mcp-sanity-images: Instructions file for Claude Code

CLAUDE.md

mcp-sanity-images CLAUDE.md is an instructions file for Claude Code from pijusz/mcp-sanity-images. It costs 717 tokens per session, scanned A, original, MIT.

Repository instructions for mcp-sanity-images, a small Bun-based MCP server that uploads local images to Sanity, a content-management system.

In plain words
What is it for?
Installing, testing, type-checking, running, or extending tools for uploading, browsing, batch-processing, and querying Sanity images.
Why use it?
They explain how configuration, authentication, image references, and standard input/output must work so the server remains compatible with Sanity and MCP.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is pijusz/mcp-sanity-images's own configuration. It tells Claude Code how to work on mcp-sanity-images itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-sanity-images configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pijusz/mcp-sanity-images. 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/pijusz/mcp-sanity-images/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pijusz/mcp-sanity-images

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.

agentmods badge for mcp-sanity-images CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pijusz/mcp-sanity-images/claude-md/github.svg)](https://agentmods.dev/instructions/pijusz/mcp-sanity-images/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pijusz/mcp-sanity-images/claude-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-sanity-images/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.

agentmods 80×15 button for mcp-sanity-images CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pijusz/mcp-sanity-images/claude-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-sanity-images/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 717 This file is loaded in full into every session.
When invoked 717 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00717 $0.00717
Opus 5.5 $0.00287 $0.00287
Sonnet 5.5 $0.00143 $0.00143
Haiku 4.5 $0.00072 $0.00072

Measured 14d ago against content hash 4904aa2f313f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-sanity-images 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 14d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-sanity-images

MCP server for uploading local images to Sanity CMS. Bun for dev; bun run build:npm bundles dist/index.js for the npm package.

See README.md for full documentation.

Quick reference

bun install
bun test
bun run typecheck
bun src/index.ts        # start server on stdio

Architecture

src/
  index.ts              MCP entry point — server setup + stdio transport
  sanity.ts             Sanity REST API helpers (token, upload, mutate, groq)
  update-check.ts       GitHub release check (warns only when a newer version exists)
  utils/register-tool.ts  readTool/writeTool wrappers (registerTool + annotations)
  tools/
    upload.ts           upload_image, upload_and_set
    batch.ts            batch_upload (folder → assets)
    browse.ts           list_images (directory listing)
    query.ts            groq_query (GROQ queries)

Key patterns

  • All tools accept optional projectId/dataset params that override env vars
  • resolveConfig() resolves config: tool params → env vars → defaults
  • getToken() resolves auth: SANITY_TOKEN env → CLI auth (~/.config/sanity/config.json)
  • console.error only — stdout is reserved for JSON-RPC (stdio transport)
  • Sanity API version is pinned in src/sanity.ts (API_VERSION = "2025-02-19"). Since that version the API defaults to the published perspective, so groq() always sends perspective (default raw, overridable via groq_query's perspective param)
  • upload_and_set calls resolvePatchTarget() before uploading: it checks <id>/drafts.<id> with a raw query and choosePatchTarget() picks the ID (exact ID if it exists, else the draft of a never-published doc, else error)
  • imageRef() builds the { _type: "image", asset: { _ref } } structure Sanity expects

Adding a tool

  1. Create src/tools/newtool.ts with a registerXTools(server: McpServer) function
  2. Use readTool(...) or writeTool(...) from src/utils/register-tool.ts (sets MCP annotations)
  3. Import and call register function in src/index.ts
  4. Add test in test/

Read the full file on GitHub · 67 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. 14d ago Changed · +3 lines · +151 tokens per session 4904aa2f313f
  2. 15d ago Changed · +2 lines · +62 tokens per session d765b4a0d040
  3. 2mo ago First seen · 62 lines · 504 tokens per session scan A ec4135700584

Subscribe to this mod's changes

mcp-sanity-images CLAUDE.md is an instructions file published in the GitHub repository pijusz/mcp-sanity-images (1 stars, last pushed 14d ago), licensed MIT. It adds 717 tokens to every session, about $0.0029 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.

Related

mcp-sanity-images CLAUDE.md compared with instructions from other repositories

mcp-sanity-images CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-sanity-images CLAUDE.mdpijusz/mcp-sanity-imagesInstructions file114d agoMITA717Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode