agentmods.dev

squarespace-mcp CLAUDE.md

squarespace-mcp CLAUDE.md is an instructions file for coding agents from timncox/squarespace-mcp. It costs 2,672 tokens per session, scanned A, original, MIT.

A set of instructions for developing and debugging a Squarespace MCP server. Squarespace is a website-building platform, and MCP lets AI tools interact with external services.

In plain words
What is it for?
Working on tools that edit Squarespace sites, rebuilding and testing the server, re-authenticating sessions, and checking API changes.
Why use it?
It gives agents project-specific guidance about commands, architecture, authentication, sessions, and common 401 errors.

Instructions file

not rated 3 27d ago A scan 2,672 tokens original MIT
View the source file timncox/squarespace-mcp
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/timncox/squarespace-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/timncox/squarespace-mcp

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.

agentmods badge for squarespace-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timncox/squarespace-mcp/claude-md.svg)](https://agentmods.dev/instructions/timncox/squarespace-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timncox/squarespace-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/timncox/squarespace-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,672 This file is loaded in full into every session.
When invoked 2,672 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 $0.02672 $0.02672
Opus 5 $0.01336 $0.01336
Sonnet 5 $0.00534 $0.00534
Haiku 4.5 $0.00267 $0.00267

Measured 4d ago against content hash 6e96086db51c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squarespace-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 4d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squarespace MCP — CLAUDE.md

What This Project Is

MCP server that edits Squarespace websites via the Content Save API. Exposes 134 tools for text, images, sections, blocks, pages, menus, forms, commerce, navigation, design, code injection, blog posts, gallery management, PDF menu parsing, section snapshots, Wayback Machine recovery, and more. Used from Claude Desktop and Claude Code (usually parked — revive via /mcp-revive squarespace).

Commands

npm run mcp     # Start MCP server (tsx src/mcp-server/index.ts)
npm run build   # TypeScript compile — the parked MCP config runs dist/, so rebuild after src changes
npm test        # vitest run (~1468 tests, 65 files; ~10 auth-tools failures pre-date 19468ed's session-refresh change)
node scripts/relogin.mjs [subdomain...] [--headless]   # re-auth the Squarespace session
node scripts/smoke.mjs [subdomain]                     # endpoint-drift check (read tools vs live API)

Auth & Sessions (read this before debugging 401s)

Auth is cookie-based (storage/auth/sqsp-session.json, a Playwright storageState). The Content API needs a per-site member-session + crumb pair for every site; sessions go stale in ~hours and any browser use of the cookies rotates them, invalidating the stored copy.

  • 401 anywhere → call the sq_relogin tool (headless, no user action) or run node scripts/relogin.mjs <subdomain>. Credentials come from SQSP_EMAIL/SQSP_PASSWORD in .env; no CAPTCHA has ever appeared.
  • Never "fix" a 401 with sq_restore_session right after a fresh login — the .bak is the older, expired session.
  • Endpoint drift is real. Squarespace changes internal APIs under this server. 2026-07-08: injection values moved out of /api/settings (read from /api/config/GetInjectionSettings), and SaveInjectionSettings requires form-encoded header/footer (old injectHeader names were accepted-but-ignored — a silent no-op). 2026-07-19: GET /api/settings started serializing set-type fields as {key: true} maps while PUT /api/settings only accepts the array form the editor UI sends — so read-modify-write PUTs 400 (empty body) until sanitized; see sanitizeSettingsForPut() in content-save/site.ts. When a tool errors or silently no-ops, run scripts/smoke.mjs first, then capture ground truth with scripts/capture-config-api.mjs <subdomain> </config/...> — headless for read traffic, --headful to drive the panel by hand (e.g. click SAVE) while it records every request with full write payloads. Diff the UI's payload against the MCP client's. Note most config panels stage changes and only write on an explicit SAVE click; nothing fires on toggle/typing. Use the trial/sandbox site (sphere-green-b2j7) for write experiments, never a live client site.

Read the full file on GitHub · 151 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. 4d ago First seen · 151 lines · 2,672 tokens per session scan A 6e96086db51c

Subscribe to this mod's changes

squarespace-mcp CLAUDE.md is an instructions file published in the GitHub repository timncox/squarespace-mcp (3 stars, last pushed 27d ago), licensed MIT. It adds 2,672 tokens to every session, about $0.0134 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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