How is this different from connecting New Relic MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the New Relic MCP API changes?

We track the New Relic MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different New Relic tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in New Relic?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the New Relic MCP server myself?

No. TrustGate connects to the New Relic MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to New Relic directly.

Connect New Relic MCP to your AI agents, securely.

Q: Is New Relic MCP secure?

The server itself exposes 38 tools, and some of them can write to your New Relic account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches New Relic.

One secured endpoint for every New Relic call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try New Relic MCP now

What your agents can ask once New Relic MCP is connected.

Select the tools your AI agents can call

38 tools from the New Relic MCP schema.

Showing 38 tools

get_entityreadFetches New Relic entities by GUID or search by name pattern.
list_related_entitiesreadLists entities one hop away from a given entity GUID.
search_entity_with_tagreadSearches for entities using a specific tag key and value.
list_available_new_relic_accountsreadLists all account IDs available to the user.
list_dashboardsreadLists all dashboards for a New Relic account.
get_dashboardreadFetches details about a specific dashboard.
list_metric_namesreadDiscovers all available metric names reported by an entity or account.
convert_time_period_to_epoch_msreadConverts a time period such as last 30 minutes to epoch milliseconds.
execute_nrql_queryreadExecutes an NRQL query against NRDB.
natural_language_to_nrql_queryreadConverts a natural language request into an NRQL query, executes it and returns the results. Requires OAuth and advanced compute.
list_alert_policiesreadLists alert policies for the specified account, optionally filtering by policy name.
list_alert_conditionsreadLists alert condition details for a specific alert policy.
search_incidentreadLists all alert events, both open and close, with flexible filtering.
list_recent_issuesreadLists all open issues in New Relic for the specified account.
list_synthetic_monitorsreadLists all synthetic monitors that check service availability and performance.
list_synthetic_monitor_resultsreadReturns individual synthetic check run rows with timings, errors and locations over a time window.
get_synthetic_check_statisticsreadAggregates synthetic check success rates, failure counts and duration percentiles across monitors or locations.
analyze_deployment_impactreadAnalyzes the performance impact of a deployment on a specific entity. Requires OAuth and advanced compute.
generate_alert_insights_reportreadGenerates an alert intelligence analysis report for a specific issue. Requires OAuth and advanced compute.
generate_user_impact_reportreadGenerates an end-user impact analysis report for a specific issue. Requires OAuth and advanced compute.
list_entity_error_groupsreadFetches error groups for a specific entity from the Errors Inbox within a time window.
list_change_eventsreadLists a history of change events for the application identified by its entity GUID.
get_error_statisticsreadComputes aggregate error counts, first and last seen timestamps and time-series trends from TransactionError events.
search_errorsreadReturns raw error events matching filters such as message, class, HTTP status or trace ID.
analyze_golden_metricsreadAnalyzes golden metrics: throughput, response time, error rate and saturation.
analyze_transactionsreadAnalyzes transactions for an entity within a time window, identifying slow and error-prone transactions with P95 and P99 latency.
analyze_entity_logsreadAnalyzes application logs to identify error patterns, anomalous behaviour and recurring issues.
analyze_threadsreadAnalyzes thread metric data for an entity, including thread state, CPU usage and memory consumption.
analyze_kafka_metricsreadAnalyzes Kafka metrics including consumer lag, producer throughput, message latency and partition balance.
list_garbage_collection_metricsreadLists garbage collection and memory metrics for an account and entity.
list_recent_logsreadLists recent logs for the specified account and entity GUID.
get_log_statisticsreadReturns aggregate log counts, breakdowns by level and attribute, and trends over a time window.
get_metric_statisticsreadFetches aggregated metric values such as average, sum, percentiles and rate for a metric.
get_distributed_trace_detailsreadReturns full span attributes, anomalies and span links for a specific entity or span within a trace.
list_entity_performance_risk_groupsreadFetches performance risk groups for an entity from the Performance Risks Inbox within a time window.
search_tracesreadSearches the traces of a specific entity within a time window, ranked by duration, error count or backend time.
analyze_trace_anomalyreadAnalyzes traces of an entity to identify the transaction or error class responsible for slow, failing or high-volume traces.
analyze_service_dependenciesreadAnalyzes an entity's service dependencies, mapping upstream and downstream connections and flagging unhealthy ones.

What New Relic MCP exposes

New Relic MCP groups its 38 tools into 6 categories, each with a suggested starting policy.

All 38 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Discovery	Entities, related entities, tags, accounts, dashboards, metric names and time conversion	Read	Limit to intended accounts
Data Access	NRQL execution against NRDB and natural language to NRQL	Read	Watch query cost; natural language tools consume advanced compute
Alerting	Alert policies, conditions, incidents, open issues and synthetic monitors	Read	Limit access to alerting data
Incident Response	Deployment impact, alert and user impact reports, error groups, change events and error search	Read	Treat error payloads as potentially sensitive
Performance Analytics	Golden metrics, transactions, threads, Kafka, garbage collection, logs and distributed traces	Read	Scope to the entities in use
Preview	Trace search, trace anomaly analysis and service dependency mapping	Read	Preview features; evaluate before relying on them

Connect New Relic MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect New Relic
Find New Relic in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow New Relic MCP or block it. You allow the exact tools each agent can call, one by one.

New Relic MCP	38 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 38 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is New Relic MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	New Relic MCP38 documented tools.
Coding assistants	Connection & credentialsper user	Performance Analytics11 tools
Internal copilots	Tool access policiesdeny by default	Discovery8 tools
Workflow automations	Request & response inspectioninline	Alerting7 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools12 tools