io.github.cyanheads/sanctions-screening-mcp-server

io.github.cyanheads/sanctions-screening-mcp-serverv0.1.7Other

Screen names against OFAC, EU, UK, UN sanctions lists; resolve entities via GLEIF. Screening aid.

In-path gate · all MCP tools

Using io.github.cyanheads/sanctions-screening-mcp-server in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-08-20 18:00 UTC

screened 2026-07-21tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“Declared capability, no hidden instructions”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-29).

Contracts can change after screening, with no version bump. The gate pins io.github.cyanheads/sanctions-screening-mcp-server’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-cyanheads-sanctions-screening-mcp-server)](https://mcpindex.ai/server/io-github-cyanheads-sanctions-screening-mcp-server)

HTML

<a href="https://mcpindex.ai/server/io-github-cyanheads-sanctions-screening-mcp-server"><img src="https://mcpindex.ai/api/v1/badge/io-github-cyanheads-sanctions-screening-mcp-server" alt="mcpindex verdict" height="20" /></a>

Environment variables

MCP_LOG_LEVEL

Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

SANCTIONS_MIRROR_PATH

Filesystem path for the local SQLite mirror. All sources are keyless; no API key is required. Populate the mirror out-of-band with `bun run mirror:init`.

SANCTIONS_FUZZY_MIN_SCORE

Default Jaro-Winkler similarity floor (0-1) for fuzzy matches when the caller omits min_score.

SANCTIONS_FUZZY_MAX_RESULTS

Hard cap on fuzzy candidates scored per query, to bound work on short queries.

MCP_HTTP_HOST

The hostname for the HTTP server.

MCP_HTTP_PORT

The port to run the HTTP server on.

MCP_HTTP_ENDPOINT_PATH

The endpoint path for the MCP server.

MCP_AUTH_MODE

Authentication mode to use: 'none', 'jwt', or 'oauth'.

MCP_LOG_LEVEL

Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

SANCTIONS_MIRROR_PATH

Filesystem path for the local SQLite mirror; a persistent volume on a hosted deployment. All sources are keyless; no API key is required.

SANCTIONS_REFRESH_CRON

Cron for the scheduled refresh of the sanctions lists + name index (HTTP transport only). GLEIF deltas are refreshed manually via mirror:refresh.

SANCTIONS_FUZZY_MIN_SCORE

Default Jaro-Winkler similarity floor (0-1) for fuzzy matches when the caller omits min_score.

SANCTIONS_FUZZY_MAX_RESULTS

Hard cap on fuzzy candidates scored per query, to bound work on short queries.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Other

hood. — .hood name service

ag.hood/name-service

Resolve .hood names on Robinhood Chain — forward/reverse, text records, availability & pricing.

Pre-Trip compliance scanner

agency.kesey/pretrip

Screen regulated-health marketing copy against source-cited rulesets, all 50 states.

agency.lona/trading

AI-powered trading strategy development: backtesting, market data, and portfolio analysis

Install this server

Remote endpoint

Streamable HTTP / SSE endpoint. Add to any MCP client that supports remote servers.

https://sanctions-screening.caseyjhand.com/mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "sanctions-screening-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "@cyanheads/sanctions-screening-mcp-server"
      ],
      "env": {
        "MCP_LOG_LEVEL": "info",
        "SANCTIONS_MIRROR_PATH": "./data/sanctions.db",
        "SANCTIONS_FUZZY_MIN_SCORE": "0.85",
        "SANCTIONS_FUZZY_MAX_RESULTS": "50",
        "MCP_HTTP_HOST": "127.0.0.1",
        "MCP_HTTP_PORT": "3010",
        "MCP_HTTP_ENDPOINT_PATH": "/mcp",
        "MCP_AUTH_MODE": "none",
        "SANCTIONS_REFRESH_CRON": "0 4 * * *"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "sanctions-screening-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "@cyanheads/sanctions-screening-mcp-server"
      ],
      "env": {
        "MCP_LOG_LEVEL": "info",
        "SANCTIONS_MIRROR_PATH": "./data/sanctions.db",
        "SANCTIONS_FUZZY_MIN_SCORE": "0.85",
        "SANCTIONS_FUZZY_MAX_RESULTS": "50",
        "MCP_HTTP_HOST": "127.0.0.1",
        "MCP_HTTP_PORT": "3010",
        "MCP_HTTP_ENDPOINT_PATH": "/mcp",
        "MCP_AUTH_MODE": "none",
        "SANCTIONS_REFRESH_CRON": "0 4 * * *"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- @cyanheads/sanctions-screening-mcp-server

Claude Code (claude mcp add)

claude mcp add --scope user sanctions-screening-mcp-server -- npx -y -- @cyanheads/sanctions-screening-mcp-server

Gemini CLI (gemini mcp add)

gemini mcp add -s user sanctions-screening-mcp-server npx -y -- @cyanheads/sanctions-screening-mcp-server

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-cyanheads-sanctions-screening-mcp-server

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.1.7
category: Other
verdict expires: 2026-08-20
quality: 80 / 100
operator: cyanheads

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Verify it → · or email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 959,933). Verify it yourself.

Links

Repository →

Remote endpoint

https://sanctions-screening.caseyjhand.com/mcp