New Relic MCP server
New Relic in any MCP client, through Memtro: New Relic does not publish this server. Memtro's New Relic connector reads New Relic through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.
What the model can do
New Relic through NerdGraph: NRQL queries over any event or metric data, entity search (applications, hosts, browser apps, monitors) with health and alert state, one entity's golden metrics and summary, open alert issues, and alert policies; when you ask, can close (resolve) an alert issue and record a deployment marker on an entity.
Reads
newrelic_accountsThe New Relic accounts this key can see (id and name) and who the key belongs to.newrelic_nrqlRun an NRQL query against an account and return the rows: e.g. "SELECT count(*) FROM Transaction WHERE appName = 'web' SINCE 1 hour ago FACET name"…newrelic_entity_searchFind monitored entities — APM applications, hosts, browser and mobile apps, synthetic monitors, dashboards, services — by name…newrelic_entityOne entity by guid in full: type, reporting and alert state, tags, link, its summary numbers (APM: apdex, error rate, response time, throughput…newrelic_issuesAlert issues on the account, newest first: id, title, priority (CRITICAL, HIGH, MEDIUM, LOW), state (ACTIVATED = open and notifying, CREATED = open…newrelic_alert_policiesAlert policies on the account: id, name and incident preference (PER_POLICY, PER_CONDITION, PER_CONDITION_AND_TARGET).
Acts, when you ask
These change something in New Relic. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.
newrelic_close_issueCloses (resolves) an open New Relic alert issue.newrelic_record_deploymentRecords a deployment on one New Relic entity (usually an APM application) as a change-tracking event: a marker on its charts with the version…
Connect it
First connect New Relic on Dashboard → Connections, then add Memtro to your client once. The New Relic tools appear alongside the tools of everything else you have connected; nothing is configured per connector.
Claude Code
The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.
claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...Cursor
Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.
{
"mcpServers": {
"memtro": {
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Claude Desktop
Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…
OpenCode
A remote server in opencode.json.
{
"mcp": {
"memtro": {
"type": "remote",
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Pi
One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.
Any other client
Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.
Who may use it
The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared New Relic connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.
Ask it like this
- › What is alerting right now, and how severe is it?
- › What was the error rate on the checkout-api application in the last hour?
- › Run SELECT average(duration) FROM Transaction WHERE appName = 'web' TIMESERIES 5 minutes SINCE 1 day ago
- › Which critical issues opened over the weekend, and are they closed?
- › Record a deployment of version 4.12.0 on checkout-api with the changelog from this release
Questions
- Is this an official New Relic MCP server?
- No. It is Memtro's MCP server with Memtro's New Relic connector behind it: the connector reads New Relic through its API with the credentials you connect on Dashboard → Connections, and New Relic publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
- What does it cost?
- Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
- Can it change anything in New Relic?
- Only when you ask, and only what it has been granted: close (resolve) an open alert issue; record a deployment marker (version, changelog, commit) on one entity. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
- Which clients work?
- Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.