What is saw-mcp AGENTS.md?

Repository instructions for AI coding agents working on Snyk API & Web MCP, a Python package that exposes security-scanning tools through MCP. They describe the project, layout, setup, commands, configuration, and audit logging.

Use them when an AI coding agent is editing, testing, configuring, or reviewing the saw-mcp codebase.

They give an agent the project context and working rules needed to make changes in the repository without guessing its structure or commands.

How snyk/saw-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to snyk/saw-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/snyk/saw-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/snyk/saw-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/snyk/saw-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/snyk/saw-mcp/agents-md)

Your own site

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

Per session 1,968 This file is loaded in full into every session.

When invoked 1,968 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	$0.01968	$0.01968
Opus 5.5	$0.00787	$0.00787
Sonnet 5.5	$0.00394	$0.00394
Haiku 4.5	$0.00197	$0.00197

Measured 1mo ago against content hash 57cff73d3d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

saw-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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Cursor, Claude Code, Copilot, etc.) working in this repo.

What this is

saw-mcp is the Snyk API & Web MCP server — a FastMCP 2.0 Python package that exposes probely_* tools so AI assistants can onboard DAST targets, configure authentication, run scans, and triage findings. It is distributed via PyPI (snyk-apiweb-mcp), the Cursor Marketplace (.cursor-plugin/), and the MCP registry (server.json).

Naming: Snyk API & Web was formerly Probely. The platform API (api.probely.com), console (plus.probely.app), and MCP tool names (probely_*) still use the legacy prefix. Config and env vars use SAW / saw / MCP_SAW_*.

Owner: @snyk/saw_saw-frontend (see .github/CODEOWNERS).

Repo layout

snyk_apiweb/           Python package — server entry point and all MCP tools
  server.py            `main()` / `saw-mcp` console script
  tools.py             FastMCP tool definitions (`probely_*`)
  probely_client.py    HTTP client for api.probely.com (mocked in tests)
  config.py            YAML + env config loading, tool allow/deny lists
  audit.py             Tool-call audit logging
config/
  config.yaml.dist     Committed template — copy to config/config.yaml locally
  saw_rules.mdc        Cursor plugin rules (shipped via .cursor-plugin/)
  skills/              Agent skills for web/API target onboarding workflows
tests/                 pytest suite (network calls mocked — no live API key needed)
scripts/
  dev.sh               FastMCP hot-reload dev server
  package.sh           Build release tarball under dist/
  setup-env.sh         Interactive .env writer (API key)
  setup-playwright.sh  Install playwright-cli + Chromium for web-target smoke tests
docs/installation-guides/   Per-IDE setup docs
.cursor-plugin/        Cursor Marketplace manifest (version must match package)
server.json            MCP registry metadata (version must match package)

User-facing docs: README.md (install), USER_GUIDE.md (tools), prompts.md (example prompts).

Read the full file on GitHub · 171 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 · -1 lines · -10 tokens per session 57cff73d3d9e
1mo ago First seen · 172 lines · 1,978 tokens per session scan A 4bc698da48ef

Subscribe to this mod's changes

saw-mcp AGENTS.md is an instructions file published in the GitHub repository snyk/saw-mcp (8 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,968 tokens to every session, about $0.0079 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 2026-09-09.

Building agents Security

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 · 9,715 tokens

saw-mcp: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

What this is

Repo layout

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

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

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md