New Relic MCP server for AI apps

What your AI apps can do with New Relic

Run NRQL queries
Review alerts, entities and incidents

New Relic MCP tools

41 tools, taken from the publisher's documentation on 29 October 2026. The server decides what it offers and can add or rename tools at any time; after you connect, Toolstile shows the current list.

Tool	What it does
`convert_time_period_to_epoch_ms`	Convert a relative time period into epoch milliseconds
`get_dashboard`	Get details of one dashboard
`get_entity`	Find entities by GUID or name pattern
`list_related_entities`	List entities directly connected to a given entity
`list_available_new_relic_accounts`	List the account IDs you can access
`list_dashboards`	List an account's dashboards
`search_entity_with_tag`	Find entities by tag key and value
`list_metric_names`	List metric names an entity or account reports
`execute_nrql_query`	Run an NRQL query
`natural_language_to_nrql_query`	Turn a plain-language request into NRQL, run it and return results
`list_alert_conditions`	List the conditions in an alert policy
`search_incident`	List open and closed alert events with filters
`list_alert_policies`	List an account's alert policies
`list_recent_issues`	List an account's open issues
`list_synthetic_monitors`	List synthetic monitors
`list_synthetic_monitor_results`	List a monitor's check runs over a time window
`get_synthetic_check_statistics`	Summarize synthetic check success rates, failures and durations
`analyze_deployment_impact`	Measure how a deployment affected an entity's performance
`generate_alert_insights_report`	Generate an alert intelligence report for an issue
`generate_user_impact_report`	Generate an end-user impact report for an issue
`list_entity_error_groups`	List an entity's error groups from Errors Inbox
`list_change_events`	List an application's change event history
`get_error_statistics`	Aggregate error counts, first and last seen times and trends
`search_errors`	Search raw error events by message, class, HTTP status or trace ID
`analyze_entity_logs`	Find error patterns, anomalies and recurring problems in logs
`analyze_golden_metrics`	Analyze throughput, response time, error rate and saturation
`analyze_threads`	Analyze an entity's thread state, CPU and memory data
`analyze_transactions`	Find slow or error-prone transactions with P95 and P99 latency
`list_garbage_collection_metrics`	List garbage collection and memory metrics for an entity
`list_recent_logs`	List recent logs for an account and entity
`list_entity_performance_risk_groups`	List risk groups from the Performance Risks Inbox
`get_metric_statistics`	Get aggregated values for a metric
`get_log_statistics`	Get log counts, breakdowns by level and attribute, and trends
`get_distributed_trace_details`	Get span attributes, anomalies and span links within a trace
`analyze_github_newrelic_gaps`	Check project files for missing New Relic instrumentation
`search_traces`	Search an entity's traces by duration, errors or backend time (read-only)
`analyze_trace_anomaly`	Find what causes slow, failing or high-volume traces (read-only)
`analyze_service_dependencies`	Map upstream and downstream service dependencies (read-only)
`analyze_kafka_health`	Check Kafka lag, partitions and broker health (read-only)
`analyze_kafka_related_entities`	Map a Kafka entity to its cluster, brokers, topics and services (read-only)
`analyze_kafka_client_metrics`	Analyze Kafka producer and consumer client metrics (read-only)

Suggested access for each AI app

The documentation this list comes from doesn't mark New Relic's tools as read-only or destructive. Read each tool's description and decide per app before allowing it.

Coding agent in Claude Code or Cursor. Allow the read tools so the agent can look things up without stopping, and require approval for tools that change shared data.

Chat or research app in Claude Desktop. Allow reading and searching. Allow writes only where you want the app to act for you.

Unattended agent, such as a scheduled Codex job. No one is watching the session, so keep it narrow: allow what the job needs, require approval for changes and block the rest.

Blocked tools are removed from the tool list an app sees, so it won't try them. Because rules apply per app, the same New Relic connection can be broad in one app and read-only in another, and the credential stays in Toolstile instead of each app's config file.

How it works with Toolstile

Connect once. Add New Relic to a workspace (browser sign-in). Toolstile keeps the credential, so no agent config holds it.
Choose access per app. Give Claude Code every New Relic tool, give Cursor only the read tools, or keep New Relic away from an app entirely.
Share approved accounts. Teammates use the connection without copying tokens, and you can remove access in one place.
Review activity. See which app called which tool and when, so you can tighten access with evidence.

Add the New Relic MCP server to an AI app

Through Toolstile, every AI app uses one gateway entry, whichever servers you connect. In Claude Code:

Shell

claude mcp add --transport http toolstile 'https://toolstile.com/mcp'

Then connect New Relic in your workspace and choose which of its tools that app may use. Client setup covers Codex, Cursor and Claude Desktop.

To connect directly instead, add the New Relic endpoint to each app separately. In Claude Code:

Shell

claude mcp add --transport http newrelic 'https://mcp.newrelic.com/mcp/'

In Cursor's mcp.json:

JSON

{
  "mcpServers": {
    "newrelic": {
      "url": "https://mcp.newrelic.com/mcp/"
    }
  }
}

Some servers accept only clients they have approved, or need a token header. Check the New Relic MCP documentation for what your client needs.

Before you connect

A New Relic account. Sign-in uses your New Relic permissions.

Server details

Detail	Value
Publisher	New Relic
Endpoint	`https://mcp.newrelic.com/mcp/`
Authentication	Browser sign-in
Categories	Development
Tool list	41 tools, observed 29 October 2026 (docs)

New Relic MCP documentation

New Relic MCP server for Claude, Codex and Cursor