MCP.Market

New Relic MCP Server

by Meet-Bhalodiya·io.github.Meet-Bhalodiya/newrelic-mcp·v1.0.0

Secure, self-hosted New Relic observability and administration tools for MCP clients

C63/100grade C
What users say
No reviews yet
Be the first
Safety scan
C63/100

full report

Adoption
Growing

0 stars56 downloads/wk

Reviews

Write one

Nobody has reviewed New Relic MCP Server yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

New Relic MCP Server tools (100, 49 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • access_grants_list

    List access grants and attached data access policy metadata.

  • account_createwrite action

    Create a managed New Relic account.

  • accounts_list

    List New Relic accounts visible to the configured user key.

  • admin_resources_list

    List authentication domains, groups, grants, roles, policies, and permissions for an organization.

  • alert_condition_createwrite action

    Create a static NRQL alert condition.

  • alert_condition_deletewrite action

    Delete an alert condition.

  • alert_condition_get

    Get an NRQL alert condition by ID.

  • alert_condition_updatewrite action

    Update a static NRQL alert condition.

  • alert_conditions_list

    List NRQL alert conditions, optionally filtered by policy.

  • alert_policies_list

    List alert policies with cursor pagination.

  • alert_policy_createwrite action

    Create an alert policy.

  • alert_policy_deletewrite action

    Delete an alert policy.

  • alert_policy_get

    Get an alert policy by ID.

  • alert_policy_updatewrite action

    Partially update an alert policy.

  • api_keys_list

    List API key IDs and metadata only. Key values are never requested.

  • audit_events_query

    Read bounded NrAuditEvent history with no tool input values used as labels or logs.

  • connection_check

    Validate the configured user key and return non-secret user/account metadata.

  • custom_roles_list

    List role and permission resources within the organization administration view.

  • dashboard_createwrite action

    Create a dashboard with at least one page. Any permission other than PRIVATE requires the destructive gate.

  • dashboard_deletewrite action

    Soft-delete a dashboard by GUID.

  • dashboard_get

    Get a complete dashboard definition by GUID, excluding live-sharing secrets.

  • dashboard_page_updatewrite action

    Replace one complete dashboard page by page GUID.

  • dashboard_undelete

    Restore a soft-deleted dashboard by GUID.

  • dashboard_updatewrite action

    Replace a dashboard definition. Omitted pages, widgets, and variables are removed.

  • dashboard_widgets_updatewrite action

    Update existing widgets in one dashboard page by page GUID.

  • dashboards_list

    List dashboard entities in an account with cursor pagination.

  • data_access_policies_list

    List data access policies without exposing log data.

  • entities_get

    Get entity identity, health, reporting, metadata, and tags by GUID.

  • entities_search

    Search the New Relic entity platform with cursor pagination, capped at 200 entities per page.

  • entity_golden_data_get

    Get effective golden metrics and golden tags for an entity.

  • entity_relationship_deletewrite action

    Delete a documented user-defined relationship.

  • entity_relationship_putwrite action

    Create or replace a documented user-defined relationship.

  • entity_relationships_list

    List incoming and outgoing entity relationships, bounded by New Relic's relationship limit.

  • entity_tags_add

    Add tag values without replacing unrelated tags.

  • entity_tags_removewrite action

    Remove selected tag keys from an entity.

  • entity_tags_replace

    Replace the full tag set for an entity.

  • groups_list

    List group resources within the organization administration view.

  • incidents_list

    Read stable incident history from NrAiIncident with bounded NRQL.

  • issue_acknowledge

    Acknowledge an issue through New Relic's experimental AiIssues API.

  • issue_resolve

    Resolve an issue through New Relic's experimental AiIssues API.

  • issue_unacknowledge

    Unacknowledge an issue through New Relic's experimental AiIssues API.

  • issues_list

    Read stable issue history from NrAiIssue with bounded NRQL.

  • log_configuration_createwrite action

    Create a typed log partition, parsing rule, obfuscation expression, or obfuscation rule.

  • log_configuration_deletewrite action

    Delete a typed log configuration.

  • log_configuration_updatewrite action

    Update a typed log configuration.

  • log_configurations_list

    List log partitions, parsing rules, obfuscation expressions, and obfuscation rules.

  • maintenance_window_createwrite action

    Create a service-level maintenance window.

  • maintenance_window_deletewrite action

    Delete a service-level maintenance window.

  • maintenance_window_updatewrite action

    Replace selected maintenance-window fields.

  • maintenance_windows_list

    Get maintenance windows by IDs.

