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.
npx agentmods add mcp/kindrat86/agentmail/sanctionsaigit clone --depth 1 https://github.com/kindrat86/agentmailWrote 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/kindrat86/agentmail/sanctionsai)<a href="https://agentmods.dev/mcp/kindrat86/agentmail/sanctionsai"><img src="https://agentmods.dev/badge/mcp/kindrat86/agentmail/sanctionsai.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
sanctionsai 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 4d 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
{ "sanctionsai": { "url": "https://sanctionsai.dev/api/mcp", "type": "streamable-http" } }
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.
- 4d ago First seen · 6 lines scan A 6428e1e5988d
sanctionsai is an MCP server published in the GitHub repository kindrat86/agentmail (1 stars, last pushed today), 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
complyedge
Runtime EU AI Act deny for agent I/O (Article 5, Article 50) — ComplyEdge Python SDK. Runs locally from the complyedge Python package.
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.
sanctions-screening
Sanctions screening against OFAC SDN, company registry verification and trade-restriction checks. Remote server at hatchloop.dev.
appointment-booking
Find real businesses and book appointments. Books via Cal.com; imports 12 platforms. Remote server at hatchloop.dev.
agent-broker
20 tools for sanctions, export-control and company-registry screening, plus messaging. 12 keyless. Remote server at hatchloop.dev.
mcp-custos
MCP server for secure coding and compliance — full MITRE CWE corpus, ISO 27001, NIST 800-53, OWASP ASVS, NIST SSDF, ISO 27017 — with official cross-framework mappings and enforcement hooks. Runs locally from the mcp-custos npm package.