Head to head
AgentLedger vs mcpm
Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.
AgentLedger
Aio.github.entradox/agent-ledgerNo reviews yet
Meter, cap, and block AI agent spend before the provider is charged.
Full listingmcpm
Bio.github.getmcpm/cliNo reviews yet
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
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 (88 and 83 out of 100). AgentLedger is hosted and callable through the gateway; mcpm runs on your own machine.
| AgentLedger | mcpm | |
|---|---|---|
| User rating | No reviews yet | No reviews yet |
| Safety grade | A88/100 | B83/100 |
| Adoption | Growing | Growing |
| GitHub stars | 0 | 3 |
| Downloads / week | – | 349 |
| Runs where | Hosted (remote) | Your machine (local) |
| Gateway-ready | Yes | No |
| Tools | 12 | 10 |
| Write actions | — | 1 |
| Price per call | Free | Free |
| Licence | MIT | MIT |
| Last release | 2026-09-19 | 2026-09-19 |
| Category | AI and agents | AI and agents |