What is sec-mcp AGENTS.md?

Repository instructions for a Python library, command-line tool, and MCP server that check domains, URLs, and IP addresses against security blacklists stored in SQLite. They describe the project layout, commands, package rules, and branch and commit conventions.

They help agents navigate the repository, run its test and build commands from the shared environment guide, follow its Python and packaging conventions, and create correctly named branches and commits.

They give coding agents the project facts and working rules needed to make small, compatible changes. They also clarify that the React landing page is separate from the Python package.

How Montimage/sec-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Montimage/sec-mcp. 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/Montimage/sec-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Montimage/sec-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/montimage/sec-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/montimage/sec-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/montimage/sec-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/montimage/sec-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/montimage/sec-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/montimage/sec-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 640 This file is loaded in full into every session.

When invoked 640 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00640	$0.00640
Opus 5.5	$0.00256	$0.00256
Sonnet 5.5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 1mo ago against content hash 514ea77c4f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sec-mcp 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 1mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

sec-mcp — Python library + CLI (and MCP server) that checks domains, URLs and IPs against security blacklists backed by SQLite. react-landing-page/ is a standalone Vite site, not part of the package. import sec_mcp is side-effect free — constructing SecMCP() is what creates the database, log file and scheduler thread (see docs/agent-env.md).

Commands

Build/test/env commands → docs/agent-env.md (single source; also named in CLAUDE.md — do not restate them here)
Package manager: uv — pyproject.toml + uv.lock are authoritative; legacy setup.py/requirements.txt still exist
Python ≥ 3.11 required

Layout

sec_mcp/ — the package; config.json is shipped package data
sec_mcp/tests/ — pytest suite (pytest.ini sets testpaths)
react-landing-page/ — standalone Vite/React site with its own package.json
docs/ — project docs, incl. agent-env.md

Conventions

Minimal diffs; don't refactor beyond the issue's scope
Branch: <type>/<issue>-<slug> (e.g. docs/23-update-api-reference)
Commit: <type>(<scope>): <description> (#<issue>) — issue ref required

Constraints

Don't commit or push to main unless asked
Never commit secrets, .env, credentials, SQLite DBs or *.db-shm/*.db-wal sidecars
Export MCP_DB_PATH to a temp path before constructing SecMCP() in probes — construction writes a DB, log file and scheduler thread (see docs/agent-env.md)

Done when

Build + suite green using the commands in docs/agent-env.md — the suite is fully green since #55; a change is done when it keeps it green and holds the --cov-fail-under=98 CI coverage gate
New behavior has a test

Read when needed

Environment, env vars, probe isolation → docs/agent-env.md
Historical (archived) PRD / task plan → docs/archive/

Token Efficiency

Never re-read files you just wrote or edited. You know the contents.
Never re-run commands to "verify" unless the outcome was uncertain.
Don't echo back large blocks of code or file contents unless asked.
Batch related edits into single operations. Don't make 5 edits when 1 handles it.
Skip confirmations like "I'll continue..." Just do it.
If a task needs 1 tool call, don't use 3. Plan before acting.
Do not summarize what you just did unless the result is ambiguous or you need additional input.

Read the full file on GitHub · 53 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.

1mo ago Changed · +9 tokens per session 514ea77c4f87
1mo ago First seen · 53 lines · 631 tokens per session scan A 4ceb12f05319

Subscribe to this mod's changes

sec-mcp AGENTS.md is an instructions file published in the GitHub repository Montimage/sec-mcp (4 stars, last pushed today), licensed Apache-2.0. It adds 640 tokens to every session, about $0.0026 per session on Opus 5.5. 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 2026-09-19.

Commits Git and workflow Security mcp-server security-tools

sec-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sec-mcp AGENTS.mdMontimage/sec-mcp	Instructions file	4	today	Apache-2.0	A	640	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sec-mcp: Instructions file for Codex