Compute Connector vs MCP Run Python
A side-by-side look at the Compute Connector and MCP Run Python MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
C
Compute ConnectorCode Execution · Remote HTTP/SSELow on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.51GoodAuth: not declaredVerdict: choose Compute Connector for code execution work over a hosted endpoint; choose MCP Run Python for code execution. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
CChoose Compute Connector when
- You need dedicated capabilities in the Code Execution domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
check_memory, run_job, save_provider_key.
Choose MCP Run Python when
- You need dedicated capabilities in the Code Execution domain.
- Its auth model fits you: No auth required.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | C Compute Connector | |
|---|---|---|
| Category | Code Execution | Code Execution |
| Quality signal | 51/100 · Good | 43/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Remote HTTP/SSE | — |
| Auth | Not declared | No auth required |
| Pricing | BYOK (pay the provider) | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | — | 20,835 |
| Directory activity | 0 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 8 | Not listed |
| Full listing | View Compute Connector | View MCP Run Python |
Tools & capabilities
Compute Connector tools 8
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.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.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.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.delete_provider_keyPro, owner only: delete a saved provider key by name. Jobs on that key stop working at once.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.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.usage_and_upgradeShow today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.
MCP Run Python tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Compute Connector
{
"mcpServers": {
"compute-connector": {
"command": "npx",
"args": [
"-y",
"compute-connector"
]
}
}
}
MCP Run Python
No confirmed install command for MCP Run Python yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Compute Connector is categorized under Code Execution and uses a remote HTTP/SSE transport. MCP Run Python belongs to Code Execution and uses an install path we have not confirmed yet. Pick Compute Connector for code execution work and MCP Run Python for code execution.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. MCP Run Python has no confirmed install command yet — follow its own setup instructions.
Compute Connector is bring-your-own-key: usage is billed by the API provider you supply a key for. MCP Run Python is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add compute-connector and pydantic-pydantic-ai-mcp-run-python as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Compute Connector has a quality signal of 51/100 (Good) with 0 views, 0 installs and 0 GitHub stars. MCP Run Python has 43/100 (Fair) with 2 views, 0 installs and 20,835 GitHub stars.