AgentGuard
io.github.MerchantGuard/agentguard
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Description as published in the official MCP registry.
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 0 | github.com/MerchantGuard/agentguard-mcp |
| Last push | 2026-09-21 | GitHub API |
| Registry version | 0.3.1 · active · updated 2026-09-21 | registry |
| Package | npm: @agentguard-run/mcp | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Connect
npx -y @agentguard-run/mcpCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- agentguard — policy proxy for agent tool calls Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy…
- agentguard47 Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
- agentguard Network-egress firewall for agent tools: check URLs against a declarative policy.
- agentguard MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit…
- AgentGuard — security checks for AI agents Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
Badge for your README
Shows the result of our latest check and links back to this page.
[](https://openforallofus.com/tools/io.github.MerchantGuard/agentguard)Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.MerchantGuard/agentguard.