Lambda Cloud MCP server

What the model can do

Lambda Cloud GPU instances: running instances with type, GPUs, region, IP, hourly price and status, instance types with prices and which regions have capacity now, images, persistent filesystems, support tickets with their status, severity and priority, and the account's audit log of actions; when you ask, can launch an instance (billed per hour), restart or terminate instances, rename or retag one, create or delete a filesystem, open a support ticket with Lambda, and comment on, re-prioritise or close one.

Reads

• lambdalabs_instancesLambda Cloud instances: name, status (booting, active, unhealthy, terminating …), type, GPU, region, public and private IP, hourly price, image…
• lambdalabs_instanceOne Lambda Cloud instance by id, with type, GPUs, region, IPs, status, price, image, filesystems and tags.
• lambdalabs_instance_typesInstance types Lambda offers: GPU, vCPUs, memory, storage, hourly price in USD, and the regions with capacity to launch one right now…
• lambdalabs_imagesMachine images that instances can boot from: name, family (pass to lambdalabs_launch_instance), version, architecture and region.
• lambdalabs_filesystemsPersistent filesystems: name, region, default mount point, whether an instance has it mounted, and bytes used.
• lambdalabs_ticketsSupport tickets with Lambda: subject, type (incident, service request, automated event), severity, priority, status (open, on_hold, pending…
• lambdalabs_audit_eventsThe account's audit log: what was done (launch, terminate, key created …) to which resource, by which service, through which surface…

Acts, when you ask

These change something in Lambda Cloud. 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.

• lambdalabs_launch_instanceLaunches a new Lambda Cloud GPU instance in the region given, which starts hourly billing at the type's price…
• lambdalabs_restart_instancesReboots the Lambda Cloud instances named by id; whatever runs in memory on them is lost and they are unreachable until they are back.
• lambdalabs_terminate_instancesPermanently terminates the Lambda Cloud instances named by id: they are destroyed with everything on their local disks…
• lambdalabs_update_instanceRenames a Lambda Cloud instance and/or replaces ALL its tags with the ones given (an empty list clears them; keys starting lambda-ai- are reserved).
• lambdalabs_create_filesystemCreates a persistent filesystem in a Lambda region, which instances in that region can mount; storage is billed while it exists.
• lambdalabs_delete_filesystemPermanently deletes a Lambda filesystem and every file on it.
• lambdalabs_create_ticketOpens a support ticket with Lambda: Lambda's support staff (people outside the company) receive the subject and description and will reply.
• lambdalabs_update_ticketAdds a comment to a Lambda support ticket (Lambda's support staff see it; comments cannot be edited), changes its severity or priority…

Connect it

First connect Lambda Cloud on Dashboard → Connections, then add Memtro to your client once. The Lambda Cloud tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

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 Lambda Cloud 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

• › Which instances are running, and what do they cost per hour?
• › Which instance types can be launched right now, and in which regions?
• › Which support tickets with Lambda are still open?
• › Which instances were launched or terminated this week, according to the audit log?
• › Restart the training-02 instance.

Questions

Is this an official Lambda Cloud MCP server?

No. It is Memtro's MCP server with Memtro's Lambda Cloud connector behind it: the connector reads Lambda Cloud through its API with the credentials you connect on Dashboard → Connections, and Lambda Cloud 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 Lambda Cloud?

Only when you ask, and only what it has been granted: launch a GPU instance (billed per hour); restart instances; terminate instances; rename or retag an instance; create a persistent filesystem; delete a filesystem; open a support ticket with Lambda; comment on, re-prioritise or close a support ticket. 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.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server