mcp-threatintel AGENTS.md

mcp-threatintel AGENTS.md is an instructions file for Codex, OpenCode from aplaceforallmystuff/mcp-threatintel. It costs 532 tokens per session, scanned A, original, MIT.

Repository guidance for a server that combines threat-intelligence data from services such as OTX, AbuseIPDB, GreyNoise, and abuse.ch. It explains the TypeScript setup, build commands, API keys, and lookup tools that appear when keys are available.

In plain words
What is it for?
Use it when changing IP, domain, hash, or URL lookups; source-specific integrations; API-key configuration; status reporting; or dynamic tool registration.
Why use it?
It clarifies which threat-data sources and tools are always available or depend on specific API keys.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add instructions/aplaceforallmystuff/mcp-threatintel/agents-md
Clone the repo
git clone --depth 1 https://github.com/aplaceforallmystuff/mcp-threatintel

Made for: 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 mcp-threatintel AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aplaceforallmystuff/mcp-threatintel/agents-md.svg)](https://agentmods.dev/instructions/aplaceforallmystuff/mcp-threatintel/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aplaceforallmystuff/mcp-threatintel/agents-md"><img src="https://agentmods.dev/badge/instructions/aplaceforallmystuff/mcp-threatintel/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 532 This file is loaded in full into every session.
When invoked 532 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00532 $0.00532
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 6d ago against content hash 4cd9a2e47d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-threatintel 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 6d 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.

AGENTS.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - mcp-threatintel

MCP server for unified threat intelligence across multiple sources (OTX, AbuseIPDB, GreyNoise, abuse.ch).

Tech Stack

  • Language: TypeScript
  • Runtime: Node.js (ES modules)
  • Protocol: Model Context Protocol (MCP)
  • Build: TypeScript compiler (tsc)

Architecture

src/
  index.ts          # Server, multi-source config, dynamic tool registration, all handlers

Development Commands

npm run build       # tsc
npm run watch       # tsc --watch

Environment Variables

Variable Required Description
OTX_API_KEY No AlienVault OTX API key
ABUSEIPDB_API_KEY No AbuseIPDB API key
GREYNOISE_API_KEY No GreyNoise API key
ABUSECH_AUTH_KEY No abuse.ch auth key (URLhaus, MalwareBazaar, ThreatFox)

Tools (up to 17, dynamic based on which keys are set)

Always available: threatintel_status, threatintel_lookup_ip, threatintel_lookup_domain, threatintel_lookup_hash, threatintel_lookup_url, feodo_tracker With AbuseIPDB key: abuseipdb_check With OTX key: otx_get_pulses, otx_search_pulses With GreyNoise key: greynoise_ip With abuse.ch key: urlhaus_lookup, urlhaus_recent, malwarebazaar_hash, malwarebazaar_recent, malwarebazaar_tag, threatfox_iocs, threatfox_search

Key Patterns

  • Uses Server class from MCP SDK (low-level API with setRequestHandler)
  • Dynamic tool registration: tools added to TOOLS array based on which API keys are present
  • Unified lookups query all configured sources, catch per-source errors, return partial results
  • apiRequest<T>() generic helper for all external API calls
  • No keys required to start (warns but continues with available sources)

Pre-Publish

Run /publish-mcp before any npm publish — mandatory pipeline that handles tests, secret scan, sanitize, docs check, version bump, tag, push, and publish in strict order. Do not run npm publish directly.

Read the full file on GitHub · 54 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. 6d ago First seen · 54 lines · 532 tokens per session scan A 4cd9a2e47d16

Subscribe to this mod's changes

mcp-threatintel AGENTS.md is an instructions file published in the GitHub repository aplaceforallmystuff/mcp-threatintel (7 stars, last pushed 24d ago), licensed MIT. It adds 532 tokens to every session, about $0.0027 per session on Opus 5. 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.