Skip to content
actionlake
Start free

Connectors · Observability & analytics

New Relic MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to New Relic and the rest of your systems. It gives your agent 199 New Relic actions (69 reads, 90 writes and 40 that wait for a confirmation) and holds the New Relic credential itself, so the agent never does. It paces New Relic's limits and records every call.

Connect New Relic freeSee pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "newrelic.alert_violations.list",  intent: "check which New Relic account is connected"}# List alert violations · read · 1 upstream call
  • 199actionsin one signed file
  • 69readlook, never change
  • 90writecreate and update
  • 40wait for a yesdestructive, confirmed first

Set up

Connect New Relic in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect New Relic.

    API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyNew Relic user API key
    • api_hostWhere your New Relic lives: your api host
    account { op: "connections.requirements", service: "newrelic" }
# free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "newrelic.alert_violations.list" }# list alert violations · read · 1 upstream callcheck { action: "newrelic.users.user_create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

New Relic at a glance

Sign-in
API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Setup fields
api_host
Limits we pace to
1,000 calls a minute, per connection
API covered
New Relic API nerdgraph+rest_v2api.newrelic.com
Built from
New Relic's documentation, read 19 September 2026api.newrelic.comdocs.newrelic.comdocs.newrelic.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
68 of 69 reads, for up to an hour; a write clears what it affects
Ready-made plans
8 in the store
Shared entities
3, so ask can line New Relic up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in New Relic.

199 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 69readlook, never change
  • 90writecreate and update
  • 40destructivewait for a confirmation

  1. Monitoring

    199

    69 read · 90 write · 40 destructive

    List alert violations · List users · List APM applications · List alert incidents

Top actions

The New Relic API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 96 of New Relic's 101 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
newrelic.alert_violations.listList alert violationsLists alert threshold violations over a time window.readmonitoring.alert.list51 connectors
newrelic.users.listList usersLists the users in an authentication domain, with their groups.readidentity.user.list474 connectors
newrelic.applications.listList APM applicationsLists the APM applications reporting to this account.readmonitoring.service.list12 connectors
newrelic.alert_incidents.listList alert incidentsLists alert incidents for this account, newest first.readmonitoring.alert.list51 connectors
newrelic.users.user_createCreate a userCreates a user in an authentication domain.writeidentity.user.create262 connectors
newrelic.plugins.listList pluginsLists the Plugins (legacy product) registered in this account.readmonitoring.service.list12 connectors
newrelic.workloads.workload_createCreate a workloadCreates a workload, a named collection of entities whose health is rolled up together.writemonitoring.service.create11 connectors
newrelic.browser_applications.createCreate a browser applicationCreates a standalone browser application and returns its monitoring key and loader script.writemonitoring.service.create11 connectors
newrelic.users.user_deleteDelete a userRemoves a user from the organisation.destructiveidentity.user.delete253 connectors
newrelic.alert_conditions.listList APM metric alert conditionsLists the APM, browser and mobile metric conditions attached to one alert policy.readmonitoring.monitor.list32 connectors
newrelic.alert_nrql_conditions.listList NRQL alert conditionsLists the NRQL conditions attached to one alert policy.readmonitoring.monitor.list32 connectors
newrelic.alert_channels.listList notification channelsLists the alert notification channels in this account.readmonitoring.notification_channel.list18 connectors

Try it

Prompts to paste into Claude.

Each one names the New Relic actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which New Relic alerts are open right now? Group them by service.

    callsnewrelic.alert_violations.list

  2. Planwrite

    Stand up an alert policy with a NRQL condition and a channel in New Relic.

    callsnewrelic.alert_policies.listnewrelic.nrql.querynewrelic.alert_policies.createnewrelic.alert_nrql_conditions.createnewrelic.alert_policy_channels.update+1 more

  3. Planwrite

    Record a deployment then watch the application for fallout in New Relic.

    callsnewrelic.applications.getnewrelic.deployments.createnewrelic.applications.metric_datanewrelic.alert_incidents.listnewrelic.deployments.list

  4. Writewrite

    Create a user in New Relic. Show me exactly what you will send before you save it.

    callsnewrelic.users.user_create

The plan store

Ready-made plans for New Relic.

8 plans in the store. Install one and your agent runs it by name; the reply says which connections are still missing. A schedule can run a plan on a timetable. There are no triggers or webhooks, by design.

  1. Report the slowest hosts behind an application

    Use it when An application is slow overall and you need to know which of its hosts is dragging the average down.

    Effect
    read
    Steps
    4 · loops
    Needs
    application id
    Install
    newrelic-slow-hosts-report

  2. Tag every entity matching an entity search

    Use it when A group of entities found by an entity search query needs a common tag such as team, environment or cost centre.

    A person decidesAdd the supplied tags to match count New Relic entities matching the search query.

    Effect
    write
    Steps
    4 · loops
    Needs
    query and tags
    Install
    newrelic-tag-entities-by-search

  3. Triage open alert incidents and acknowledge them

    Use it when An on-call engineer wants every open New Relic incident acknowledged and a list of what is currently firing.

    Effect
    write
    Steps
    4 · loops
    Install
    newrelic-triage-open-incidents

  4. Create a synthetic monitor and alert on its failures

    Use it when A public endpoint needs uptime checking from New Relic synthetics together with alerting when the checks fail.

    Effect
    write
    Steps
    5
    Needs
    account id, monitor name, url and policy id
    Install
    newrelic-synthetic-monitor-rollout

  5. Record a deployment then watch the application for fallout

    Use it when A release has just gone out and you want it marked in New Relic and checked for immediate fallout.

    Effect
    write
    Steps
    6
    Needs
    application id and revision
    Install
    newrelic-deploy-marker-and-watch

  6. Stand up an alert policy with a NRQL condition and a channel

    Use it when A new service needs alerting from scratch: a policy, a NRQL condition and somewhere for the notification to go.

    Effect
    write
    Steps
    6
    Needs
    account id, policy name, nrql and threshold
    Install
    newrelic-new-alert-policy-with-nrql

  7. Retire an application that has stopped reporting

    Use it when An application has stopped reporting and you want it removed from New Relic after a human signs off.

    A person decidesPermanently delete the New Relic application name (id application id), which currently reports number of items hosts.

    Effect
    destructive
    Steps
    5
    Needs
    application id
    Install
    newrelic-retire-stale-application

  8. Mute alerts for a maintenance window

    Use it when Planned maintenance is about to start and alerts for the affected account should be silenced only for its duration.

    A person decidesSilence New Relic alerts on account account id with muting rule rule name for a one hour maintenance window.

    Effect
    destructive
    Steps
    6
    Needs
    account id, rule name and condition
    Install
    newrelic-mute-alerts-for-maintenance
install a plan
account { op: "plans.install", slug: "newrelic-slow-hosts-report" }
# then ask for it by name; a schedule can run it on a timetable

Governance for New Relic

Destructive actions wait for a yes.

40 New Relic actions are destructive. The first 10:

  • Delete a usernewrelic.users.user_delete
  • Delete an APM applicationnewrelic.applications.delete
  • Delete a workloadnewrelic.workloads.workload_delete
  • Delete an agent application (NerdGraph)newrelic.agent_applications.agent_application_delete
  • Delete a key transaction (NerdGraph)newrelic.key_transactions_nerdgraph.key_transaction_delete
  • Delete an APM metric alert conditionnewrelic.alert_conditions.delete
  • Delete an NRQL alert conditionnewrelic.alert_nrql_conditions.delete
  • Delete a Plugins alert conditionnewrelic.alert_plugins_conditions.delete
  • Delete a Synthetics alert conditionnewrelic.alert_synthetics_conditions.delete
  • Delete an external service alert conditionnewrelic.alert_external_service_conditions.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

donewrelic.applications.deleteconfirm_policy: human

Delete an APM application?

intent: the user asked me to delete an APM application

run suspended · waiting for a named person · key newrelic-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "newrelic-agent",  allowed_actions: ["newrelic.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "newrelic.users.user_delete", approver: "[email protected]" },    { match: "newrelic.applications.delete", approver: "[email protected]" },    { match: "newrelic.workloads.workload_delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to New Relic only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What New Relic costs on actionlake.

Every New Relic action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call New Relic refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 199 New Relic actions
  • 199actions pageeach page of a long list is one call
  • 68reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every New Relic action.

199 actions by area: the id your agent calls, what it does, and its effect.

