MCP100 Assessment

Editorial verdict

Promising observability tooling, but it remains on the Shortlist until telemetry sensitivity, account and entity permissions, write-capable actions, and data-handling behavior receive fuller independent review.

Reviewed July 30, 2026

Task Fit

Mapped

Specialized workflows

Trust

Status warning

mcp_relevance; documentation; maintenance_source_health; client_coverage; tool_contract; install_supply_chain; advisory_freshness; resource_type_requirements

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals available

Visible usage signals are shown for discovery only, not as proof of safety.

Best for

Observability investigation and alerting workflows in New Relic.

Not ideal for

Production use before the documented maturity gaps are resolved

Avoid if

The connected identity is broader than the task requires
Tool calls cannot be reviewed before consequential mutations

Trade-offs

New Relic explicitly provides the feature as a Preview program.

Evidence scope

Evidence

Current source snapshot

Popularity

7 MCP repository stars

New Relic MCP · no comparable public usage metric

Repository identity: newrelic/mcp-server

Official New Relic MCP is documented as a service endpoint/integration; no comparable public MCP-specific usage metric is available.

Stars observed September 8, 2026 · Downloads observed September 8, 2026

Exact implementation repository metric.

Official New Relic MCP is documented as a service endpoint/integration; no comparable public MCP-specific usage metric is available.

Maintenance

Publisher activity observed July 30, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed July 30, 2026

Sources

Official setup docs ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Streamable HTTP

MCP100 logic checked

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

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Reconnect Claude Code, complete the publisher OAuth or authentication flow if prompted, confirm newrelic tools are listed, and perform one read-only test.

Uninstall and revoke

Remove newrelic from Claude Code, clear its stored MCP OAuth credentials, and revoke the publisher authorization if it is no longer needed.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-08-12

Evidence 1 ↗Evidence 2 ↗

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

� Getting Started

For detailed setup instructions and complete documentation, visit: New Relic MCP Documentation

Quick Setup

Set up authentication (API key or OAuth2.0 - see full documentation)
Configure your MCP client with the server endpoint
Start using natural language to interact with your observability data

Loading optional publisher installation details…

Capability

What it does

Use authorized New Relic discovery, alerting, and telemetry tools through regional hosted endpoints.

Monitoring & ObservabilitySoftware & Technology

Representative uses

Observability investigation and alerting workflows in New Relic.

Important limits

Production use before the documented maturity gaps are resolved

Tools36 documented capabilitiesView tools

Discovery
Discover New Relic accounts, entities, and other resources available to the authenticated user.
Data access / NRQL
Query telemetry and other observability data, including NRQL-based analysis.
Alerting
Inspect alert policies, conditions, incidents, and related alerting configuration exposed by the MCP.
Incident response
Investigate active problems and operational context that support incident triage and response.
Performance analytics
Analyze performance signals and golden metrics across monitored entities.
Advanced analysis
Run deeper New Relic analyses that combine entity, telemetry, deployment, or error context.

Current official tool reference states a 36-tool full catalog.

Source: Official source

Context Footprint

Varies by configuration

Estimated token footprint of the MCP tool schemas exposed to the agent.

~7,200 schema tokens is an Approx. catalog/reference estimate, not Runtime Verified.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: The hosted server supports OAuth and New Relic API keys.
Permissions: New Relic RBAC, account permissions, API keys, and include-tags tool filtering constrain access.
Data handling: Authorized service data and tool results pass through the MCP server to the connected AI client. Review the publisher and client data policies before using sensitive monitoring & observability information.
Cost: The MCP integration has no separately verified MCP100 price conclusion. Publisher subscriptions, API usage, compute, storage, and AI-client charges may apply.
Risk and cautions: New Relic explicitly provides the feature as a Preview program. Use a test environment where practical, least-privilege credentials, narrowly enabled tools, and explicit confirmation for mutations. MCP100 did not execute third-party server code during this documentation review.

Related reviewed MCPs

Other options

Grafana Cloud MCP

MCP100 Recommended

Query Grafana Cloud metrics, logs, dashboards, and observability context.

Choose this instead if

Choose Grafana Cloud MCP instead if query Grafana Cloud metrics, logs, dashboards, and observability context.

Query Grafana Cloud metrics, logs, dashboards, and observability context.

Compare with New Relic MCP View Grafana Cloud MCP details

Datadog MCP

MCP100 Recommended

Investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.

Choose this instead if

Choose Datadog MCP instead if investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.

Investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.

Compare with New Relic MCP View Datadog MCP details

MCP Server for Splunk platform

MCP100 Recommended

Search and investigate governed Splunk Cloud Platform data through granular MCP tools.

Choose this instead if

Choose MCP Server for Splunk platform instead if security and operations investigation over authorized Splunk searches and platform objects.

Search and investigate governed Splunk Cloud Platform data through granular MCP tools.

Compare with New Relic MCP View MCP Server for Splunk platform details

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

New Relic MCP

What is New Relic MCP?

An MCP server implementation that connects AI agents and tools to New Relic's observability data. With this server, you can use natural language to query your telemetry data, investigate alerts, analyze performance, and generate intelligent insights from your monitoring infrastructure.

Tool Categories

Some of the tools organized by category:

Entity and Account Management: Entity lookup, account management
Alerting and Monitoring: Alert policies, incident management, recent issues
Incident Response: Change tracking, error and alert analysis
Performance Analytics: Golden metrics, logs, thread analysis
Data Access: NRQL queries, natural language processing
Advanced Analysis: Deployment impact assessment, entity log analysis

Loading optional publisher documentation…

FAQ

What can New Relic MCP do?

Use authorized New Relic discovery, alerting, and telemetry tools through regional hosted endpoints.

Can New Relic MCP query telemetry and alerting data?

Yes. The official hosted MCP covers discovery, NRQL and other data access, alerting, incident response, performance analytics, and advanced analysis. RBAC, account access, and include-tags filtering can narrow the exposed tools.

Does New Relic MCP work with Claude Code?

Yes. MCP100 reviewed an evidence-backed setup for Claude Code, but has not independently verified it with a live runtime test.

How does New Relic MCP authenticate?

The hosted server supports OAuth and New Relic API keys.

What observability data can an AI agent access through New Relic MCP?

Authorized service data and tool results pass through the MCP server to the connected AI client. Review the publisher and client data policies before using sensitive monitoring & observability information.

Is this an official MCP?

ecosystem:new-relic is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