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/TheBarmaEffect/glassboxWrote 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/thebarmaeffect/glassbox/glassbox-framework)<a href="https://agentmods.dev/mcp/thebarmaeffect/glassbox/glassbox-framework"><img src="https://agentmods.dev/badge/mcp/thebarmaeffect/glassbox/glassbox-framework/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/thebarmaeffect/glassbox/glassbox-framework"><img src="https://agentmods.dev/badge/mcp/thebarmaeffect/glassbox/glassbox-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
glassbox-framework 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
{
"glassbox-framework": {
"command": "npx",
"args": [
"-y",
"@glassbox-framework/mcp"
],
"env": {
"ANTHROPIC_API_KEY": "",
"GLASSBOX_MODEL": "claude-sonnet-4-6",
"GLASSBOX_MAX_TOKENS": "2048",
"GLASSBOX_ECS_MODE": "arithmetic"
}
}
}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 · 15 lines scan A 7fd24f1d476f
glassbox-framework is an MCP server published in the GitHub repository TheBarmaEffect/glassbox (11 stars, last pushed today), 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 2026-08-30.
Other mcp servers, from other repositories
core
MCP server "core" as configured in DariuszNewecki/CORE. Launched with core-admin mcp run. Needs 1 environment variable to run.
agentguard47
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health. Runs locally from the @agentguard47/mcp-server npm package. Needs 2 environment variables to run.
creedspace-mcp-server
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication. Runs locally from the @creedspace/mcp-server npm package.
mettle-mcp
METTLE reverse-CAPTCHA challenges for machine-oriented verification. Runs locally from the mettle-verifier Python package.
warrant-mcp
Write the rules for your AI agent once, in plain English. Deterministic code checks every tool call, and a Claude Code hook blocks the ones your rules forbid. Runs locally from the warrant-mcp npm package.
qorami
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection. Runs locally from the qorami-mcp npm package. Needs 1 environment variable to run.