Monitoring199
  • newrelic.accounts.listList accessible accountsread
  • newrelic.agent_applications.agent_application_create_browserCreate a browser application (NerdGraph)write
  • newrelic.agent_applications.agent_application_deleteDelete an agent application (NerdGraph)destructive
  • newrelic.agent_applications.agent_application_settings_updateUpdate agent application settings (NerdGraph)write
  • newrelic.alert_channels.createCreate a notification channelwrite
  • newrelic.alert_channels.deleteDelete a notification channeldestructive
  • newrelic.alert_channels.listList notification channelsread
  • newrelic.alert_conditions.createCreate an APM metric alert conditionwrite
  • newrelic.alert_conditions.deleteDelete an APM metric alert conditiondestructive
  • newrelic.alert_conditions.listList APM metric alert conditionsread
  • newrelic.alert_conditions.updateUpdate an APM metric alert conditionwrite
  • newrelic.alert_conditions_nerdgraph.alerts_condition_deleteDelete an alert condition (NerdGraph)destructive
  • newrelic.alert_entity_conditions.addAdd an entity to an alert conditionwrite
  • newrelic.alert_entity_conditions.listList alert conditions on an entityread
  • newrelic.alert_entity_conditions.removeRemove an entity from an alert conditiondestructive
  • newrelic.alert_events.listList alert eventsread
  • newrelic.alert_external_service_conditions.createCreate an external service alert conditionwrite
  • newrelic.alert_external_service_conditions.deleteDelete an external service alert conditiondestructive
  • newrelic.alert_external_service_conditions.listList external service alert conditionsread
  • newrelic.alert_external_service_conditions.updateUpdate an external service alert conditionwrite
  • newrelic.alert_incidents.acknowledgeAcknowledge an alert incidentwrite
  • newrelic.alert_incidents.closeClose an alert incidentwrite
  • newrelic.alert_incidents.listList alert incidentsread
  • newrelic.alert_location_failure_conditions.createCreate a multi-location Synthetics conditionwrite
  • newrelic.alert_location_failure_conditions.deleteDelete a multi-location Synthetics conditiondestructive
  • newrelic.alert_location_failure_conditions.listList multi-location Synthetics conditionsread
  • newrelic.alert_location_failure_conditions.updateUpdate a multi-location Synthetics conditionwrite
  • newrelic.alert_nrql_conditions.createCreate an NRQL alert conditionwrite
  • newrelic.alert_nrql_conditions.deleteDelete an NRQL alert conditiondestructive
  • newrelic.alert_nrql_conditions.listList NRQL alert conditionsread
  • newrelic.alert_nrql_conditions.updateUpdate an NRQL alert conditionwrite
  • newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_baseline_createCreate a baseline NRQL alert condition (NerdGraph)write
  • newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_baseline_updateUpdate a baseline NRQL alert condition (NerdGraph)write
  • newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_static_createCreate a static NRQL alert condition (NerdGraph)write
  • newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_condition_static_updateUpdate a static NRQL alert condition (NerdGraph)write
  • newrelic.alert_nrql_conditions_nerdgraph.alerts_nrql_conditions_searchSearch NRQL alert conditions (NerdGraph)read
  • newrelic.alert_plugins_conditions.createCreate a Plugins alert conditionwrite
  • newrelic.alert_plugins_conditions.deleteDelete a Plugins alert conditiondestructive
  • newrelic.alert_plugins_conditions.listList Plugins alert conditionsread
  • newrelic.alert_plugins_conditions.updateUpdate a Plugins alert conditionwrite
  • newrelic.alert_policies.createCreate an alert policywrite
  • newrelic.alert_policies.deleteDelete an alert policydestructive
  • newrelic.alert_policies.listList alert policiesread
  • newrelic.alert_policies.updateUpdate an alert policywrite
  • newrelic.alert_policies_nerdgraph.alerts_policies_searchSearch alert policies (NerdGraph)read
  • newrelic.alert_policies_nerdgraph.alerts_policy_createCreate an alert policy (NerdGraph)write
  • newrelic.alert_policies_nerdgraph.alerts_policy_deleteDelete an alert policy (NerdGraph)destructive
  • newrelic.alert_policies_nerdgraph.alerts_policy_updateUpdate an alert policy (NerdGraph)write
  • newrelic.alert_policy_channels.deleteDetach a notification channel from a policydestructive
  • newrelic.alert_policy_channels.updateAttach notification channels to a policywrite
  • newrelic.alert_synthetics_conditions.createCreate a Synthetics alert conditionwrite
