C

Compute Connector

Checks local memory and offloads shell jobs to short-lived cloud sandboxes through supported providers.

Install Compute Connector

Pick your client, then add it in one click or paste the config.

Streamable HTTP (Remote)
Server URL
https://compute.cloudforbots.com/mcp

Remote servers are added in the app, not the config file: Customize → Connectors → Add custom connector, then paste this URL.

Hosted endpointLive · 3d agoLive Remote EndpointOur automated health check connected to this remote MCP endpoint successfully.Last checked 10/21/2026, 6:30:32 PM

Clients with native remote MCP support can connect directly to this URL.

Remote endpoint
https://compute.cloudforbots.com/mcp

Overview

Compute Connector routes heavy shell jobs from an agent to temporary sandboxes on Vercel, e2b, Daytona, Modal, or Workers Sandbox accounts. Its memory check recommends running locally or offloading based on available memory and the planned command. Provider keys are encrypted before storage, while jobs return exit status plus the final 16 KB of output. Reach for it when local agent hardware cannot reliably handle a task and you want execution billed to your own provider account.

Use cases

  • Check available memory before starting a resource-heavy task
  • Run shell commands in temporary cloud sandboxes
  • Compare supported providers before choosing an execution backend
  • Review weekly offload decisions, runtime, and failures
  • Remove provider credentials when a backend should no longer be used

Key features

  • Memory-based local-versus-cloud execution recommendations
  • Temporary shell job execution across five cloud providers
  • Encrypted provider-key storage with read-only validation
  • Small input-file transfer for Pro jobs
  • Seven-day usage and failure reporting
  • Daily usage visibility and upgrade information

Tools8

What Compute Connector lets your agent do. Expand a tool for its parameters.

Verified live~1.2k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

What it can do

From the 8 tools this server returned when we ran it.

Runs commands · 1Can delete or modify data · 1Handles credentials · 1Read-only tools · 6

Observed 2026-10-21 in an isolated sandbox. A description of reach, not a security audit.

How Compute Connector works

What Compute Connector MCP server does

Compute Connector helps an agent decide whether a task should run on its local machine or in a cloud sandbox. The check_memory tool accepts available-memory information and a description of the planned work, then returns a warning and either a run_local or offload recommendation.

For Pro usage, run_job starts a fresh sandbox with a selected provider, executes a shell command, optionally uploads small input files, and returns the exit code along with the last 16 KB of standard output and standard error. The sandbox is stopped after the job, so the job does not leave an idle runtime running on the provider account.

Supported providers are Vercel Sandbox, e2b, Daytona, Modal, and Workers Sandbox. Vercel is the default provider.

How it works

The server uses provider credentials saved for the account owner. save_provider_key validates a credential with a read-only provider call, encrypts it with AES-256-GCM before it reaches the database, and does not return or log the key. Saved credentials are referenced by name rather than exposed to the agent. list_providers shows provider names, fingerprints, default status, and last-use information without displaying secrets.

Free operation is watch-only for execution-related workflows: memory checks can record jobs that would have been offloaded, and run_job does not execute a command. Pro operation runs the requested job. Weekly reporting summarizes memory checks, warnings, would-offload events or completed jobs, provider usage, minutes, and failures for the previous seven days.

Setup and configuration

Provider credentials are configured through the MCP tools rather than by returning secrets to the caller. Use provider_setup to get provider-specific instructions, credential locations, save parameters, documentation links, and pricing links.

Vercel requires both team_id and project_id when its key is saved. Modal and Workers Sandbox require a bridge_url; their bridge code is provided for deployment on the user’s own account. Provider keys can be removed by name with delete_provider_key, after which jobs using that key stop working.

Tools and capabilities

  • check_memory: evaluates available memory and the planned task.
  • run_job: executes a shell command in a temporary provider sandbox for Pro users.
  • save_provider_key: validates and stores one encrypted provider credential for the owner.
  • list_providers: lists providers and non-secret saved-key metadata.
  • delete_provider_key: removes a saved provider key.
  • provider_setup: provides setup details for a selected provider.
  • weekly_report: returns a read-only seven-day activity summary.
  • usage_and_upgrade: shows daily usage and the upgrade link.

Limitations and notes

The free tier allows 500 calls per day and is not metered. Free execution workflows only record what would have happened; they do not run cloud jobs. weekly_report requires an API key, while usage_and_upgrade can show usage for an API key or IP. Removing a provider key immediately prevents jobs that depend on it from working. Job output is limited to the final 16 KB of stdout and stderr.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Compute Connector

Compute Connector is an MCP server that checks local memory and runs shell jobs in short-lived cloud sandboxes through Vercel Sandbox, e2b, Daytona, Modal, or Workers Sandbox. Its main tools cover memory verdicts, job execution, provider-key management, setup, reporting, and usage.

Compute Connector supports Vercel Sandbox, e2b, Daytona, Modal, and Workers Sandbox. Vercel Sandbox is the default provider. Modal and Workers Sandbox require a bridge URL, while Vercel requires a team ID and project ID during provider-key setup.

Compute Connector encrypts provider keys with AES-256-GCM before storing them and validates each key with a read-only call first. Keys are never returned or logged, and listing providers exposes only metadata such as the key fingerprint and last-used information.

No, the free tier does not execute cloud jobs. It provides watch-only memory and offload logging, while Pro can run commands in temporary sandboxes. The free tier allows 500 calls per day and is not metered.

A completed job returns its exit code and the last 16 KB of standard output and standard error. Pro jobs can also send small input files, and the sandbox is stopped after execution.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCompute Connector AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/compute-connector?style=directory)](https://allmcps.com/mcp/compute-connector)
HTML Embed
<a href="https://allmcps.com/mcp/compute-connector"><img src="https://allmcps.com/api/badge/compute-connector?style=directory" alt="Compute Connector on AllMCPs" /></a>