Skip to main content
Glama

ParalonCloud MCP server

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

  • rent: browse GPUs, start a rental, get its connection URL, and stop it;

  • provide: list your nodes with live GPU load and temperature, add a node and get its install command, take a node off the market and back, set its price, reclaim a spot node, and read your earnings,

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.

Tools

Renting (key needs the rental scope)

Tool

What it does

Cost

list_gpus

List rentable GPUs with price, VRAM, compute capability, country

free

get_balance

Your credit balance

free

list_templates

Apps a rental can start with (ComfyUI, Open WebUI with Ollama, Unsloth Studio), their version and minimums

free

create_rental

Start a rental with JupyterLab or SSH (type: "ssh"), optionally with an app installed (template: "comfyui", "openwebui" or "unsloth"; an app with its own sign-in returns it in app.login) (async → poll)

spends credits

get_rental

Status + the JupyterLab URL or the SSH command once running, and an app's link (connection.app_url)

free

list_rentals

Your active rentals (status: "all" for history)

free

destroy_rental

Stop a rental and stop billing

—

list_ssh_keys

The SSH public keys an SSH rental installs

free

add_ssh_key

Save an SSH public key (the .pub line, never the private key)

free

delete_ssh_key

Delete a saved key; new SSH rentals stop accepting it

free

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.

Your nodes, for GPU providers (key needs the nodes scope)

Tool

What it does

list_my_nodes

Your nodes: state (available, rented, paused, offline, …), GPUs, price and its allowed range, the current rental, live per-GPU load, temperature, power and memory

get_my_node

One node, same fields

add_node

Add a node; returns the docker command that installs the agent (it holds the node's token)

get_node_install_command

The install command of an existing node, again

set_node_available

Take a node off the market, or put it back; a running rental goes on to its end

set_node_price

Set the price in USD per hour for the node, or null for the default

update_node

Change name, spot, availability and price in one call

reclaim_spot_node

Take a spot node back for your own use; a spot rental on it stops in 2 minutes

get_node_access

Who can rent a node: everyone, or only the people, domains and organizations listed

set_node_access

Keep a node private for chosen renters (email, domain, organization), or open it to everyone ([])

get_earnings

Earnings by day (rentals per node, inference per account) and the withdrawable balance

Payouts are not reachable from the API or this server. Deleting a node stays on the site.

Related MCP server: Latitude.sh MCP Server

Setup

1. Get a key with the right scope

  1. Create an API key in the Console.

  2. To rent, turn on GPU rentals for that key (rentals are opt-in), and optionally set Max rentals running at once as a safety cap.

  3. To manage your own nodes, turn on My nodes. One key can have both.

Use a dedicated key for the agent, not your production key.

2. Add it to your MCP client

The client passes your key via the PARALON_API_KEY env var — you never edit the server.

Claude Desktop — claude_desktop_config.json:

{
  "mcpServers": {
    "paraloncloud": {
      "command": "npx",
      "args": ["-y", "@paraloncloud/mcp"],
      "env": {
        "PARALON_API_KEY": "prlc_your_key_here"
      }
    }
  }
}

Claude Code — one command:

claude mcp add paraloncloud \
  --env PARALON_API_KEY=prlc_your_key_here \
  -- npx -y @paraloncloud/mcp

Cursor — .cursor/mcp.json (same shape as Claude Desktop above).

Optional env: PARALON_BASE_URL (defaults to https://paraloncloud.com/api/v1).

3. Try it

"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?"

Safety

  • 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.

  • Pass hours so a rental auto-stops even if the agent forgets to.

  • The key's max_active_rentals limit (set in the Console) caps concurrency regardless.

  • The node tools that change something (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.

  • Give the agent a key with only the scopes it needs.

Test

npm install
PARALON_API_KEY=prlc_your_key_here node smoke-test.mjs

It calls the read-only tools, and the node tools only on a node that does not exist, so it changes nothing.

Run locally (dev)

PARALON_API_KEY=prlc_your_key_here node server.js

MIT

Available Tools

17 tools
add_nodeA

PROVIDER: 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.

