sanctions-screening-mcp-server: Instructions file for Claude Code

AGENTS.md

sanctions-screening-mcp-server AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from cyanheads/sanctions-screening-mcp-server. It costs 7,954 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

A project-specific instruction file for a server that checks names against sanctions lists and identifies registered companies. It explains the server's rules, technical patterns, and safety limits.

In plain words
What is it for?
Guiding changes to the sanctions-screening server, including its screening, company-identification, ownership-tracing, and result-reporting code.
Why use it?
It keeps development consistent and makes clear that possible matches require human verification rather than being treated as final compliance decisions.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cyanheads/sanctions-screening-mcp-server's own configuration. It tells Claude Code, Codex and OpenCode how to work on sanctions-screening-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sanctions-screening-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cyanheads/sanctions-screening-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cyanheads/sanctions-screening-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cyanheads/sanctions-screening-mcp-server

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for sanctions-screening-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyanheads/sanctions-screening-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/cyanheads/sanctions-screening-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cyanheads/sanctions-screening-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/sanctions-screening-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,954 This file is loaded in full into every session.
When invoked 7,954 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 75% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.07954 $0.07954
Opus 5 $0.03977 $0.03977
Sonnet 5 $0.01591 $0.01591
Haiku 4.5 $0.00795 $0.00795

Measured 8d ago against content hash 4aa958134005, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sanctions-screening-mcp-server AGENTS.md 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 8d 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.

Origin

This is a copy

75% identical to obsidian-mcp-server AGENTS.md — 396 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: sanctions-screening-mcp-server Version: 0.1.11 Framework: @cyanheads/mcp-ts-core ^0.12.3 Engines: Bun ≥1.3.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.0.0 (via the framework) Zod: ^4.4.3

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


What This Server Is

Entity screening and resolution over the world's open sanctions data plus the global legal-entity registry, served offline. It screens a name against the consolidated OFAC (SDN + Consolidated), EU, UK (UKSL), and UN sanctions lists at once, and resolves legal entities against the GLEIF LEI database with corporate-ownership tracing.

Screening aid, not a compliance determination. Every tool returns potential matches with a transparent score and source provenance — never a verdict. This framing is load-bearing: it lives in SCREENING_CAVEAT (src/mcp-server/tools/definitions/_shared.ts), in every screening tool's description, and in its output. A hit is a candidate to verify against the official source; an empty result is never a clearance. Preserve it in any edit to the surface.

The data path is a local mirror, not a live API. All five sources are bulk, keyless, and clear for redistribution. They are normalized into two local SQLite + FTS5 mirrors via the framework MirrorService — a sanctions designation mirror with a per-alias name index (Double-Metaphone phonetic keys), and a GLEIF lei_entity mirror with a lei_relationship ownership table. The real corpus loads out-of-band via bun run mirror:init; the read path gates on mirror readiness. Do not commit or modify the populated data/ mirrors — they are environment state, not source.

Match signal is the raw Jaro-Winkler value (0–1) — never a fabricated confidence percentage. Strict matching (exact-normalized → all-tokens-present via FTS5) is the default and the ~90% path; fuzzy (Jaro-Winkler + phonetic) is opt-in or auto-on-empty. Surface only real signal: matchType (exact/strong/approximate), the matched name and its type, the raw score for approximate hits, and queryTokenCoverage — a literal count of the query tokens a candidate explains. Coverage ranks candidates the score ties (one shared exact token pins several at 1.0) and is surfaced so a caller can account for that order; it is a second measurement beside the score, never a term blended into it.

Read the full file on GitHub · 461 lines

Changes

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.

  1. 8d ago First seen · 461 lines · 7,954 tokens per session scan A 4aa958134005

Subscribe to this mod's changes

sanctions-screening-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/sanctions-screening-mcp-server (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 7,954 tokens to every session, about $0.0398 per session on Opus 5. A static security scan graded it A with 0 findings. It is 75% identical to obsidian-mcp-server AGENTS.md, differing in 396 lines, and is treated as a copy.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens