// SCAN REPORT

Newrelic

27 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 28 Jun 2026

10 can modify or destroy data

17 read-only

27 tools total

Community server · catalogue entry verified 28/06/2026

How to control Newrelic ↓

TOOL MAP

What Newrelic exposes to your agents

Read (17) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Newrelic tools

Destructive · High delete_log_parsing_rule This tool permanently removes a log parsing rule configuration from New Relic. Execute · Critical nerdgraph_query This tool runs arbitrary NerdGraph GraphQL queries supplied by the caller. Execute · High query_nrql This tool executes arbitrary query statements, which could include data-modifying or data-exposing operations depending on NRQL capabilities. Execute · Medium test_log_parsing_rule Testing a parsing rule involves running/executing logic against sample data.

10 of Newrelic's 27 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Newrelic

PolicyLayer is an MCP gateway — it sits between your AI agents and Newrelic, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_log_parsing_rule": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_deployment": {
    "limits": [
      {
        "counter": "create_deployment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_alert_policy": {
    "limits": [
      {
        "counter": "get_alert_policy_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Newrelic — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON NEWRELIC →

Instant setup, no code required.

FULL CATALOGUE

All 27 Newrelic tools

DESTRUCTIVE 1 tools

Destructive delete_log_parsing_rule Delete a log parsing rule

EXECUTE 3 tools

Execute nerdgraph_query Execute a custom NerdGraph GraphQL query Execute query_nrql Execute an NRQL query Execute test_log_parsing_rule Test a log parsing rule against sample logs.

WRITE 6 tools

Write create_deployment Record a new deployment for an application Write create_log_parsing_rule Create a new log parsing rule Write generate_log_parsing_rule generate_log_parsing_rule Write manage_credentials Manage New Relic credentials securely in keychain. Write update_dashboard update_dashboard Write update_log_parsing_rule Update an existing log parsing rule

READ 17 tools

Read get_alert_policy Get details for a specific alert policy Read get_application Get details for a specific New Relic application Read get_application_metric_data Get metric data for an application Read get_application_metrics Get available metrics for an application Read get_dashboard Get details for a specific dashboard Read get_server Get details for a specific server Read get_synthetic_monitor Get details for a specific synthetic monitor Read get_user Get details for a specific user Read list_alert_policies List all alert policies Read list_applications List all New Relic APM applications Read list_dashboards List all dashboards for an account Read list_deployments List deployments for an application Read list_log_parsing_rules List all log parsing rules for an account Read list_servers List all servers monitored by New Relic Infrastructure Read list_synthetic_monitors List all synthetic monitors Read list_users List all users in the New Relic account Read search_entities Search for entities in New Relic

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Newrelic

Can an AI agent delete data through the Newrelic MCP server? +

Yes. The Newrelic server exposes 1 destructive tools including delete_log_parsing_rule. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Newrelic? +

The Newrelic server has 6 write tools including create_deployment, create_log_parsing_rule, generate_log_parsing_rule. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Newrelic.

How many tools does the Newrelic MCP server expose? +

27 tools across 3 categories: Destructive, Read, Write. 17 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Newrelic? +

Register the Newrelic MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Newrelic tool call.

Deterministic rules across all 27 Newrelic tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NEWRELIC →

Instant setup, no code required.

27 Newrelic tools catalogued and risk-classified — across an index of 43,000+ MCP servers.