Compute Connector

Working · 849 ms

com.botrecipe/computev1.0.0 Domain verified

Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.

Cloud & DevOps

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://compute.cloudforbots.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

check_memory

Before a heavy job, send how much memory the machine your agent runs on has free (free -m, os.freemem()) and what you are about to run. Get a memory warning and a verdict: run_local, or offload with the provider to use. Free watch-only logs would_offload for the weekly report; nothing runs.

free_mbnumber, required

Free or available memory right now, in MB (Linux: the "available" column of free -m).

jobstring

The command or a short description, e.g. "npm run build" or "playwright crawl of 40 pages".

hoststring

Optional name of the machine, e.g. "my-laptop".

job_mbnumber

Optional: your own estimate of the job's peak memory in MB. Without it we use a rough guess by job type.

floor_mbnumber

Keep at least this much free. Default 2048.

total_mbnumber

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (8)

check_memory

Argument	Type	Description
job	string	The command or a short description, e.g. "npm run build" or "playwright crawl of 40 pages".
host	string	Optional name of the machine, e.g. "my-laptop".
job_mb	number	Optional: your own estimate of the job's peak memory in MB. Without it we use a rough guess by job type.
free_mb*	number	Free or available memory right now, in MB (Linux: the "available" column of free -m).
floor_mb	number	Keep at least this much free. Default 2048.
total_mb	number

Input schema (JSON)

{
  "type": "object",
  "required": [
    "free_mb"
  ],
  "properties": {
    "job": {
      "type": "string",
      "description": "The command or a short description, e.g. \"npm run build\" or \"playwright crawl of 40 pages\"."
    },
    "host": {
      "type": "string",
      "description": "Optional name of the machine, e.g. \"my-laptop\"."
    },
    "job_mb": {
      "type": "number",
      "description": "Optional: your own estimate of the job's peak memory in MB. Without it we use a rough guess by job type."
    },
    "free_mb": {
      "type": "number",
      "description": "Free or available memory right now, in MB (Linux: the \"available\" column of free -m)."
    },
    "floor_mb": {
      "type": "number",
      "description": "Keep at least this much free. Default 2048."
    },
    "total_mb": {
      "type": "number"
    }
  }
}

delete_provider_key

Pro, owner only: delete a saved provider key by name. Jobs on that key stop working at once.

Argument	Type	Description
name*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string"
    }
  }
}

list_providers

Every provider this connects to, how each one runs, and (with your key) the provider keys you saved: name, provider, fingerprint, default, last used. Never shows a key.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

provider_setup

Step-by-step setup for one provider: where to get the key, what to pass to save_provider_key, links to its docs and price page, and for Modal or Workers Sandbox the bridge code to deploy on your own account.

Argument	Type	Description
provider*	string	vercel, e2b, daytona, modal or workers.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "provider"
  ],
  "properties": {
    "provider": {
      "type": "string",
      "description": "vercel, e2b, daytona, modal or workers."
    }
  }
}

run_job

Pro: run a shell command in a fresh cloud sandbox on your own provider account (vercel (Vercel Sandbox, default), e2b, daytona, modal, workers (Workers Sandbox)) and get the exit code and the last 16 KB of stdout and stderr back. Send small input files with it. The sandbox is created for the job and stopped right after, so nothing idles on your bill. Free watch-only logs would_offload and runs nothing.

Argument	Type	Description
cmd*	string	Shell command, run with bash -lc, e.g. "git clone https://github.com/you/app && cd app && npm ci && npm test".
env	object	Optional non-secret environment variables for the command (strings).
files	array	Optional input files written before cmd runs: [{path, content, encoding?: "base64"}]. 50 files, 500 KB total.
free_mb	number	Optional: memory free on your machine now, for the weekly report.
runtime	string	Vercel only: node24 (default), node22, node26 or python3.13.
provider	string	Name of a saved provider key (default: your default key, else vercel).
template	string	E2B only: template id, default base.
timeout_s	integer

save_provider_key

Pro, owner only: save one provider key, sealed with AES-256-GCM before it reaches the database. Providers: vercel (Vercel Sandbox, default), e2b, daytona, modal, workers (Workers Sandbox). Vercel needs team_id and project_id; Modal and Workers Sandbox need bridge_url (see provider_setup). The key is checked with a read-only call first and is never returned or logged. Free stores nothing.

Argument	Type	Description
name	string	Label for this key, default the provider name. Use it in run_job provider.
token*	string	The provider API key or token (or your bridge token).
api_url	string	Daytona: API base, default https://app.daytona.io/api.
team_id	string	Vercel: team id (team_...).
provider*	string	vercel, e2b, daytona, modal or workers.
bridge_url	string	Modal / Workers Sandbox: https URL of the bridge you deployed.
project_id	string	Vercel: project id or name the sandboxes bill to.
skip_check	boolean	Save without the read-only check (not recommended).

usage_and_upgrade

Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

weekly_report

Plain-English summary of the last 7 days: memory checks, low-memory warnings, jobs that would have been offloaded (free) or ran (Pro) by provider, minutes and failures. Read-only; sends nothing. Needs an API key.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}