io.github.ParalonCloudPublished by GitHub account ParalonCloudv1.1.0Updated Nov 5, 2026
Rent GPUs on ParalonCloud, or as a provider manage your nodes, prices and earnings.
Rent ParalonCloud GPUs from an AI assistant, or manage your own GPU nodes, prices and earnings as a provider.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
Rent GPUs from inside your AI agent, and, if you provide GPUs, run your own nodes from it. This is an MCP server for the ParalonCloud Rental API and Provider API: it lets Claude Code, Claude Desktop, Cursor, or any MCP client
using natural language.
One key for everything: the same
prlc_key powers ParalonCloud's OpenAI-compatible inference API. Build an agent that calls a model and rents the GPU to run the heavy job.
Formerly
@paraloncloud/mcp-rentals. That package is deprecated: switch your config to@paraloncloud/mcp.
rental scope)An SSH rental installs every saved key, so the agent can make its own key, add it, rent with
type: "ssh", and run commands on the machine. Connecting needs
cloudflared
on the computer that holds the private key: get_rental returns the command.
nodes scope)Payouts are not reachable from the API or this server. Deleting a node stays on the site.
Use a dedicated key for the agent, not your production key.
The client passes your key via the PARALON_API_KEY env var — you never edit the server.
Claude Desktop — claude_desktop_config.json:
Claude Code — one command:
Cursor — .cursor/mcp.json (same shape as Claude Desktop above).
Optional env: PARALON_BASE_URL (defaults to https://paraloncloud.com/api/v1).
"List the cheapest GPUs I can rent, then start a 2-hour Jupyter rental on one with at least 24GB of VRAM."
The agent calls list_gpus, picks a node, and calls create_rental with hours: 2. It then
polls get_rental for the Jupyter URL. Say "stop it" and it calls destroy_rental.
"Rent a 4090 over SSH, run nvidia-smi on it, then stop it."
The agent makes a key with ssh-keygen, saves it with add_ssh_key, picks a node with
ssh: true, starts it with type: "ssh", runs the command get_rental returns, and stops it.
"Start ComfyUI on a GPU with 24 GB for an hour and give me the link."
The agent calls list_templates, picks a node whose templates has comfyui, starts it with
template: "comfyui" and hours: 1, and hands you connection.app_url from get_rental once the
app answers, a minute or two after the machine.
As a provider:
"How are my nodes doing? Is any GPU running hot?"
"Take rig-2 off the market for the afternoon, and set rig-1 to $0.60 an hour."
"How much did I earn this week, and from which node?"
create_rental and destroy_rental change what you're billed — your MCP client will ask you
to approve them (Claude Code/Desktop confirm tool calls by default). Keep that on.create_rental auto-generates an idempotency key, so a retried call never starts a second GPU.hours so a rental auto-stops even if the agent forgets to.max_active_rentals limit (set in the Console) caps concurrency regardless.add_node, set_node_available, set_node_price,
update_node, reclaim_spot_node, set_node_access) tell the agent to confirm with you first;
reclaim_spot_node stops a renter's spot rental two minutes later.add_node and get_node_install_command return a command with the node's secret token:
keep it private.It calls the read-only tools, and the node tools only on a node that does not exist, so it changes nothing.
MIT
Source: README.md at commit ad6a3e1
List GPU nodes available to rent right now, with price per hour, GPU model, VRAM, CUDA compute capability, and country. Rent by the returned node_id. Read-only, no cost. For modern LLM work prefer compute_cap >= 8.9 (FP8).
Takes no parameters.
Get the account's credit balance (rentals are billed per minute against it). Read-only, no cost.
Takes no parameters.
