# Compute Connector (remote · compute.cloudforbots.com)

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

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `compute.cloudforbots.com`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-botrecipe-compute/compute.md), [page](https://verifymcp.io/servers/com-botrecipe-compute/compute)

## Channel facts

- Endpoint: `https://compute.cloudforbots.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1166 tokens (~145/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_provider_key" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Compute Connector MCP server?

Compute Connector is a hosted endpoint at https://compute.cloudforbots.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-botrecipe-compute 'https://compute.cloudforbots.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-botrecipe-compute": {
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-botrecipe-compute": {
      "type": "http",
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-botrecipe-compute]
url = "https://compute.cloudforbots.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-botrecipe-compute": {
      "type": "remote",
      "url": "https://compute.cloudforbots.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-botrecipe-compute --url 'https://compute.cloudforbots.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-botrecipe-compute:
    url: "https://compute.cloudforbots.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-botrecipe-compute": {
      "Transport": "http",
      "Url": "https://compute.cloudforbots.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-botrecipe-compute -t streamable-http -u 'https://compute.cloudforbots.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-botrecipe-compute": {
      "type": "http",
      "url": "https://compute.cloudforbots.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 63)

First indexed and scored.

## MCP tools (8)

### `check_memory` (~217 tokens)

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.

Input parameters:

- `floor_mb` (number): Keep at least this much free. Default 2048.
- `free_mb` (number, required): Free or available memory right now, in MB (Linux: the "available" column of free -m).
- `host` (string): Optional name of the machine, e.g. "my-laptop".
- `job` (string): The command or a short description, e.g. "npm run build" or "playwright crawl of 40 pages".
- `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.
- `total_mb` (number)

### `run_job` (~299 tokens)

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.

Input parameters:

- `cmd` (string, required): 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.
- `provider` (string): Name of a saved provider key (default: your default key, else vercel).
- `runtime` (string): Vercel only: node24 (default), node22, node26 or python3.13.
- `template` (string): E2B only: template id, default base.
- `timeout_s` (integer): 1-240 seconds, default 120.

### `save_provider_key` (~267 tokens)

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.

Input parameters:

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

### `list_providers` (~48 tokens)

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.

### `delete_provider_key` (~38 tokens)

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

Input parameters:

- `name` (string, required)

### `provider_setup` (~74 tokens)

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.

Input parameters:

- `provider` (string, required): vercel, e2b, daytona, modal or workers.

### `weekly_report` (~58 tokens)

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.

### `usage_and_upgrade` (~37 tokens)

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-botrecipe-compute/compute#diagnostics

## Score history

- 2026-10-17: 63

## Common questions

### What is the Compute Connector MCP server?

Compute Connector is an MCP server listed in the public MCP registry as com.botrecipe/compute. Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee. This page covers its hosted endpoint (https://compute.cloudforbots.com/mcp).

### Is the Compute Connector MCP server safe to use?

Compute Connector scores 63 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Compute Connector MCP server expose?

Compute Connector exposes 8 tools: check_memory, run_job, save_provider_key, list_providers, delete_provider_key, and 3 more. Their descriptions and schemas cost roughly 1,038 tokens of context every time the server is loaded.

### Does the Compute Connector MCP server require authentication?

No. We connected to Compute Connector without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Compute Connector MCP server still maintained?

Compute Connector is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://compute.cloudforbots.com/mcp
- Website: https://compute.cloudforbots.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-botrecipe-compute/compute.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-botrecipe-compute/compute.json
- HTML version of this page: https://verifymcp.io/servers/com-botrecipe-compute/compute