Is this an official Logz.io MCP server?

No. It is Memtro's MCP server with Memtro's Logz.io connector behind it: the connector reads Logz.io through its API with the credentials you connect on Dashboard → Connections, and Logz.io publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

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 Logz.io?

Only when you ask, and only what it has been granted: enable an alert; disable an alert; create a log alert that notifies the recipients you name; delete an alert (permanent); add a deployment marker; add a value to a lookup list; remove a value from a lookup list (permanent). 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.

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.

MCP server · Engineering and operations

Logz.io MCP server

Logz.io in any MCP client, through Memtro: Logz.io does not publish this server. Memtro's Logz.io connector reads Logz.io 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

Logz.io observability: search and count logs over a window of up to two days, unified log and metric alerts with their queries, alert events by state and severity, and lookup lists; when you ask, can enable, disable, create or delete log alerts, add deployment markers, and add or remove lookup list values.

Reads

logzio_search_logsSearch Logz.io logs with a Lucene query (as typed in Logz.io's search bar) over a window of at most two days; defaults to the last hour, newest first.
logzio_count_logsCount Logz.io logs matching a Lucene query over a window of at most two days (default the last hour)…
logzio_list_alertsLogz.io unified alerts (log and metric): title, type, enabled, severities, tags, schedule and when changed.
logzio_get_alertOne Logz.io unified alert in full: its queries, group-by fields, aggregation, thresholds per severity, schedule, runbook…
logzio_alert_eventsLogz.io alert events: which alerts fired, their state (triggered, resolved, pending, no data), severity, reason and the grouped values…
logzio_lookup_listsLogz.io lookup lists (named value lists that alerts and security rules match against), or with list_id the values in one list…

Acts, when you ask

These change something in Logz.io. 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.

logzio_enable_alertEnables a Logz.io alert, so it is evaluated again and notifies its recipients and endpoints when it triggers.
logzio_disable_alertDisables a Logz.io alert: it stops being evaluated and nobody is notified until it is enabled again.
logzio_delete_alertPermanently deletes a Logz.io alert and its configuration; it cannot be restored.
logzio_create_log_alertCreates a Logz.io log alert: a Lucene query evaluated over a sliding window, counted by up to three group-by fields (or an aggregation of a field)…
logzio_create_deployment_markerAdds a deployment (or other) marker to Logz.io, so it appears on Exception graphs and in the Deployments list.
logzio_add_lookup_valueAdds a value (an IP, a user name, a domain) to a Logz.io lookup list…
logzio_remove_lookup_valuePermanently removes one value from a Logz.io lookup list; alerts and rules using the list stop matching it.

Connect it

First connect Logz.io on Dashboard → Connections, then add Memtro to your client once. The Logz.io 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 Logz.io 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 alerted overnight on checkout?
› How many errors per service in the last hour?
› Show the latest payment timeout log lines.
› What thresholds does the checkout latency alert use?
› Add a deployment marker for release 4.2.

Questions

Is this an official Logz.io MCP server?: No. It is Memtro's MCP server with Memtro's Logz.io connector behind it: the connector reads Logz.io through its API with the credentials you connect on Dashboard → Connections, and Logz.io 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 Logz.io?: Only when you ask, and only what it has been granted: enable an alert; disable an alert; create a log alert that notifies the recipients you name; delete an alert (permanent); add a deployment marker; add a value to a lookup list; remove a value from a lookup list (permanent). 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.