New Relic MCP server
Yes. New Relic publishes 2 official MCP servers: New Relic MCP Server and io.github.newrelic-experimental/preflight. We last checked them on 22 Nov 2026.
Official: answers MCP requests at mcp.newrelic.com, on New Relic's own domain newrelic.com. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, the best of New Relic's 2 official MCP servers, New Relic MCP Server, scores 90/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 55 of our 55 checks in the last 90 days and has 7 tools named in its documentation.
How the Agent Readiness Index works · Wrong? Suggest a correction
New Relic MCP server review
90/100
New Relic's New Relic MCP Server scores 90/100 on MartechDB's Agent Readiness Index: one of the easiest marketing tools to connect an AI agent to.
The good
Hosted by New Relic: connect by URL, with nothing to install
Sign in with your New Relic account: your AI client sets up the sign-in itself, with no API key
Documented, with 7 tools known
Published to the official MCP Registry
Answered 100% of our checks in the last 90 days
No card needed to start
Spending can be capped
The bad
Nothing we've found.
Official MCP servers
New Relic MCP Server
Access New Relic observability data through MCP - query metrics, logs, traces, entities, and more
- Address
- https://mcp.newrelic.com/mcp
- Runs
- Hosted
- Sign-in
- Cost to use
- Plan: All accounts · No card needed · Spend limits2,000 tool calls an hour per user; most tools use Core CCUs, four need Advanced Compute
- Official MCP Registry
-
Listed as
com.newrelic/mcp-server· published 28 Oct 2025 - How we know it's official
-
- Answers MCP requests at mcp.newrelic.com, on New Relic's own domain newrelic.com.
- Published in the official MCP Registry as com.newrelic/mcp-server, a name only the owner of newrelic.com can publish under.
- Documentation
- docs.newrelic.com/docs/agentic-ai/mcp/overview/
- Tools
- 7 tools · from New Relic's documentation
- First seen
- 28 Oct 2025
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
New Relic MCP Server tools (7)
The server needs sign-in before it lists its tools, so these are as New Relic's documentation names them (read 10 Nov 2026). They may be out of date.
-
natural_language_to_nrql_query -
generate_alert_insights_report -
generate_user_impact_report -
analyze_deployment_impact -
search_traces -
analyze_trace_anomaly -
analyze_service_dependencies
io.github.newrelic-experimental/preflight
New Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)
- npm package
- @newrelic/preflight v1.75.0
- Runs
- Install locally
- Sign-in
- Vendor docs
- Official MCP Registry
-
Listed as
io.github.newrelic-experimental/preflight· published 18 Sep 2026 - How we know it's official
-
- Published in the official MCP Registry as io.github.newrelic-experimental/preflight, from the newrelic-experimental GitHub account.
- Source code
- github.com/newrelic-experimental/preflight
- Tools
- 45 tools · from New Relic's documentation
- First seen
- 18 Sep 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
io.github.newrelic-experimental/preflight tools (45)
The server needs sign-in before it lists its tools, so these are as New Relic's documentation names them (read 3 Oct 2026). They may be out of date.
-
nr_observe_healthCheck server health and connection status.
-
nr_observe_install_hooksInstall PreToolUse and PostToolUse monitoring hooks into ~/.claude/settings.json, headlessly (no TTY required).
-
nr_observe_get_configShow the current server configuration with sensitive fields masked.
-
nr_observe_get_session_statsCurrent session metrics snapshot.
-
nr_observe_get_session_timelineOrdered list of recent tool calls.
-
nr_observe_report_tokensSelf-report token usage for cost tracking.
-
nr_observe_get_cost_breakdownSession cost breakdown by task, model, and efficiency.
-
nr_observe_get_workflow_traceComplete tool call trace for a task with anti-pattern and efficiency analysis.
-
nr_observe_get_anti_patternsDetected anti-patterns for the most recent task.
-
nr_observe_get_efficiency_scoreComposite efficiency score for the most recent task and session average.
-
nr_observe_report_feedbackRecord user quality feedback for a task.
-
nr_observe_mark_task_boundaryExplicitly mark the end of the current task.
-
nr_observe_get_session_historyPaginated list of past sessions with summary metrics.
-
nr_observe_get_weekly_summaryWeekly aggregate report with per-developer breakdown.
-
nr_observe_get_trendsMetric trends over time, aggregated by ISO week.
-
nr_observe_get_collaboration_profileDeveloper collaboration style profile with team comparison.
-
nr_observe_get_claudemd_impactBefore/after impact analysis of the most recent CLAUDE.md change.
-
nr_observe_get_cost_per_outcomeCost attribution by outcome type with waste ratio and ROI estimate.
-
nr_observe_get_recommendationsPersonalized optimization recommendations from multiple analyzers.
-
nr_observe_get_personal_insightsNarrative coaching report comparing this week's personal AI coding metrics against the developer's historical baseline.
-
nr_observe_get_platform_comparisonSide-by-side comparison of AI coding platforms on a given metric.
-
nr_observe_get_budget_statusCurrent spend against configured session/daily/weekly budget caps.
-
nr_observe_get_prompt_cache_healthCache hit rate, savings, and a concrete recommendation for improving cache efficiency.
-
nr_observe_get_cost_forecastProjects future spend based on current session burn rate.
