GPU MCP server

https://mcp.ecohash.com/gpu is an MCP server that gives an AI coding agent the GPU-instance lifecycle as tools — find capacity, quote, launch, get the SSH command, stop — on your account, with your API key and credit. The agent loop is the client's (Claude Code, Codex, Claude Desktop); we only expose tools.

It needs the same thing the Compute API needs: Compute access enabled on your account, and a key created with Compute access ticked. There is nothing extra to enable for MCP.

Connect

Claude Code

claude mcp add --transport http ecolink-gpu https://mcp.ecohash.com/gpu \
  --header "Authorization: Bearer eco_YOUR_KEY"

Codex / Claude Desktop / others — add to the client's MCP servers configuration:

{
  "mcpServers": {
    "ecolink-gpu": {
      "url": "https://mcp.ecohash.com/gpu",
      "headers": { "Authorization": "Bearer eco_YOUR_KEY" }
    }
  }
}

Then ask, in plain words: "launch an RTX Pro 6000 with my SSH key and give me the command", "what GPU instances do I have running?", "stop instance 512".

If the key is wrong or has no Compute access, the first tool call returns the same sentence the API gives (for example "this API key has no compute scope — create a key with Compute access enabled").

Tools

GPU instances

Tool	What it does	Cost
`list_gpu_availability`	Regions, GPU types, how many are free, what one GPU comes with, price per hour	free
`get_balance`	Your available credit	free
`quote_instance`	What a launch will hold now and cost per hour after	free
`list_instances`	Your instances, with status and SSH command	free
`get_instance`	One instance: status, SSH command, service URL, credit held	free
`create_instance`	Launch. Defaults to no end time (billed hourly until you stop it) and to the GPU Base platform image (has OpenSSH). Pass an SSH public key to get an SSH command back; pass `cloud_drives` / `shared_filesystems` ids to mount storage	holds credit
`extend_instance`	Add hours to a fixed-duration instance	holds credit
`terminate_instance`	Stop it; GPUs released, unused held credit refunded	irreversible

GPU clusters

Tool	What it does	Cost
`list_clusters`, `get_cluster`	Your clusters; one cluster with its replicas and attached filesystems	free
`create_cluster`	2–8 replicas, fixed duration, optional new or existing shared filesystem	holds credit for the whole run
`scale_cluster`	Change the replica count	confirm
`extend_cluster`	Add hours	holds credit
`terminate_cluster`	Stop all replicas	irreversible

Templates

Tool	What it does	Cost
`list_templates`	Your saved launch configurations and the public catalogue (instance and cluster templates)	free
`quote_template`	What launching one would hold, in which region, and whether capacity is free	free
`launch_template`	Start an instance or cluster from a template, with optional name / region / duration / SSH key overrides	holds credit

Storage and SSH keys

Tool	What it does	Cost
`list_storage`	Cloud drives, shared filesystems, free capacity per region	free
`create_storage`	A drive or filesystem (50–500 GB) in a region	bills daily until deleted
`delete_storage`	Destroy one (refused while mounted)	irreversible
`list_ssh_keys`, `add_ssh_key`	Saved public keys	free

Every tool that commits money or destroys something requires confirm: true. A well-behaved agent quotes first, tells you the amount, and only confirms after you agree — the tool descriptions say so, and your client also asks before running a tool with side effects.

Deliberately not tools: a terminal, file upload, file browse, folder export. Once an instance is running, the agent works over SSH, which is a better terminal than any tool.

Limits

On top of the API's rate limits, the MCP server caps what one key can commit through it: 20 launches per hour and $200 of estimated holds per day per key. Above that a tool call is refused with a message saying so, and nothing is charged. Contact us if you need more.

Security notes

The server holds no credentials. Your key travels in the request header and is used for that request only.
The key lives in your client's configuration file. Revoke it from the console's API Keys page at any time; create a separate key for the agent rather than reusing one from a production service.
Nothing the agent does bypasses your account's limits: the same holds, the same GPU cap, the same membership rules as the console.

Connect​

Tools​

Limits​

Security notes​

Connect

Tools

Limits

Security notes