Sanctions AI MCP Server

agentmail gives any AI agent three capabilities it can't provide itself: It exposes all of these through three surfaces - MCP tools (for Claude Code / Cursor / Hermes), an HTTP API (for any agent), and a CLI (for you). Same core, same data. It is available as a remote MCP endpoint.

Teams that work with agent economy, compliance and kya and want a hosted endpoint instead of running a local process. The project is written in HTML.

VERIFIED ACTIVE

LAST COMMIT 2026-09-17 · ★ 2 · #81 OF 90 MAINTAINED EMAIL · VERIFIED 2026-09-18

MIT · HTML · how we verify → /methodology

01 · Install Sanctions AI

before you install - you'll need

AGENTMAIL_COMPLIANCE_PROVIDER is optional or environment-specific per the README.

Claude Code

claude mcp add kindrat86-agentmail --transport http https://sanctionsai.dev/api/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "kindrat86-agentmail": {
      "url": "https://sanctionsai.dev/api/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://sanctionsai.dev/api/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-09-18

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as remote - your agent's requests go to sanctionsai.dev

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license MIT - declared in the repository

registry namespace io.github.kindrat86 is GitHub-verified and matches the repo owner

03 · What Sanctions AI can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.5.0 · 2026-07-18

All notable changes to sanctions-mcp (agentmail) are documented here. · The format follows Keep a Changelog, and this project adheres to Semantic Versioning. · [0.5.0] - 2026-07-18 · Added · agentmail Sanctions…

v0.4.0 · 2026-06-28

What's in this release · Compliance layer (real OFAC data): · sanctions_check - screen wallets/names/countries against 782 crypto addresses + 19,086 names + 16 embargoed jurisdictions · risk_score - pre-payment fraud…

04 · Who maintains Sanctions AI

SanctionsAI is maintained by kindrat86. We track 7 MCP servers from kindrat86 - 6 actively maintained, 8 combined GitHub stars, oldest repo from Apr 2026. Full record: all servers from kindrat86.

  1. GitDealFlow - GitHub signals for startup investors GitHub engineering acceleration signals for venture deal flow across 15 sectors. ★ 6

05 · Facts

category
email - ranked #81 of 90 actively-maintained email servers as of 2026-09-18.
release cadence
2 releases in the last 90 days (latest 2026-07-18)
registry
io.github.kindrat86/sanctionsai (active, first published 2026-08-14)

06 · Sanctions AI FAQ

What is Sanctions AI?

agentmail gives any AI agent three capabilities it can't provide itself: It exposes all of these through three surfaces - MCP tools (for Claude Code / Cursor / Hermes), an HTTP API (for any agent), and a CLI (for you). Same core, same data. It is available as a remote MCP endpoint.

Is Sanctions AI still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-17 and it shipped 2 releases in the last 90 days. We re-verify nightly.

How do I install Sanctions AI?

Run `claude mcp add kindrat86-agentmail --transport http https://sanctionsai.dev/api/mcp`. The README documents one environment variable (AGENTMAIL_COMPLIANCE_PROVIDER) to set first. AGENTMAIL_COMPLIANCE_PROVIDER is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Sanctions AI require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-09-18; you can connect without credentials.

07 · Alternatives to Sanctions AI