Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Garl-Protocol/garlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/garl-protocol/garl/mcp-server-agent-trust)<a href="https://agentmods.dev/mcp/garl-protocol/garl/mcp-server-agent-trust"><img src="https://agentmods.dev/badge/mcp/garl-protocol/garl/mcp-server-agent-trust/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/garl-protocol/garl/mcp-server-agent-trust"><img src="https://agentmods.dev/badge/mcp/garl-protocol/garl/mcp-server-agent-trust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-trust scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"agent-trust": {
"command": "npx",
"args": [
"-y",
"@garl-protocol/mcp-server"
],
"env": {
"GARL_API_KEY": "",
"GARL_AGENT_ID": "",
"GARL_API_URL": ""
}
}
}What else server.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 14 lines scan A a3a6ae5d4ccd
agent-trust is an MCP server published in the GitHub repository Garl-Protocol/garl (2 stars, last pushed 28d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
agent-economy-os
MCP server "agent-economy-os" as configured in agentrails/agent-economy-os. Launched with https://agent-economy-os-production.up.railway.app.
cotal
MCP server "cotal", hosted remotely at cotal.ai, as configured in Cotal-AI/Cotal.
froglet
MCP server for local Froglet verifiable compute, signed receipts, settlement, and service publication. Runs locally from the froglet-mcp npm package. Needs 5 environment variables to run.
agent-commerce-mcp
Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program. Runs locally from the agent-commerce-mcp npm package.
mcp-a2a-bridge
Bidirectional bridge between MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocols. Runs locally from the mcp-a2a-bridge Python package.
mcp
MCP server "mcp", hosted remotely at astranl.com, as configured in ASTRANL/astranl-mcp.