Lambda Labs MCP by usefulapi

io.usefulapi由 usefulapi.io 發布官方發布者v1.36.4更新於 Nov 7, 2026

Read GPU instances, types, images, filesystems and firewall rules; launch and terminate instances.

發布方自己的服務：Ably MCP by usefulapi

已驗證Streamable HTTP可網頁執行雲端與基礎設施安全與監控

服務詳細資訊

識別碼: io.usefulapi/lambda-labs
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此服務的命名空間屬於 usefulapi.io，且該網域同時執行其端點。這可以確認發布者，但並不代表該服務的工具是安全的。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.usefulapi%2Flambda-labs.svg)](https://sourceweft.com/mcp/io.usefulapi%2Flambda-labs?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

面向 Lambda Labs GPU 雲的託管 MCP 伺服器：檢視執行個體、機型、映像、檔案系統與防火牆規則，並可啟動或終止執行個體。

可以做什麼: 列出並檢視 GPU 執行個體、含價格與容量的機型、映像、檔案系統、防火牆規則與規則集，以及稽核事件
啟動、重新啟動、終止執行個體，以及修改執行個體名稱與標籤
建立與刪除持久性檔案系統
查看每月工具呼叫用量、提出功能需求，以及升級或取消付費方案
適用情境: 適合讓助理查看 Lambda Labs 上正在執行或可用的 GPU 資源、回顧帳戶操作紀錄，或在不開啟主控台的情況下啟停執行個體。
執行需求: 透過 streamable HTTP 連線的遠端端點，無需本機安裝。登入使用 OAuth，登入頁面要求填寫 Lambda Cloud 主控台的 API 金鑰，並依使用者儲存。用戶端設定中不要加入 API 金鑰或 Authorization 標頭。免費方案每月 50 次工具呼叫。

安裝前請注意

寫入類工具會異動真實雲端資源：啟動執行個體即刻開始按小時計費，重新啟動期間計費持續，終止不可逆且會銷毀非持久性資料，刪除檔案系統會銷毀其中所有資料。伺服器會依使用者保存你的 Lambda Cloud API 金鑰。付費方案（Pro、Pro+）透過 Stripe 結帳連結付款，取消後當期不退款。

安裝

在 SourceWeft 中

開啟儀表板中的 Lambda Labs MCP by usefulapi，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.usefulapi%2Flambda-labs/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "lambda-labs-by-usefulapi": {
      "type": "http",
      "url": "https://lambda-labs.usefulapi.io/mcp"
    }
  }
}

README

Lambda Labs MCP by usefulapi

Use your Lambda Labs account from Claude, Cursor, or any MCP client — read GPU instances, instance types, images, filesystems and firewall rules, and launch or terminate instances. Hosted, no local install: connect with your own credentials.

Live endpoint: https://lambda-labs.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://lambda-labs.usefulapi.io/mcp.
Claude Code: claude mcp add --transport http lambda-labs https://lambda-labs.usefulapi.io/mcp, then run /mcp to log in.
VS Code: Add to VS Code.
Cursor and other clients: add the URL as a remote MCP server:

json

{  "mcpServers": {    "lambda-labs": {      "url": "https://lambda-labs.usefulapi.io/mcp"    }  }}

{  "mcpServers": {    "lambda-labs": {      "url": "https://lambda-labs.usefulapi.io/mcp"    }  }}

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, and the login page asks for your Lambda Labs credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/lambda-labs/

On first connect you'll provide your Lambda Cloud API key (Lambda Cloud dashboard → API keys). It is validated, stored per-user, and scoped to you — no keys in config files.

Tools

Tool	Type	What it does
`lambda_list_instances`	read	List instances
`lambda_get_instance`	read	Get instance
`lambda_list_instance_types`	read	List instance types
`lambda_list_images`	read	List images
`lambda_list_filesystems`	read	List filesystems
`lambda_list_firewall_rules`	read	List firewall rules
`lambda_list_firewall_rulesets`	read	List firewall rulesets
`lambda_get_firewall_ruleset`	read	Get firewall ruleset
`lambda_list_audit_events`	read	List audit events
`lambda_launch_instance`	write	Launch instance
`lambda_restart_instances`	write	Restart instances
`lambda_terminate_instances`	write	Terminate instances
`lambda_update_instance`	write	Update instance
`lambda_create_filesystem`	write	Create filesystem
`lambda_delete_filesystem`	write	Delete filesystem
`lambda_labs_usage_status`	meta	Usage status (free-tier meter)
`lambda_labs_request_feature`	meta	Request a missing feature
`lambda_labs_upgrade`	meta	Upgrade to Pro or Pro+
`lambda_labs_cancel_subscription`	meta	Cancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this 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].

License

MIT — see LICENSE. Documentation only; the server is hosted.

來源：servers/lambda-labs/README.md，提交 4046075

工具

lambda_list_instances

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.

無需輸入參數。

lambda_get_instance

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}.

輸入參數id必填

lambda_list_instance_types

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.

無需輸入參數。

lambda_list_images

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.

無需輸入參數。

lambda_list_filesystems

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.

無需輸入參數。

lambda_list_firewall_rules

List firewall rules

List the account's inbound firewall rules (protocol, port range, source CIDR, description). Lambda Cloud REST: GET /api/v1/firewall-rules.

無需輸入參數。

lambda_list_firewall_rulesets

List firewall rulesets

List firewall rulesets (id, name, region, rules) that can be applied to instances. Lambda Cloud REST: GET /api/v1/firewall-rulesets.

無需輸入參數。

lambda_get_firewall_ruleset

Get firewall ruleset

Get a single firewall ruleset by id. Lambda Cloud REST: GET /api/v1/firewall-rulesets/{id}.

輸入參數id必填

lambda_list_audit_events

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.

輸入參數endstartpage_tokenresource_type

lambda_launch_instance

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.

輸入參數nametagshostnameimage_idquantityuser_dataregion_name必填image_familyssh_key_names必填file_system_namesinstance_type_name必填

lambda_restart_instances

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.

輸入參數instance_ids必填

lambda_terminate_instances

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.

輸入參數instance_ids必填

lambda_update_instance

Update instance

Update a live instance's name and/or tags. Only provided fields are changed. Lambda Cloud REST: POST /api/v1/instances/{id}.

輸入參數id必填nametags

lambda_create_filesystem

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.

輸入參數name必填region必填

lambda_delete_filesystem

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}.

輸入參數id必填