Start renting a GPU. SPENDS CREDITS (per-minute billing) — confirm with the user before calling. Asynchronous: returns a rental_id with status 'pending'. Provisioning + the secure tunnel take ~20-40 seconds. After creating, call get_rental ONCE to fetch the connection URL — it waits internally for startup and returns when ready, so do NOT poll it in a tight loop. DURATION: the rental is open-ended by default (runs until the user stops it with destroy_rental) — use open-ended as the default. When starting one, briefly tell the user it's open-ended and bills per minute until stopped, and that they can set an 'hours' auto-stop cap instead if they prefer; only pass 'hours' when the user asks for a time limit. An idempotency key is generated automatically so accidental repeats don't start a second GPU.
nametypehoursnode_idrequiredGet one rental's status and connection details (Jupyter URL + token). After create_rental, call this to get the URL. It WAITS internally (up to ~24s) for the rental to finish coming up and returns as soon as it's ready — so you usually only need ONE call, at most two. Do NOT call it repeatedly in a tight loop. Provisioning plus the secure tunnel take ~20-40 seconds total; the URL is ready when connection_pending is false. Read-only.
rental_idrequiredList the account's rentals. By default only active ones (what's running and billing). Pass status='all' for full history. Read-only.
statusStop a rental — stops the GPU and STOPS BILLING. This is the money brake; safe to call twice. Confirm with the user unless they clearly asked to stop it.
rental_idrequiredPROVIDER: list the GPU nodes this account provides (needs a key with the 'nodes' scope). For each node: state (available, rented, paused, not_verified, not_ready, offline), GPUs and VRAM, price (default, allowed min/max, custom, what a renter pays), verification, reputation, the current rental (never the renter), and live metrics from the last minute: per-GPU load %, temperature °C, power W and VRAM, plus host CPU and memory. Read-only.
Takes no parameters.
PROVIDER: one of the account's nodes, same fields as list_my_nodes (state, price, rental, live GPU metrics). Read-only.
node_idrequiredPROVIDER: add a new node to the account and get the docker command that installs the agent on the machine. Confirm the name and type with the user first. The returned command contains the node's secret token: show it only to the user, never paste it anywhere public. The node comes online once the command runs on the machine, then goes through the GPU check. At most 20 nodes an hour per key.
osnamerequiredspottypeavailablePROVIDER: the docker command that installs the agent for an existing node (to reinstall or move it). It contains the node's secret token: show it only to the user. Read-only.
node_idrequiredPROVIDER: take a node off the market (available=false) or put it back (available=true). Off stops new rentals at once; a rental already running goes on to its end. Use it when the owner needs the machine or it is rented on another marketplace. Confirm with the user unless they asked for exactly this.
node_idrequiredavailablerequiredPROVIDER: set a node's price in US dollars per hour for the whole node (what the renter pays; the provider gets it minus the platform fee), or null to go back to the platform default. Must be within the node's price.min and price.max (50% to 300% of the default; see get_my_node). A rental already running keeps its price. Not possible on a spot node. Confirm the new price with the user first.
node_idrequiredprice_per_hourrequiredPROVIDER: change several things on a node at once: name, spot (true/false; refused while the node is rented, and turning spot on clears a custom price), available, price_per_hour (USD per hour or null). Send only what changes. Confirm changes with the user first.
namespotnode_idrequiredavailableprice_per_hourPROVIDER: take a spot node back for the owner's own use ("In use"): rentals and inference go off, and a spot rental running on it STOPS TWO MINUTES LATER (the renter is told). Only for spot nodes. Always confirm with the user first. Put the node back afterwards with set_node_available(true).
node_idrequiredPROVIDER: the account's earnings in USD by UTC day for the last `days` days (default 30, max 366): rentals per node and inference for the account, after the platform fee; the total; the balance that can be withdrawn now; and what rentals still running have billed so far. Payouts themselves are not available through the API. Read-only.
days90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
{ "mcpServers": { "paraloncloud": { "command": "npx", "args": ["-y", "@paraloncloud/mcp"], "env": { "PARALON_API_KEY": "prlc_your_key_here" } } }}claude mcp add paraloncloud \ --env PARALON_API_KEY=prlc_your_key_here \ -- npx -y @paraloncloud/mcpnpm installPARALON_API_KEY=prlc_your_key_here node smoke-test.mjsPARALON_API_KEY=prlc_your_key_here node server.js