  • newrelic.alert_synthetics_conditions.deleteDelete a Synthetics alert conditiondestructive
  • newrelic.alert_synthetics_conditions.listList Synthetics alert conditionsread
  • newrelic.alert_synthetics_conditions.updateUpdate a Synthetics alert conditionwrite
  • newrelic.alert_violations.listList alert violationsread
  • newrelic.api_access_keys.api_access_key_getGet an API access keyread
  • newrelic.api_access_keys.createCreate API access keyswrite
  • newrelic.api_access_keys.deleteDelete API access keysdestructive
  • newrelic.api_access_keys.updateUpdate API access keyswrite
  • newrelic.application_hosts.getGet an application hostread
  • newrelic.application_hosts.listList hosts for an applicationread
  • newrelic.application_hosts.metric_dataGet metric data for an application hostread
  • newrelic.application_hosts.metric_namesList metric names for an application hostread
  • newrelic.application_instances.getGet an application instanceread
  • newrelic.application_instances.listList instances for an applicationread
  • newrelic.application_instances.metric_dataGet metric data for an application instanceread
  • newrelic.application_instances.metric_namesList metric names for an application instanceread
  • newrelic.applications.deleteDelete an APM applicationdestructive
  • newrelic.applications.getGet an APM applicationread
  • newrelic.applications.listList APM applicationsread
  • newrelic.applications.metric_dataGet metric data for an applicationread
  • newrelic.applications.metric_namesList metric names for an applicationread
  • newrelic.applications.updateUpdate an APM applicationwrite
  • newrelic.browser_applications.createCreate a browser applicationwrite
  • newrelic.browser_applications.listList browser applicationsread
  • newrelic.change_tracking.deployment_marker_createRecord a deployment (change tracking)write
  • newrelic.cloud.configure_integrationConfigure a cloud integrationwrite
  • newrelic.cloud.disable_integrationDisable a cloud integrationwrite
  • newrelic.cloud.link_accountLink a cloud accountwrite
  • newrelic.cloud.linked_accounts_listList linked cloud accountsread
  • newrelic.cloud.rename_accountRename a linked cloud accountwrite
  • newrelic.cloud.unlink_accountUnlink a cloud accountdestructive
  • newrelic.components.getGet a plugin componentread
  • newrelic.components.listList plugin componentsread
  • newrelic.components.metric_dataGet metric data for a plugin componentread
  • newrelic.components.metric_namesList metric names for a plugin componentread
  • newrelic.dashboards.dashboard_createCreate a dashboardwrite
  • newrelic.dashboards.dashboard_deleteDelete a dashboarddestructive
  • newrelic.dashboards.dashboard_getGet a dashboardread
  • newrelic.dashboards.dashboard_snapshot_url_createCreate a dashboard snapshot URLwrite
  • newrelic.dashboards.dashboard_updateUpdate a dashboardwrite
  • newrelic.deployments.createRecord a deployment markerwrite
  • newrelic.deployments.deleteDelete a deployment markerdestructive
  • newrelic.deployments.listList deployment markersread
  • newrelic.entities.entity_getGet an entity by GUIDread
  • newrelic.entities.entity_searchSearch entitiesread
  • newrelic.entities.get_batchGet several entities by GUIDread
  • newrelic.groups.group_createCreate a user groupwrite
  • newrelic.groups.group_deleteDelete a user groupdestructive
  • newrelic.groups.group_updateUpdate a user groupwrite
  • newrelic.groups.group_users_addAdd users to groupswrite
  • newrelic.groups.group_users_removeRemove users from groupsdestructive
  • newrelic.groups.listList user groupsread
  • newrelic.insights.queryRun an NRQL query through the Insights query APIread
  • newrelic.key_transactions.getGet a key transactionread
  • newrelic.key_transactions.listList key transactionsread
  • newrelic.key_transactions_nerdgraph.key_transaction_createCreate a key transaction (NerdGraph)write
  • newrelic.key_transactions_nerdgraph.key_transaction_deleteDelete a key transaction (NerdGraph)destructive
  • newrelic.key_transactions_nerdgraph.key_transaction_updateUpdate a key transaction (NerdGraph)write
  • newrelic.labels.deleteDelete a labeldestructive
  • newrelic.labels.listList labelsread
  • newrelic.labels.upsertCreate or update a labelwrite
  • newrelic.log_data_partition_rules.listList log data partition rulesread
  • newrelic.log_data_partition_rules.log_data_partition_rule_createCreate a log data partition rulewrite
