mcp CLAUDE.md

Project instructions for ShipStatic's MCP server, which exposes the ShipStatic deployment and domain-management SDK to AI agents. MCP is a standard way for an agent to call tools; this server supports both local stdio and hosted HTTP connections.

In plain words
What is it for?
Use them when developing, documenting, or operating the ShipStatic MCP server and its deployment or domain tools.
Why use it?
They prevent workflows from using outdated environment-variable names, tool names, versions, or authentication assumptions.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/shipstatic/mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/shipstatic/mcp
Per session 9,447 This file is loaded in full into every session.
When invoked 9,447 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.09447 $0.09447
Opus 5 $0.04723 $0.04723
Sonnet 5 $0.01889 $0.01889
Haiku 4.5 $0.00945 $0.00945

Measured 2d ago against content hash 1ba3375d6cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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 · 566 lines

How it starts

The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Claude Code instructions for the ShipStatic MCP Server.

@shipstatic/mcp — MCP server that exposes the ShipStatic SDK to AI agents via stdio. Thin wrapper over @shipstatic/ship. Published to the MCP Registry as com.shipstatic/mcp. Maturity: v1.x — Deployments + Domains (15 tools).

The version says which platform it speaks to: the 1.x MCP is the one that speaks to the 2.x platform. 1.0.0 is a true major for consumers — SHIP_API_KEY is no longer read (every existing server config breaks until its env var is renamed) and the delete tools were renamed (deployments_removedeployments_delete, domains_removedomains_delete), so a saved agent workflow naming the old tool stops resolving.

A hosted Streamable-HTTP variant lives at https://mcp.shipstatic.com, registered alongside this package under the same com.shipstatic/mcp registry entry (see server.json remotes). Source: cloudflare/mcp/ in the monorepo. It serves the same fifteen tools: deployments_upload to anyone, the other fourteen to an OAuth-connected caller (since 2026-08-13 in production). The user-facing strings — tool description, INSTRUCTIONS — must stay coordinated where they overlap; the hosted side documents the divergence boundaries.

README positioning (public docs)

README.md ships to npm, Glama, and the MCP Registry. From the reader's perspective, ShipStatic MCP is one product whose door is the hosted endpoint, with this package as the local alternative for a different NEED — never a bigger feature set. The README never reveals that the hosted variant lives in a separate, private repo (cloudflare/mcp/).

The README opens by telling the reader they probably don't need it (2026-08-15), in a > ⚡ blockquote before anything else — the same shape npm/shipstatic/README.md uses to redirect someone who landed on the alias instead of @shipstatic/ship. The reasoning is identical in both places: a package page's most valuable service to a reader is telling them, immediately, whether they are in the right place. Here that means naming https://mcp.shipstatic.com above the fold and linking down to the local setup for the readers who genuinely want it.

Read the full file on GitHub · 566 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.

  1. 2d ago First seen · 566 lines · 9,447 tokens per session scan A 1ba3375d6cd4

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository shipstatic/mcp (7 stars, last pushed 2d ago), licensed MIT. It adds 9,447 tokens to every session, about $0.0472 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.