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/JoeyBrar/agentseal-mcpWrote 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/joeybrar/agentseal-mcp/agentseal)<a href="https://agentmods.dev/mcp/joeybrar/agentseal-mcp/agentseal"><img src="https://agentmods.dev/badge/mcp/joeybrar/agentseal-mcp/agentseal/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/joeybrar/agentseal-mcp/agentseal"><img src="https://agentmods.dev/badge/mcp/joeybrar/agentseal-mcp/agentseal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentseal 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 9d 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
{
"agentseal": {
"command": "npx",
"args": [
"-y",
"agentseal-mcp"
],
"env": {
"AGENTSEAL_API_KEY": ""
}
}
}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.
- 9d ago First seen · 12 lines scan A d2027f72a1e9
agentseal is an MCP server published in the GitHub repository JoeyBrar/agentseal-mcp (1 stars, last pushed 4mo 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. 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
mcp-witness
Security testing toolkit for MCP servers and AI agents. Runs locally from the mcp-witness Python package.
org-as-code
MCP server "org-as-code" as configured in SYNTRIAD/org-as-code. Runs locally from the org-as-code Python package.
cloud-audit
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance…
permit0-gmail
MCP server "permit0-gmail", hosted remotely at localhost, as configured in permit0-ai/permit0.
evidence
Counter-signed evidence records for agent commerce: receipts, verification, dispute envelopes. Runs locally from the tersign npm package. Needs 7 environment variables to run.
haltproof
Cryptographically auditable emergency-shutdown orchestration for Slurm, Kubernetes, and IPMI/BMC clusters. Runs locally from the haltproof-cli Python package.