What is mcp-microsoft-ads CLAUDE.md?

A project instruction file for an MCP server that connects to Microsoft Advertising's SOAP API, a web service for managing advertising accounts. It documents testing rules, safe two-step changes, and details of the API's data shapes.

Developing and testing Microsoft Advertising integrations, normalizing API responses, building update requests, and applying drafted changes with confirmation.

It helps coding agents avoid mistakes caused by the API's unusual response formats and ensures changes are reviewed before they are applied.

How wvuhskr/mcp-microsoft-ads configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wvuhskr/mcp-microsoft-ads. 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/wvuhskr/mcp-microsoft-ads/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wvuhskr/mcp-microsoft-ads

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/wvuhskr/mcp-microsoft-ads/claude-md/github.svg)](https://agentmods.dev/instructions/wvuhskr/mcp-microsoft-ads/claude-md)

Your own site

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

Per session 795 This file is loaded in full into every session.

When invoked 795 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	$0.00795	$0.00795
Opus 5	$0.00398	$0.00398
Sonnet 5	$0.00159	$0.00159
Haiku 4.5	$0.00080	$0.00080

Measured 10d ago against content hash f85eeebf9381, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-microsoft-ads 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 10d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-microsoft-ads

MCP server for Microsoft Advertising SOAP API (bingads SDK, suds under the hood). Two-phase writes: every mutating tool returns a draft; rails.apply_draft / confirm_and_apply lands it. Rails + audit live in rails.py / audit.py.

Live-verified rules — violate these and the live API breaks, tests won't catch it

suds ONE-CHILD RULE: a *Response element that declares exactly ONE child comes back stripped (the response IS that child); two+ children keep the wrapper. Not recursive — applies to *Response elements only. Explains every unwrapped-shape surprise. Test fakes must encode the suds shape, not the WSDL shape. Full rule: client.partial_errors docstring.
Never write getattr(resp, "Thing", None) or [] — always client.as_list(...). suds collapses single-item arrays to a bare object; as_list normalizes. Every SOAP list read routes through it (swept repo-wide, a5a1dde).
client.blank() is mandatory for Update payloads. Bare SimpleNamespace fails suds serialization. Null fields on a blank()-built Update mean "leave unchanged" (live-proven for Campaign; inferred for other entities).
Type discriminators: criterions use the class name (Type="Location"); Ads use the AdType ENUM (Type="ResponsiveSearch", not the class name). Probe per entity family — don't generalize.
Factory ns prefixes are load-bearing: ns3:ArrayOflong, ns3:ArrayOfstring (campaign mgmt), ns1: (reporting). Wrong prefix = suds silently builds the wrong type.
Docstring status lines are evidence, keep them honest: every write tool states Live-verified … or NOT live-verified … (greppable, append-only). Never claim live verification for a path that hasn't run against the real account through THAT tool.

Testing

.venv/bin/python -m pytest -q (bare python3 lacks bingads). 0 warnings expected — a token-refresh warning in pytest output = a test is hitting the LIVE API (conftest autouse patches account_id/customer_id; new fixtures must not bypass it).
New regression tests must be verified discriminating: fail against pre-fix code (reverse-apply the fix), then pass.
ruff check . must be clean (config in pyproject; pre-commit enforces gitleaks + ruff).

Read the full file on GitHub · 55 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.

10d ago First seen · 55 lines · 795 tokens per session scan A f85eeebf9381

Subscribe to this mod's changes

mcp-microsoft-ads CLAUDE.md is an instructions file published in the GitHub repository wvuhskr/mcp-microsoft-ads (1 stars, last pushed 3d ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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.

Marketing and SEO

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

mcp-microsoft-ads: Instructions file for Claude Code