  • newrelic.log_data_partition_rules.log_data_partition_rule_deleteDelete a log data partition ruledestructive
  • newrelic.log_data_partition_rules.log_data_partition_rule_updateUpdate a log data partition rulewrite
  • newrelic.log_obfuscation.expression_createCreate a log obfuscation expressionwrite
  • newrelic.log_obfuscation.expression_deleteDelete a log obfuscation expressiondestructive
  • newrelic.log_obfuscation.expression_updateUpdate a log obfuscation expressionwrite
  • newrelic.log_obfuscation.expressions_listList log obfuscation expressionsread
  • newrelic.log_obfuscation.rule_createCreate a log obfuscation rulewrite
  • newrelic.log_obfuscation.rule_deleteDelete a log obfuscation ruledestructive
  • newrelic.log_obfuscation.rule_updateUpdate a log obfuscation rulewrite
  • newrelic.log_obfuscation.rules_listList log obfuscation rulesread
  • newrelic.log_parsing_rules.listList log parsing rulesread
  • newrelic.log_parsing_rules.log_grok_testTest a Grok pattern against log linesread
  • newrelic.log_parsing_rules.log_parsing_rule_createCreate a log parsing rulewrite
  • newrelic.log_parsing_rules.log_parsing_rule_deleteDelete a log parsing ruledestructive
  • newrelic.log_parsing_rules.log_parsing_rule_updateUpdate a log parsing rulewrite
  • newrelic.mobile_applications.getGet a mobile applicationread
  • newrelic.mobile_applications.listList mobile applicationsread
  • newrelic.mobile_applications.metric_dataGet metric data for a mobile applicationread
  • newrelic.mobile_applications.metric_namesList metric names for a mobile applicationread
  • newrelic.muting_rules.listList alert muting rulesread
  • newrelic.muting_rules.muting_rule_createCreate an alert muting rulewrite
  • newrelic.muting_rules.muting_rule_deleteDelete an alert muting ruledestructive
  • newrelic.muting_rules.muting_rule_getGet an alert muting ruleread
  • newrelic.muting_rules.muting_rule_updateUpdate an alert muting rulewrite
  • newrelic.nerdgraph.queryRun any NerdGraph GraphQL queryread
  • newrelic.notification_channels.listList notification channelsread
  • newrelic.notification_channels.notification_channel_createCreate a notification channelwrite
  • newrelic.notification_channels.notification_channel_deleteDelete a notification channeldestructive
  • newrelic.notification_channels.notification_channel_updateUpdate a notification channelwrite
  • newrelic.notification_destinations.listList notification destinationsread
  • newrelic.notification_destinations.notification_destination_createCreate a notification destinationwrite
  • newrelic.notification_destinations.notification_destination_deleteDelete a notification destinationdestructive
  • newrelic.notification_destinations.notification_destination_updateUpdate a notification destinationwrite
  • newrelic.nrql.queryRun an NRQL queryread
  • newrelic.nrql_drop_rules.createCreate NRQL drop ruleswrite
  • newrelic.nrql_drop_rules.deleteDelete NRQL drop rulesdestructive
  • newrelic.nrql_drop_rules.listList NRQL drop rulesread
  • newrelic.plugins.getGet a pluginread
  • newrelic.plugins.listList pluginsread
  • newrelic.service_levels.listList service level indicatorsread
  • newrelic.service_levels.service_level_createCreate a service level indicatorwrite
  • newrelic.service_levels.service_level_deleteDelete a service level indicatordestructive
  • newrelic.service_levels.service_level_updateUpdate a service level indicatorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_broken_links_createCreate a Synthetics broken links monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_broken_links_updateUpdate a Synthetics broken links monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_cert_check_createCreate a Synthetics certificate check monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_cert_check_updateUpdate a Synthetics certificate check monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_deleteDelete a Synthetics monitordestructive
  • newrelic.synthetics_monitors.synthetics_monitor_script_api_createCreate a Synthetics scripted API monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_script_api_updateUpdate a Synthetics scripted API monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_script_browser_createCreate a Synthetics scripted browser monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_script_browser_updateUpdate a Synthetics scripted browser monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_simple_browser_createCreate a Synthetics simple browser monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_simple_browser_updateUpdate a Synthetics simple browser monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_simple_createCreate a Synthetics ping monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_simple_updateUpdate a Synthetics ping monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_step_createCreate a Synthetics step monitorwrite