  • metric_normalization_rule_createwrite action

    Create a preview metric normalization rule.

  • metric_normalization_rule_disable

    Disable a preview metric normalization rule.

  • metric_normalization_rule_enable

    Enable a preview metric normalization rule.

  • metric_normalization_rule_updatewrite action

    Edit a preview metric normalization rule.

  • metric_normalization_rules_list

    List metric normalization rules and enabled state.

  • muting_rule_createwrite action

    Create a muting rule and schedule.

  • muting_rule_deletewrite action

    Delete a muting rule.

  • muting_rule_updatewrite action

    Update a muting rule; schedule changes may replace existing schedule fields.

  • muting_rules_list

    List alert muting rules and schedules.

  • notification_createwrite action

    Create a destination, channel, or workflow. Slack destinations are explicitly rejected.

  • notification_deletewrite action

    Delete a destination, channel, or workflow.

  • notification_testwrite action

    Send a test notification through a configured channel.

  • notification_updatewrite action

    Update a destination, channel, or workflow. Slack destinations are explicitly rejected.

  • notifications_list

    List destinations, channels, and workflows without secret values.

  • nrql_async_cancelwrite action

    Cancel a running asynchronous NRQL query.

  • nrql_async_start

    Start a long-running read-only NRQL query and return its query progress identifier.

  • nrql_async_status

    Poll a previously started asynchronous NRQL query.

  • nrql_querywrite action

    Run bounded read-only NRQL for one authorized account. Maximum upstream result size is 5,000 rows.

  • organization_get

    Get non-secret organization metadata.

  • pipeline_rule_createwrite action

    Create a current Pipeline Control cloud rule that suppresses future data.

  • pipeline_rule_updatewrite action

    Update a current Pipeline Control cloud rule that suppresses future data.

  • pipeline_rules_list

    List current Pipeline Control cloud rules. Results are filtered to configured account scopes.

  • service_level_createwrite action

    Create an SLI and its objectives for an entity.

  • service_level_get

    Get a service-level indicator by ID from an entity.

  • service_level_resultswrite action

    Run a bounded read-only result query for a service-level indicator.

  • service_level_updatewrite action

    Update an SLI definition and objectives. No unsupported delete mutation is exposed.

  • service_levels_list

    List service-level indicators attached to an entity.

  • synthetic_downtime_createwrite action

    Create a monitor downtime schedule.

  • synthetic_downtime_deletewrite action

    Delete a monitor downtime schedule.

  • synthetic_downtime_updatewrite action

    Update a monitor downtime schedule.

  • synthetic_downtimes_list

    List configured monitor downtime schedules.

  • synthetic_locations_list

    List private synthetic location metadata. Public location identifiers are configured on monitors.

  • synthetic_monitor_createwrite action

    Create a ping, simple-browser, scripted-browser, scripted-API, step, certificate-check, or broken-link monitor.

  • synthetic_monitor_deletewrite action

    Delete a synthetic monitor by GUID.

  • synthetic_monitor_get

    Get a monitor summary by entity GUID without secure credential values.

  • synthetic_monitor_updatewrite action

    Update a typed synthetic monitor definition.

  • synthetic_monitors_list

    List synthetic monitors and non-secret configuration metadata.

  • synthetic_private_location_createwrite action

    Create private-location metadata. Runtime keys remain managed by New Relic.

  • synthetic_private_location_deletewrite action

    Delete a private synthetic location.

  • synthetic_private_location_updatewrite action

    Update private-location metadata.

  • synthetic_secure_credentials_list

    List secure credential entity metadata. Secret values are never queried.

  • trace_get

    Retrieve a complete distributed trace graph, spans, relationships, entities, and anomalies by trace ID.

  • users_list

    List users in one authentication domain.

  • workload_createwrite action

    Create a workload from entity GUIDs and/or entity search queries.

  • workload_deletewrite action

    Delete a workload by GUID.

  • workload_duplicate

    Duplicate a workload into an authorized account.

  • workload_get

    Get workload identity, membership, health, and permalink metadata by GUID.

  • workload_status_get

    Get calculated workload status and rollup summary.

  • workload_updatewrite action

    Replace workload membership queries, entities, scope accounts, and status configuration.

