Read GPU instances, types, images, filesystems and firewall rules; launch and terminate instances. For ML engineers and researchers who rent GPU servers on Lambda Cloud. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"lambda-labs": {
"url": "https://lambda-labs.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"lambda-labs": {
"type": "http",
"url": "https://lambda-labs.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The AI lists your GPU instances with name, IP, status, region, instance type and attached filesystems, and opens one for full details.
lambda_list_instances lambda_get_instance
The AI lists instance types with vCPUs, memory, GPUs, hourly price and the regions that have capacity. It compares them and picks a fit for you.
lambda_list_instance_types lambda_list_images
The AI launches one or more instances in a region with an instance type and one SSH key name that you give. Billing starts when the instance boots.
Changes data · lambda_launch_instance lambda_list_instance_types
The AI reboots instances, changes an instance's name or tags, or terminates instances by id. Terminating destroys non-persistent data.
Changes data · lambda_restart_instances lambda_update_instance lambda_terminate_instances
The AI lists inbound firewall rules and rulesets, and the audit events of the account in a time window. You see the rules in place and recent actions.
lambda_list_firewall_rules lambda_list_firewall_rulesets lambda_list_audit_events
The login page asks for your Lambda Labs API key.
Create one in the Lambda Cloud dashboard → API keys. Your API key is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Lambda Labs API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Lambda Labs connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
lambda_list_instances | read | List instances List your running GPU cloud instances (id, name, ip, status, region, instance_type, ssh_key_names, filesystems, jupyter_url). Lambda Cloud REST: GET /api/v1/instances. |
lambda_get_instance | read | Get instance Get full details of a single instance by id (status, ip, region, instance_type, ssh/filesystem attachments, jupyter url, available actions). Lambda Cloud REST: GET /api/v1/instances/{id}. |
lambda_list_instance_types | read | List instance types List all GPU instance types with their specs (vcpus, memory, storage, gpus), hourly price (price_cents_per_hour), and which regions currently have capacity available. Use this to pick region_name + instance_type_name before launching. Lambda Cloud REST: GET /api/v1/instance-types. |
lambda_list_images | read | List images List available machine images (id, name, family, version, region availability) that can be selected when launching an instance. Lambda Cloud REST: GET /api/v1/images. |
lambda_list_filesystems | read | List filesystems List your persistent filesystems (id, name, region, status, created_at) that can be attached to instances at launch. Lambda Cloud REST: GET /api/v1/file-systems. |
lambda_list_firewall_rules | read | List firewall rules List the account's inbound firewall rules (protocol, port range, source CIDR, description). Lambda Cloud REST: GET /api/v1/firewall-rules. |
lambda_list_firewall_rulesets | read | List firewall rulesets List firewall rulesets (id, name, region, rules) that can be applied to instances. Lambda Cloud REST: GET /api/v1/firewall-rulesets. |
lambda_get_firewall_ruleset | read | Get firewall ruleset Get a single firewall ruleset by id. Lambda Cloud REST: GET /api/v1/firewall-rulesets/{id}. |
lambda_list_audit_events | read | List audit events List account audit-log events, optionally filtered by time window and resource type, with page_token pagination. Lambda Cloud REST: GET /api/v1/audit-events. |
lambda_launch_instance | write | Launch instance Launch one or more GPU cloud instances. COSTS MONEY: billing starts as soon as the instance boots (hourly rate per instance_type). Pick region_name + instance_type_name from lambda_list_instance_types (only regions with capacity available), and pass exactly one existing SSH key name in ssh_key_names (create keys in the Lambda dashboard). Lambda Cloud REST: POST /api/v1/instance-operations/launch. |
lambda_restart_instances | write | Restart instances Restart one or more running instances by id (a reboot — the instances are NOT destroyed and billing continues). Lambda Cloud REST: POST /api/v1/instance-operations/restart. |
lambda_terminate_instances | write | Terminate instances Terminate (permanently destroy) one or more instances by id. This STOPS billing for them but DESTROYS the instances and any non-persistent data — persistent filesystems survive. Irreversible. Lambda Cloud REST: POST /api/v1/instance-operations/terminate. |
lambda_update_instance | write | Update instance Update a live instance's name and/or tags. Only provided fields are changed. Lambda Cloud REST: POST /api/v1/instances/{id}. |
lambda_create_filesystem | write | Create filesystem Create a new persistent filesystem in a region (can then be attached to instances at launch). Lambda Cloud REST: POST /api/v1/filesystems. |
lambda_delete_filesystem | write | Delete filesystem Delete a persistent filesystem by id. Irreversible — DESTROYS all data on it. The filesystem must not be attached to any instance. Lambda Cloud REST: DELETE /api/v1/filesystems/{id}. |
lambda_labs_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
lambda_labs_request_feature | Request a missing feature Tell usefulapi that the user needs something the Lambda Labs tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
lambda_labs_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Lambda Labs (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $39/month or $390/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
lambda_labs_cancel_subscription | Cancel the Pro subscription Cancel the caller's Lambda Labs Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run lambda_labs_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Lambda Labs server only. Subscribe with lambda_labs_upgrade (it returns a Stripe Checkout link). Cancel any time with lambda_labs_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running lambda_labs_upgrade before then undoes the cancel. Or write to [email protected].
See running instances with region and status. Find a GPU type that is available now. Launch GPU instances. Restart, rename, tag or terminate instances. Review firewall rules and recent account actions. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Lambda Labs. The server calls the Lambda Labs API with your own Lambda Labs access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Lambda Labs API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Lambda Labs API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Lambda Labs API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Lambda Labs.
Yes, if you approve it. 6 of the 15 Lambda Labs tools can create or change data. The other 9 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Lambda Labs server only. Cancel any time: Pro then runs to the end of the paid period. Run lambda_labs_usage_status to see how many calls you used.
Ask the AI to run lambda_labs_upgrade: it returns a Stripe Checkout link. To cancel, run lambda_labs_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with lambda_labs_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.