SanctionsAI MCP server
Commit Nov 8, 2026Enables AI agents to perform OFAC sanctions screening, risk scoring, and identity verification through compliance, email, and SMS tools.
Also known as kindrat86/agentmail, agentmail
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.1.1
- Last commit
- Nov 8, 2026
- License
- MIT
What is SanctionsAI MCP?
SanctionsAI enables AI agents to perform OFAC sanctions screening, risk scoring, and identity verification through compliance, email, and SMS tools.
Summary generated from the project's README
About SanctionsAI MCP server
SanctionsAI provides a specialized toolkit for AI agents to manage compliance and identity verification during autonomous transactions. It addresses the legal risks of agents interacting with sanctioned entities by offering real-time screening against OFAC data, including 782 crypto wallets and over 19,000 sanctioned names. Developers can integrate these capabilities into agents using Claude Code, Cursor, or Hermes via MCP tools, or through a standalone HTTP API and CLI.
The toolkit is divided into three functional layers. The compliance layer includes tools for sanctions checks, transaction risk scoring, Know-Your-Agent verification, and dispute management. The verification layer provides disposable email inboxes for receiving magic links or OTPs and rentable phone numbers for SMS verification. While the system can be self-hosted for free using open-source data, a hosted API version is available for those requiring managed endpoints, rate limits, and audit logs.
What you can do with it
- 1Verify crypto wallet safetyAn AI agent can check if a specific wallet address is on a sanctions list before sending funds.
- 2Assess transaction riskA developer can request a risk score for a specific counterparty and amount to decide whether to allow a payment.
- 3Handle agent identity verificationAgents can use disposable email addresses to receive one-time passwords during sign-up processes.
Written from the project's README. Every use case is checked against a quote from it.
How to install SanctionsAI MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall SanctionsAI MCP in Claude Code
$ claude mcp add --transport http agentmail https://sanctionsai.dev/api/mcpInstall SanctionsAI MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentmail": {
"url": "https://sanctionsai.dev/api/mcp"
}
}
}Install SanctionsAI MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentmail": {
"type": "http",
"url": "https://sanctionsai.dev/api/mcp"
}
}
}Install SanctionsAI MCP in VS Code CLI
$ code --add-mcp '{"name":"agentmail","type":"http","url":"https://sanctionsai.dev/api/mcp"}'Install SanctionsAI MCP in Codex
$ codex mcp add agentmail --url https://sanctionsai.dev/api/mcpInstall SanctionsAI MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentmail] url = "https://sanctionsai.dev/api/mcp"
Install SanctionsAI MCP in Gemini CLI
$ gemini mcp add -s user --transport http agentmail https://sanctionsai.dev/api/mcpInstall SanctionsAI MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentmail": {
"url": "https://sanctionsai.dev/api/mcp",
"type": "http"
}
}
}Configuration
AGENTMAIL_COMPLIANCE_PROVIDER
| Name | Description | |
|---|---|---|
| AGENTMAIL_COMPLIANCE_PROVIDER | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablekindrat86/agentmail is public and reachablegithub.com/kindrat86/agentmail ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-08github.com/kindrat86/agentmail ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2024-11-05 in 98 msPass
README
View on GitHubSanctionsAI — compliance & verification toolkit for AI agents
Your agent is about to send USDC to a stranger. Is that stranger sanctioned? 782 OFAC crypto wallets · 19,086 sanctioned names · 16 embargoed jurisdictions. No API key. No signup. 30-second setup. Free & open source.
SanctionsAI gives any AI agent three capabilities it can't provide itself:
| Layer | What | Status |
|---|---|---|
| 🛡️ Compliance | OFAC sanctions screen, KYA, transaction risk score, disputes | ✅ Live — real OFAC data |
| Disposable verification inbox (receive OTP/magic links) | ✅ Live | |
| 📱 SMS | Rentable phone numbers (receive SMS/OTP) | ✅ Live (mock free, 5sim/Twilio paid) |
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.
Why this exists
Agents are starting to pay for things (x402, AP2, ACP, Coinbase AgentKit). But every payment rail assumes a human is watching. If your agent autonomously pays a wallet that's on the OFAC Specially Designated Nationals list, that's your legal problem — and the big payment infra players (OpenAI, Stripe, Coinbase) explicitly do not handle per-jurisdiction sanctions screening, Know-Your-Agent, or agent-transaction fraud signals. That's the gap this fills.
agent ──about to pay──▶ sanctions_check(wallet) ──▶ clean? proceed. sanctioned? ABORT.