  • newrelic.synthetics_monitors.synthetics_monitor_step_updateUpdate a Synthetics step monitorwrite
  • newrelic.synthetics_monitors.synthetics_script_getGet a Synthetics monitor scriptread
  • newrelic.synthetics_monitors.synthetics_steps_getGet a Synthetics step monitor's stepsread
  • newrelic.synthetics_private_locations.synthetics_private_location_createCreate a Synthetics private locationwrite
  • newrelic.synthetics_private_locations.synthetics_private_location_deleteDelete a Synthetics private locationdestructive
  • newrelic.synthetics_private_locations.synthetics_private_location_purge_queuePurge a Synthetics private location queuedestructive
  • newrelic.synthetics_private_locations.synthetics_private_location_updateUpdate a Synthetics private locationwrite
  • newrelic.synthetics_secure_credentials.synthetics_secure_credential_createCreate a Synthetics secure credentialwrite
  • newrelic.synthetics_secure_credentials.synthetics_secure_credential_deleteDelete a Synthetics secure credentialdestructive
  • newrelic.synthetics_secure_credentials.synthetics_secure_credential_updateUpdate a Synthetics secure credentialwrite
  • newrelic.tags.addAdd tags to an entitywrite
  • newrelic.tags.deleteDelete tag keys from an entitydestructive
  • newrelic.tags.replaceReplace all tags on an entitywrite
  • newrelic.tags.tag_values_deleteDelete specific tag values from an entitydestructive
  • newrelic.users.listList usersread
  • newrelic.users.user_createCreate a userwrite
  • newrelic.users.user_current_getGet the authenticated userread
  • newrelic.users.user_deleteDelete a userdestructive
  • newrelic.users.user_updateUpdate a userwrite
  • newrelic.workflows.listList alert workflowsread
  • newrelic.workflows.workflow_createCreate an alert workflowwrite
  • newrelic.workflows.workflow_deleteDelete an alert workflowdestructive
  • newrelic.workflows.workflow_updateUpdate an alert workflowwrite
  • newrelic.workloads.workload_createCreate a workloadwrite
  • newrelic.workloads.workload_deleteDelete a workloaddestructive
  • newrelic.workloads.workload_duplicateDuplicate a workloadwrite
  • newrelic.workloads.workload_getGet a workloadread
  • newrelic.workloads.workload_updateUpdate a workloadwrite

Questions

The New Relic MCP server, answered.

Is there a New Relic MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 199 New Relic actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by New Relic.

What do I need to connect New Relic?

New Relic user API key. Plus your api host. The free call account { op: "connections.requirements", service: "newrelic" } lists exactly what to paste.

Can an AI agent delete or change things in New Relic?

Only if its key allows it, and only with an explicit confirmation. 40 New Relic actions are destructive, including delete a user, delete an APM application and delete a workload. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my New Relic API limit?

actionlake paces every call to the limits in the New Relic service file: 1,000 calls a minute per connection. Repeated reads are answered from cache (68 New Relic actions can be), which never reaches New Relic.

What does a New Relic action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (199 New Relic actions page). Cache hits, searches, dry runs and calls New Relic refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which New Relic API does it cover?

The New Relic API nerdgraph+rest_v2 at api.newrelic.com by default, or the base URL set when you connect. It is built from New Relic's documentation as read on 19 September 2026. 199 actions in 1 area, each one in the signed service file (version 1.0.0).

Does actionlake keep my New Relic data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your New Relic credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

More connectors like New Relic

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by New Relic; the name is the vendor's own. Counts are from the New Relic service file, version 1.0.0.

Give your agent New Relic today.

Connect New Relic freeSee pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.