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.
npx agentmods add instructions/shipstatic/mcp/claude-mdgit clone --depth 1 https://github.com/shipstatic/mcpWhat 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 | $0.09447 | $0.09447 |
| Opus 5 | $0.04723 | $0.04723 |
| Sonnet 5 | $0.01889 | $0.01889 |
| Haiku 4.5 | $0.00945 | $0.00945 |
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.
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_remove → deployments_delete, domains_remove → domains_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.
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.
- 2d ago First seen · 566 lines · 9,447 tokens per session scan A 1ba3375d6cd4
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.
Other instructions, from other repositories
ship CLAUDE.md
Instructions for shipstatic/ship, covering claude.md, architecture, quick reference, key files and comments state the law; this file keeps the story.
ship AGENTS.md
Instructions for shipstatic/ship: Read CLAUDE.md (same directory). It is the single source of truth for this repo's instructions; everything in it applies to every agent, not just Claude. Do not duplicate its content here.
vercel AGENTS.md
Instructions for vercel/vercel, covering agents.md, repository structure, essential commands, changesets and changeset rules.
pinme AGENTS.md
Instructions for glitternetwork/pinme, covering agents.md, project overview, build & dev, architecture and key patterns.
local-studio AGENTS.md
AGENTS.md instructions for sybil-solutions/local-studio: Local Studio is a local-first workstation whose Bun/Hono controller and Next.js/Electron frontend share one controller API for model lifecycle, serving, system state, settings, usage, and agent sessions. Work decisively without asking questions during execution…
bex CLAUDE.md
Instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.