Inputs: name (required), os, spot, type, +1 more.

create_rentalA

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.

Inputs: node_id (required), name, type, hours.

destroy_rentalA

Stop 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.

Inputs: rental_id (required).

get_balanceA

Get the account's credit balance (rentals are billed per minute against it). Read-only, no cost.

Inputs: no named parameters.

get_earningsA

PROVIDER: 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.

Inputs: days.

get_my_nodeC

PROVIDER: one of the account's nodes, same fields as list_my_nodes (state, price, rental, live GPU metrics). Read-only.

Inputs: node_id (required).

get_node_accessC

PROVIDER: who can rent a node. An empty list (private: false) means everyone; otherwise only the people (email), email domains and organizations listed see the node and can rent it. Read-only.

Inputs: node_id (required).

get_node_install_commandA

PROVIDER: 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.

Inputs: node_id (required).

get_rentalA

Get 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.

Inputs: rental_id (required).

list_gpusA

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. reserved_for_you: true marks a node its provider keeps for this key's person or organization: such nodes come first and nobody else sees them. Read-only, no cost. For modern LLM work prefer compute_cap >= 8.9 (FP8).

Inputs: no named parameters.

list_my_nodesA

PROVIDER: 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.

Inputs: no named parameters.

list_rentalsA

List the account's rentals. By default only active ones (what's running and billing). Pass status='all' for full history. Read-only.

Inputs: status.

reclaim_spot_nodeA

PROVIDER: 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).

Inputs: node_id (required).

set_node_accessA

PROVIDER: set who can rent a node, replacing the whole list. Each entry is {kind: "email", value: "ana@company.com"}, {kind: "domain", value: "company.com"} or {kind: "org", value: ""}. A non-empty list makes the node PRIVATE: only those renters see it and can rent it, and ParalonCloud places no inference or other work on it, so it earns from their rentals only. [] opens it to everyone again. Call get_node_access first to keep existing entries. Always confirm with the user first. People and organizations added are told by email.

Inputs: entries (required), node_id (required).

set_node_availableA

PROVIDER: 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.

Inputs: node_id (required), available (required).

set_node_priceA

PROVIDER: 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.

Inputs: node_id (required), price_per_hour (required).

update_nodeA

PROVIDER: 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.

Inputs: node_id (required), name, spot, available, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 17 tools

    Disambiguation4/5

    Provider and renter operations are clearly separated, and each tool names a distinct resource+action. There is some overlap: update_node can also change 'available' and 'price_per_hour', which collides with set_node_available and set_node_price, and reclaim_spot_node overlaps with set_node_available(false) on spot nodes. The descriptions clarify the difference (batch vs. single-field, spot-specific semantics), so misselection is unlikely but not impossible.

    Naming Consistency5/5

    All 17 tools follow a consistent verb_noun snake_case pattern (list_my_nodes, set_node_access, create_rental, destroy_rental). The role prefixes (my/rental/node) are used predictably, and read vs. write is obvious from the verb. Minor variation between add_node and create_rental is the only deviation and does not break the pattern.

    Tool Count4/5

    17 tools is on the heavy side of the sweet spot but justified because the server serves two distinct roles (provider node management and renter GPU usage). Almost every tool maps to a real operation earning its place. It could be tightened if update_node absorbed the single-field setters.

    Completeness4/5

    The renter lifecycle (list_gpus, create_rental, get_rental, destroy_rental, list_rentals) and provider lifecycle (add, install command, get/list, price, availability, access, earnings) are well covered. Notable gaps: there is no way to remove/delete a node from the account once added, and no credit top-up or payout operation (payouts explicitly excluded). These are minor and documented, so agents can mostly work around them.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables natural language management of Latitude.sh infrastructure, allowing users to list, create, and delete servers, projects, and SSH keys through MCP-compatible clients.
      21 npm
      4
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      MCP server that wraps the Vast.ai REST API to enable LLM agents to search GPU marketplace, rent machines, manage instance lifecycle, run commands, and inspect billing.
      20
      1
      -