-
nr_observe_get_context_efficiencyContext window efficiency: unique vs. repeated file reads.
-
nr_observe_get_latency_percentilesTool call latency: p50, p95, p99 per tool type.
-
nr_observe_get_task_completion_rateTask lifecycle tracking: completed vs. in-progress vs. abandoned.
-
nr_observe_get_model_usageWhich AI model was used per request, cost-efficiency per model, and any model switches during the session.
-
nr_observe_get_model_recommendationData-driven model recommendation ranked by historical efficiency score, cost, and task success rate across past sessions, both overall and broken down by task outcome type.
-
nr_observe_get_context_trackingPer-turn context window tracking: token growth, category breakdown (system/tools/user/assistant), fill percentage, and per-tool output contribution.
-
nr_observe_get_cost_per_toolCost attribution per tool type — approximate, based on turn-level token correlation.
-
nr_observe_get_turn_analysisConversation turn analysis: groups tool calls by AI response, shows parallelism and turn patterns.
-
nr_observe_get_git_efficiencyGit workflow efficiency metrics: merge conflicts, aborted operations, force pushes, stale branch detection, and actionable suggestions.
-
nr_observe_get_retry_alertsThrashing and retry detection alerts within a sliding window.
-
nr_observe_get_context_compositionPer-turn token breakdown by category with context fill percentage and dominance alerts.
-
nr_observe_get_latency_decompositionTime split between LLM API calls, tool execution, and overhead — with p50/p95 percentiles for each component.
-
nr_observe_get_decision_treeDecision branch analysis with reasoning extraction and failure chain post-mortem.
-
nr_observe_get_instruction_driftCLAUDE.md and system prompt change correlations with session outcomes.
-
nr_observe_get_tool_selection_scoreTool selection quality score with penalty breakdown for redundant reads, repeated failures, and unused large outputs.
-
nr_observe_get_quality_proxyQuality signal tracking: diff apply rate, test pass rate, self-correction count, and degradation detection.
-
nr_observe_get_api_failuresAPI failure tracking: per-model reliability scorecards, tokens lost, throttle alerts, and mean time to recovery.
-
nr_observe_get_team_summaryAggregated AI coding cost and efficiency metrics for all developers in the configured team, queried via New Relic NRQL.
-
nr_observe_subscribe_digestRegister a Slack webhook URL to receive weekly AI coding cost and efficiency summaries.
-
nr_observe_unsubscribe_digestRemove the registered Slack webhook for weekly digests.
-
nr_observe_send_digestGenerate the current weekly AI coding summary and POST it to the configured Slack webhook immediately.
Connect your AI to New Relic
Add the official New Relic MCP server to Claude, ChatGPT or your editor.
Connect New Relic MCP to Claude
New Relic MCP Server
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it New Relic, paste the address below and click Add.
io.github.newrelic-experimental/preflight
Connect New Relic MCP to ChatGPT
New Relic MCP Server
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it New Relic and paste the address below.
Connect New Relic MCP to Cursor
New Relic MCP Server
Opens Cursor if it's installed. If nothing happens, use the JSON below.
io.github.newrelic-experimental/preflight
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect New Relic MCP to VS Code
New Relic MCP Server
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
io.github.newrelic-experimental/preflight
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
New Relic MCP server questions
Does New Relic have an official MCP server?
Yes. New Relic publishes 2 MCP servers itself. MartechDB only lists servers a vendor publishes, never community copies.
What is the New Relic MCP server URL?
New Relic MCP Server: The address is https://mcp.newrelic.com/mcp.
How do I connect New Relic MCP to Claude, ChatGPT or Cursor?
These steps are for New Relic MCP Server. The others connect the same way, each at its own address. In Claude, add https://mcp.newrelic.com/mcp as a custom connector (Customize, Connectors, Add custom connector). In ChatGPT, turn on developer mode (Settings, Apps, Advanced settings) and create an app with the same address. In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http new-relic https://mcp.newrelic.com/mcp
What can New Relic's MCP servers do?
Together they offer 52 tools, including natural_language_to_nrql_query, generate_alert_insights_report, generate_user_impact_report, analyze_deployment_impact and search_traces (as their documentation names them, read on 10 Nov 2026).
Are New Relic's MCP servers in the official MCP Registry?
Yes, all 2 are listed there.
Are New Relic's MCP servers working?
Yes. All of them answered our most recent checks. We last checked them on 22 Nov 2026.
What are the alternatives to New Relic's MCP server?
In Developer tools, the most agent-friendly alternatives with an official MCP server are Devcycle (100/100), LaunchDarkly (97/100), Cekura (97/100), Linear (95/100) and Jam (95/100). New Relic scores 90/100 on the same index.
Alternatives to New Relic's MCP server
Vendors in Developer tools with an official MCP server, the most agent-friendly first. New Relic scores 90/100.
Compare all 32 Developer tools vendors →Change history
What we've seen change for New Relic, newest first.
-
New Relic: io.github.newrelic-experimental/preflight: version 1.75.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.74.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.73.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.72.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.71.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.70.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.68.0 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.67.3 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.67.2 published to npm
-
New Relic: io.github.newrelic-experimental/preflight: version 1.67.1 published to npm
Use with AI
Connect your AI to MartechDB
Then ask it about New Relic, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at New Relic, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.