Quick start (30 seconds)
pip install sanctions-mcp
Option A — use it from an MCP client (Claude Code / Cursor)
// .mcp.json or your client's MCP config
{
"mcpServers": {
"SanctionsAI": {
"command": "python",
"args": ["-m", "agentmail.mcp_server"]
}
}
}
Now your agent can call sanctions_check, risk_score, kya_verify, dispute_open, create_inbox, fetch_code, create_number, fetch_sms, release_number, list_inboxes.
Note: the PyPI package is
sanctions-mcp(the nameSanctionsAIwas taken). The Python import name is stillSanctionsAI.
Option B — use it as an HTTP API
python -m agentmail.api # serves on :8000
# Screen a wallet against real OFAC data — no key, no auth needed for self-host
curl "http://localhost:8000/sanctions?wallet=0x098B716B8Aaf21512996dC57EB0615e2383E2f96"
# → {"matches":[{"list":"OFAC_SDN","match_type":"wallet_exact","confidence":1.0}],
# "clean":false,"provider":"osint"}
curl "http://localhost:8000/risk" -d '{"counterparty_id":"0xabc...","amount":"5000","rail":"x402"}'
# → {"score":0,"recommendation":"decline","reasons":["sanctions_match:OFAC_SDN/..."]}
Option C — use it from the CLI
# Sanctions screen — real OFAC data, no key
python -m agentmail.cli sanctions --wallet 0x098B716B8Aaf21512996dC57EB0615e2383E2f96
# → flagged: OFAC_SDN wallet_exact
python -m agentmail.cli risk 0xabc123def456 5000 --rail x402
python -m agentmail.cli kya my-agent --wallet 0xabc... --wallet-age 400 --domain bot.dev
python -m agentmail.cli compliance-status
# → OFAC SDN: 782 wallets, 19086 names; source=vile/ofac-sdn-list@...
The compliance layer (the part that matters)
Four tools, called before an agent trusts or pays a counterparty:
| Tool | When to call | Returns |
|---|---|---|
sanctions_check(name, wallet, country) |
Cheapest check. Call first. | {matches, clean} |
risk_score(counterparty, amount, ...) |
Right before authorizing payment | {score 0-100, recommendation: allow/review/decline} |
kya_verify(agent_id, evidence) |
Before trusting another agent | {trust_score, verified, flags} |
dispute_open(transaction_id, reason) |
When a paid transaction went bad | {dispute_id, escalation_at} |
Where the data comes from (all public, free, no key)
| Source | What | Refresh |
|---|---|---|
| vile/ofac-sdn-list (GitHub releases) | 782 multi-chain crypto addresses (ETH/USDT/TRX/XBT/...) | daily |
US Treasury OFAC sdn.csv |
19,086 sanctioned individuals & entities | as published |
| Embargoed jurisdictions set | 16 ISO-2 codes under comprehensive OFAC/UN/EU sanctions | tracked manually |
Lists are cached locally (~/.agentmail/cache/, 24h TTL) and refresh from source. If the network is down, a stale cache is used and status() reports degraded: true so you know screening is against older data rather than failing silently.
Providers (swappable backend)
AGENTMAIL_COMPLIANCE_PROVIDER=osint ← default, real OFAC data, free
AGENTMAIL_COMPLIANCE_PROVIDER=mock ← rule-based, for offline tests
AGENTMAIL_COMPLIANCE_PROVIDER=paid ← ComplyAdvantage passthrough (roadmap)
The osint provider does exact + token-subset name matching, exact case-insensitive wallet matching, and ISO-2 country matching. Every match carries a confidence so you can decide how hard to block.
The other two layers (verification toolkit)
Email — a disposable inbox an agent can use to sign up and receive OTP/magic-link verifications (backed by Mail.tm). create_inbox() → address → fetch_code() → OTP.
SMS — a rentable phone number an agent can use for phone/SMS verification. Mock provider works with no key (for dev); AGENTMAIL_SMS_PROVIDER=fivesim AGENTMAIL_FIVESIM_KEY=... goes live with real numbers.
