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.
npx agentmods add instructions/aplaceforallmystuff/mcp-threatintel/agents-mdgit clone --depth 1 https://github.com/aplaceforallmystuff/mcp-threatintelWrote 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.
[](https://agentmods.dev/instructions/aplaceforallmystuff/mcp-threatintel/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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
Serverclass from MCP SDK (low-level API withsetRequestHandler) - Dynamic tool registration: tools added to
TOOLSarray 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.
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.
- 6d ago First seen · 54 lines · 532 tokens per session scan A 4cd9a2e47d16
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.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.