  • workloads_list

    List workloads for an account with cursor pagination.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

2 medium
  • Code scan99 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 77 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumnpm install lifecycle script presentinstall.script
  • mediumnpm install lifecycle script presentinstall.script
    package.json: …: "npm run clean && npm run build", "postinstall": "node -e \"const m=Number(process.versi…
Overall 63/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How New Relic MCP Server compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
63/100
higher than 18% of 48,255 servers
Tools
100
the typical server has 7
Tools that change things
49%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
56
more than 46% of 12,191 servers with a package

What its tools let an agent do: 51 read · 49 change

Install New Relic MCP Server in Claude Code, Cursor or VS Code

Runs npx -y @meet-bhalodiya/newrelic-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add newrelic-mcp -- npx -y @meet-bhalodiya/newrelic-mcp
Add to Cursor

What the publisher says

From the New Relic MCP Server repository's README, as published. We do not edit it. Read it on GitHub

New Relic MCP Server

<!-- mcp-name: io.github.Meet-Bhalodiya/newrelic-mcp -->

Connect your AI assistant to New Relic — safely.

A production-oriented, self-hostable Model Context Protocol (MCP) server that gives Claude, Cursor, Codex, and other MCP clients typed, read-only-by-default access to NRQL, logs, metrics, traces, errors, entities, alerts, incidents, dashboards, synthetics, workloads, service levels, and selected administration APIs — all over New Relic's NerdGraph.

It deliberately does not expose arbitrary GraphQL, forward client credentials to New Relic, or accept New Relic keys as tool arguments. Mutations are absent unless their feature gates are explicitly enabled, and every write uses a dry-run, confirmation phrase, and post-write readback workflow.

Highlights

  • 🔒 Safe by default — read-only out of the box; writes are opt-in, gated, and run a dry-run → confirmation-phrase → post-write readback flow.
  • 🧱 Bounded API surface — a fixed, documented set of NerdGraph operations; no arbitrary GraphQL and no credentials passed as tool arguments.
  • 🔌 Works with any MCP client — Claude Code, Claude Desktop, Cursor, Codex, and more, over stdio or stateless Streamable HTTP.
  • 📈 Usage telemetry built in — a Prometheus /metrics endpoint with per-tool call counts, durations, and outcomes, plus upstream NerdGraph, queue-depth, retry, rate-limit, and cache metrics.
  • 🏢 Enterprise-ready — bearer/OIDC authentication, Host/Origin allowlists, account allowlists, secret and PII redaction, Docker, and Helm.
  • 🧰 Broad coverage — independently selectable toolsets for NRQL, entities, alerts, dashboards, synthetics, workloads, service levels, logs, and metrics.
  • 📚 Documented and tested — architecture docs, ADRs, and a unit/integration/contract/security/load test suite that gates every change in CI.

What you can ask

Once connected, ask your MCP client in plain language — it selects and calls the right read-only tools for you:

  • "What are the slowest transactions for the checkout service in the last hour?"
  • "Summarize the open incidents for the payments team and their likely causes."
  • "Which service levels are at risk of missing their objective this week?"
  • "Review my alert policies and point out coverage gaps."
  • "Why did the login synthetic monitor fail overnight?"

See the tool catalog for the complete set of capabilities.

Why this MCP?

New Relic offers an official, New Relic-hosted MCP server (New Relic AI MCP, currently in preview). This project is a complementary, self-hostable and open-source alternative. Choose it when you want:

own credentials; only outbound NerdGraph calls leave your perimeter. (New Relic's preview is not offered for FedRAMP-regulated accounts.)

  • Self-hosting and control — run the MCP bridge inside your own network with your

dry-run → confirmation-phrase → readback flow.

  • Read-only by default, with gated writes — every mutation is opt-in and runs a

with no arbitrary GraphQL and no New Relic keys passed as tool arguments.

  • A fixed, auditable operation surface — a documented set of NerdGraph operations,

redaction, and independently selectable toolsets.

  • Your own controls — bearer/OIDC auth, Host/Origin and account allowlists, secret

you can scrape into your existing observability stack.

  • First-class telemetry — Prometheus metrics for tool usage and upstream calls that
  • Apache-2.0 and forkable — inspect, pin, and extend exactly what you deploy.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

New Relic MCP Server: common questions

Is New Relic MCP Server safe?
With care: it is graded C, so read the findings first (63/100). Read the New Relic MCP Server safety report
How do I install New Relic MCP Server?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does New Relic MCP Server need an API key?
Yes. The registry entry asks for NEW_RELIC_API_KEY.
Is New Relic MCP Server maintained?
The last commit was 78 days ago (2026-08-18). The latest release is v1.0.0.
How does New Relic MCP Server compare with other MCP servers?
safety score 63/100 (higher than 18% of 48,255 servers); tools 100 (the typical server has 7); tools that change things 49% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.