Both share an otp.py extraction brain (regex for codes + magic links) so email and SMS produce the same {code, link} shape.
Self-host vs. hosted
Self-host is fully functional and free — that's what this repo is. Run the MCP server locally or the HTTP API on your own box, screen against real OFAC data, never pay a cent.
Hosted API is live at https://agentmail-api.fly.dev — a managed endpoint with API-key auth, rate limits, and an audit log of every screen (the thing regulators/investors ask for). Free tier: 50 checks/day, no signup (by IP). For higher volume, get an API key → (Dev $19/mo, Team $99/mo — self-serve checkout). 🚀 Launch week: code LAUNCH50 = 50% off your first month (until Nov 15).
# Try the hosted API right now — no key needed:
curl "https://agentmail-api.fly.dev/sanctions?wallet=0x098B716B8Aaf21512996dC57EB0615e2383E2f96"
# → {"matches":[{"list":"OFAC_SDN",...}],"clean":false}
# With an API key:
curl -H "X-API-Key: sk_live_..." "https://agentmail-api.fly.dev/risk" \
-d '{"counterparty_id":"0xabc...","amount":"5000","rail":"x402"}'
Roadmap
- Email inbox (Mail.tm) + SMS/OTP (mock/5sim/twilio) + OTP extraction
- Compliance layer — real OFAC data (osint provider): 782 wallets + 19,086 names
- MCP server (10 tools) + HTTP API + CLI
- SanctionsAI Sanctions Exposure Index (SEI) — proprietary 5-factor framework for scoring AI agent OFAC exposure (2026 report: sanctionsai.dev/research)
- Hosted API with API-key auth + rate limiting (Fly.io)
- Audit log (tamper-evident screen history — the enterprise wedge)
- EU + UN consolidated lists (osint provider, phase 2)
- Paid provider: ComplyAdvantage passthrough (enterprise)
- x402 per-call billing (when agents pay themselves)
SEI: the SanctionsAI Sanctions Exposure Index
The SanctionsAI Sanctions Exposure Index (SEI) is a 5-factor proprietary framework for quantifying an AI agent's OFAC sanctions exposure:
| Factor | Weight | What it measures |
|---|---|---|
| V — Velocity | 30% | Transactions/day the agent can execute unattended |
| J — Jurisdiction overlap | 25% | Fraction of counterparties in/near embargoed regions |
| A — Asset class | 20% | Crypto (highest SDN coverage), fiat, mixed |
| S — Screening posture | 15% | No screen → batch → pre-payment inline → inline + audit |
| D — Disclosure readiness | 10% | Can operator produce a VSD within 5 days? |
Score 10 (min exposure) → 1000 (max). S and D are the two factors you can change today — collapse both from 1→10 with a single inline screening call and a timestamped audit trail. Full report + interactive calculator at sanctionsai.dev.
Cite as: "SanctionsAI Sanctions Exposure Index (SEI), 2026 Agent-Payment Sanctions Exposure Report, sanctionsai.dev" — licensed CC BY 4.0.
Design notes (honest)
- The compliance layer has the real moat. Email/SMS are plumbing a platform could swallow. Sanctions screening tied to agent-transaction history builds a dataset nobody else has, and per-jurisdiction rules are something the big infra players explicitly avoid.
- Self-host is the free tier, not a trap. The value you pay for (eventually) is not the data — it's uptime, freshness, and the audit trail. The data is and will stay public.
- 5sim numbers are shared-after-release. Fine for receiving an OTP, never for 2FA on accounts you intend to keep.
License
MIT — see LICENSE.
Contributing
Issues and PRs welcome. If you're using SanctionsAI in production, I'd love to hear what for.
SanctionsAI MCP questions
How do I add SanctionsAI MCP to Claude Code?
Run claude mcp add --transport http agentmail https://sanctionsai.dev/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add SanctionsAI MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does SanctionsAI require an API key?
No, the self-hosted version and the free tier of the hosted API do not require an API key or signup.
What kind of data is used for sanctions screening?
It uses real OFAC data, including 782 multi-chain crypto addresses and 19,086 sanctioned individuals and entities.
Can I use SanctionsAI for testing purposes?
Yes, you can use a mock provider for offline tests or a mock SMS provider for development.