What is catalyst-sdwan-super-mcp CLAUDE.md?

Project-specific instructions for a Python server that exposes Cisco Catalyst SD-WAN Manager, a network management system, through MCP tools. The server reads the service's OpenAPI description at startup instead of generating code.

Working on the catalyst-sdwan-super-mcp project, including its Python code, tests, documentation, dynamic API loading, and development setup.

It gives the coding agent the project's goals, architecture, tools, setup commands, and testing conventions. This reduces guesswork when changing or reviewing the server.

How thomaschristory/catalyst-sdwan-super-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thomaschristory/catalyst-sdwan-super-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/thomaschristory/catalyst-sdwan-super-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thomaschristory/catalyst-sdwan-super-mcp

Made for: Claude Code.

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/thomaschristory/catalyst-sdwan-super-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/thomaschristory/catalyst-sdwan-super-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thomaschristory/catalyst-sdwan-super-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thomaschristory/catalyst-sdwan-super-mcp/claude-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/thomaschristory/catalyst-sdwan-super-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thomaschristory/catalyst-sdwan-super-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,911 This file is loaded in full into every session.

When invoked 6,911 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	$0.06911	$0.06911
Opus 5	$0.03455	$0.03455
Sonnet 5	$0.01382	$0.01382
Haiku 4.5	$0.00691	$0.00691

Measured 8d ago against content hash 53cd203d7a39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

catalyst-sdwan-super-mcp CLAUDE.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.

CLAUDE.md · 535 lines

How it starts

The opening of the file, as written. The whole thing — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — catalyst-sdwan-super-mcp

Project goal

A FastMCP server that exposes the Cisco Catalyst SD-WAN Manager (vManage) REST API as MCP tools, with dynamic spec loading so it stays in sync as the API evolves across versions. No codegen — everything is derived from the upstream OpenAPI spec.

Public repo: https://github.com/thomaschristory/catalyst-sdwan-super-mcp. Docs: https://thomaschristory.github.io/catalyst-sdwan-super-mcp/.

Stack

Python ≥ 3.11 (CI: 3.11, 3.12, 3.13 on Linux + macOS)
Packaging: pyproject.toml (hatchling), managed with uv
MCP framework: fastmcp
HTTP client: httpx2 (async) — Pydantic's maintained continuation of httpx (#99)
Config parsing: pyyaml + python-dotenv
Tests: pytest, pytest-asyncio, and tests/mocking.py (a respx-shaped router over httpx2.MockTransport — respx cannot mock httpx2)
Lint / format: ruff
Docs: zensical (reads mkdocs.yml natively), deployed to GitHub Pages

Setup:

uv sync --group dev --group docs
uv run sdwan-mcp --help

Architecture

No code generation — dynamic loading

The server reads the OpenAPI spec at startup and registers MCP tools dynamically. Upgrading to a new vManage version = drop a new spec folder + change one config line.

Supported vManage versions

20.15+ only. Pre-20.15 specs are not bundled and not supported — see issue #13 for the analysis. The repo ships 20.15, 20.16, and 20.18 specs; 20.18 is the default.

Adaptive tool splitting

Cisco's spec has thousands of operations. A single tool per section would push the description payload past most clients' per-tool budgets. The loader splits adaptively based on a size cap:

sdwan.max_actions_per_tool: 150 (default; 0 disables splitting).
Algorithm: section → if over cap, split by sub-tag → if a sub-tag is still over cap, recurse on URL path segments at depth 3, 4, 5.
Sibling sub-tags with <4 operations collapse into a single <parent>_misc tool to avoid a long tail of tiny tools.
Buckets still over the cap at depth 5 (or oversized _misc umbrellas) emit a WARNING but are still registered.

Read the full file on GitHub · 535 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.

8d ago First seen · 535 lines · 6,911 tokens per session scan A 53cd203d7a39

Subscribe to this mod's changes

catalyst-sdwan-super-mcp CLAUDE.md is an instructions file published in the GitHub repository thomaschristory/catalyst-sdwan-super-mcp (2 stars, last pushed today), licensed Apache-2.0. It adds 6,911 tokens to every session, about $0.0346 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.

LLM cisco claude fastmcp mcp network-automation

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

catalyst-sdwan-super-mcp: Instructions file for Claude Code