carryall-policy-enforcement vs io.github.azender1/safeagent
carryall-policy-enforcement is a plugin bundle for AI coding tools published by tronmongoose. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.azender1/safeagent is an MCP server published by azender1. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-15. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  carryall-policy-enforcement |  io.github.azender1/safeagent |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.3.1 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.22 Downloads/month (PyPI): 458 Downloads/week (PyPI): 72 Forks (GitHub): 4 Stars (GitHub): 7 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | carryall-policy-enforcement | io.github.azender1/safeagent |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 0 (worse) | 7 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 4 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (safeagent-exec-guard) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | 3, secrets among them: 2 | Not published |
| Parts of the bundle (differs) | 2 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/tronmongoose/agent.carryall_plugin | github.com/azender1/safeagent |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
carryall-policy-enforcement
Deterministic IAM control plane for AI agents. Translates natural language intent into minimal-scope Ed25519-signed envelopes. You bring your own data plane. Carryall governs access with least-privilege enforcement and a tamper-evident audit trail.
io.github.azender1/safeagent
Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.
How to run each
carryall-policy-enforcement As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install carryall-policy-enforcement@claude-communityio.github.azender1/safeagent As a local MCP server: PyPI package
claude mcp add --transport stdio safeagent -- uvx safeagent-exec-guardCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of io.github.azender1/safeagent publish no settings it asks for, so we do not compare settings.
What it can do: carryall-policy-enforcement · What it can do: io.github.azender1/safeagent · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.