Compute Connector
com.botrecipe/computeVersion 1.0.0Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.
Status
Responds310 msAnswered our handshake without sign-in.- Last checked
- Nov 14, 2026, 13:49 UTC
- Latency
- 310 ms
- Remotes responding
- 1 of 1
- Sign-in
- No sign-in
- Hosting
- Hosted outside the EU (detected)
- Registry data as of
- Nov 14, 2026, 21:12 UTC
Data from the official MCP Registry, checked by run.zero. How we check
Connect
Streamable HTTP
https://compute.cloudforbots.com/mcpResponds310 msNo sign-in
Claude Code
claude mcp add --transport http compute https://compute.cloudforbots.com/mcpClaude Desktop and claude.ai
Settings > Connectors > Add custom connector
Name: compute
Remote MCP server URL: https://compute.cloudforbots.com/mcpCursor
{
"mcpServers": {
"compute": {
"url": "https://compute.cloudforbots.com/mcp"
}
}
}VS Code
code --add-mcp '{"name":"compute","type":"http","url":"https://compute.cloudforbots.com/mcp"}'Built your own server? run.zero hosts MCP servers on European infrastructure.
Tools
8 tools
Read-only | Idempotent | Open world | ||
|---|---|---|---|---|
check_memoryBefore 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. | Not declared | Not declared | Not declared | Not declared |
delete_provider_keyPro, owner only: delete a saved provider key by name. Jobs on that key stop working at once. | Not declared | Not declared | Not declared | Not declared |
list_providersEvery 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. | Not declared | Not declared | Not declared | Not declared |
provider_setupStep-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. | Not declared | Not declared | Not declared | Not declared |
run_jobPro: 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. | Not declared | Not declared | Not declared | Not declared |
save_provider_keyPro, 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. | Not declared | Not declared | Not declared | Not declared |
usage_and_upgradeShow today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered. | Not declared | Not declared | Not declared | Not declared |
weekly_reportPlain-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. | Not declared | Not declared | Not declared | Not declared |
Details
- Registry status
- Active
- Published
- Oct 17, 2026
- Updated
- Oct 17, 2026
- Repository
- Not given
- Categories (suggested)
- Cloud and infrastructureKnowledge and notesSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
- GDPR
- Not declared