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/ScopeBlind/scopeblind-gatewayWrote 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/scopeblind/scopeblind-gateway/protect-mcp)<a href="https://agentmods.dev/mcp/scopeblind/scopeblind-gateway/protect-mcp"><img src="https://agentmods.dev/badge/mcp/scopeblind/scopeblind-gateway/protect-mcp/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/scopeblind/scopeblind-gateway/protect-mcp"><img src="https://agentmods.dev/badge/mcp/scopeblind/scopeblind-gateway/protect-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
protect-mcp 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 10d 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
{
"protect-mcp": {
"command": "npx",
"args": [
"-y",
"protect-mcp",
"serve",
"--enforce"
],
"description": "Ed25519 receipt signing + Cedar policy enforcement for tool calls"
}
}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.
- 10d ago First seen · 12 lines scan A 63fb6799c17d
protect-mcp is an MCP server published in the GitHub repository ScopeBlind/scopeblind-gateway (9 stars, last pushed 2mo ago), licensed MIT. 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. It comes from a forked repository.
Other mcp servers, from other repositories
tooltrust-scanner
Scans MCP servers for prompt injection, data exfiltration, and privilege escalation. Runs locally from the tooltrust-mcp npm package.
cyanheads-mcp-server
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets. Runs locally from the @cyanheads/cyanheads-mcp-server npm package. Needs 6 environment variables to run.
scopeblind-mcp
Scan, protect, and monitor APIs from AI coding tools. Device-level rate limiting. Runs locally from the scopeblind-mcp npm package.
sovereign-mcp-gateway
A gating proxy for Model Context Protocol servers: policy, verification and one audit trail across every upstream. Runs locally from the sovereign-mcp-gateway Python package.
shellward
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP. Runs locally from the shellward npm package. Needs 3 environment variables to run.
web-fetcher
MCP server "web-fetcher" as configured in akanthed/SecureAI-Scan. Runs locally from the some-mcp-fetch-server npm package. Needs 1 environment variable to run.