What is ovh-api-mcp CLAUDE.md?

Instruction files for a Rust MCP server that connects to the OVH API. OVH is a cloud and internet-services provider; this server lets an agent search services and run API operations through a controlled JavaScript environment.

Use them when building, testing, linting, formatting, or running the OVH API MCP server locally.

They give coding agents the project’s commands, architecture, conventions, security limits, and required environment setup.

How davidlandais/ovh-api-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to davidlandais/ovh-api-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/davidlandais/ovh-api-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/davidlandais/ovh-api-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/davidlandais/ovh-api-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/davidlandais/ovh-api-mcp/claude-md)

Your own site

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

Per session 738 This file is loaded in full into every session.

When invoked 738 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	$0.00738	$0.00738
Opus 5.5	$0.00295	$0.00295
Sonnet 5.5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash 063084559373, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ovh-api-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 2mo 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ovh-api-mcp

Native Rust MCP server for the OVH API. Uses the "Code Mode" pattern: 2 tools (search + execute), the LLM writes JavaScript executed in a QuickJS sandbox.

Commands

cargo build                      # Build
cargo test                       # 12 tests (6 SpecValidator + 3 security + 3 sandbox)
cargo clippy --all-targets       # Lint (0 warnings required)
cargo fmt --check                # Formatting

docker build -t ovh-api-mcp .    # Docker image (~19 MB)

# Run locally (requires OVH env vars)
ovh-api-mcp --port 3104 --services domain

Architecture

src/
  main.rs      CLI (clap), logging, axum server, graceful shutdown
  tools.rs     MCP tools (search, execute) — rmcp macros #[tool_router] / #[tool_handler]
  sandbox.rs   QuickJS sandbox with resource limits (64 MiB mem, 1 MiB stack, 10s/30s timeout)
  auth.rs      OVH API client (API key SHA1 signature, OAuth2 client credentials, clock sync, SecretString)
  spec.rs      OpenAPI spec fetching, caching, merging, and SpecValidator
  types.rs     MCP input types (JsonSchema)

Conventions

Rust 1.92+, edition 2021
rmcp 1.2 — #[tool_router] / #[tool_handler] / #[tool(name = "...")]
secrecy 0.10 — SecretString (not Secret<String>), .expose_secret() returns &str
Error handling: anyhow in main, CallToolResult::error(...) in tool handlers
Commits: conventional commits (fix:, deps:, docs:, chore:, security:, style:, test:)
CI: cargo fmt + clippy + test + docker build on every push/PR
Release: git tag vX.Y.Z && git push origin vX.Y.Z triggers the automated workflow

Security

QuickJS sandbox with CPU/memory/stack limits
SpecValidator: every API call validated against the OpenAPI spec
Path injection rejected (?, #, ..)
SecretString with zeroize on drop
HTTP redirects disabled (credential leak prevention)
Non-root Docker container (mcpuser)

Environment

OVH API keys are loaded from system environment. No .env file in the repo.

Read the full file on GitHub · 71 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.

2mo ago First seen · 71 lines · 738 tokens per session scan A 063084559373

Subscribe to this mod's changes

ovh-api-mcp CLAUDE.md is an instructions file published in the GitHub repository davidlandais/ovh-api-mcp (3 stars, last pushed 4mo ago), licensed MIT. It adds 738 tokens to every session, about $0.0030 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 2026-08-31.

Cloud DevOps and cloud LLM claude cloud-api dns mcp mcp-server

ovh-api-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ovh-api-mcp CLAUDE.mddavidlandais/ovh-api-mcp	Instructions file	3	4mo ago	MIT	A	738	Claude Code
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

ovh-api-mcp: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ovh-api-mcp

Commands

Architecture

Conventions

Security

Environment

What this file has done since we first saw it

ovh-api-mcp CLAUDE.md compared with instructions from other repositories