key and grant only the provider access required by the selected actions.
- 17 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_alert_policy`, `delete_dashboard`, and `delete_nrql_condition` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in New Relic rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the New Relic task completed successfully.
CONNECTION MODEL
API key
New Relic user key sent with the Api-Key header for NerdGraph and supported REST API requests. Manage user keys from the official API keys page: https://docs.newrelic.com/docs/apis/intro-apis/new-relic-api-keys/.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 11
- WRITE SIGNALS
- 12
- HIGH IMPACT
- 5
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by New Relic.