Head to head
mcpm vs Codexbox
Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.
mcpm
Bio.github.getmcpm/cliNo reviews yet
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
Full listingNo reviews yet
Self-hosted MCP server: run OpenAI Codex CLI prompts and manage workspace files.
Full listingThe short version
Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. Both score close on the safety scan (83 and 88 out of 100). mcpm has noticeably more public adoption.
| mcpm | Codexbox | |
|---|---|---|
| User rating | No reviews yet | No reviews yet |
| Safety grade | B83/100 | A88/100 |
| Adoption | Growing | New |
| GitHub stars | 3 | 0 |
| Downloads / week | 349 | – |
| Runs where | Your machine (local) | Your machine (local) |
| Gateway-ready | No | No |
| Tools | 10 | — |
| Write actions | 1 | — |
| Price per call | Free | Free |
| Licence | MIT | WTFPL |
| Last release | 2026-09-19 | 2026-09-14 |
| Category | AI and agents | AI and agents |