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/first3things/optimizely-cms-mcp/claude-mdgit clone --depth 1 https://github.com/first3things/optimizely-cms-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 | $0.02566 | $0.02566 |
| Opus 5 | $0.01283 | $0.01283 |
| Sonnet 5 | $0.00513 | $0.00513 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
optimizely-cms-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 3d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimizely CMS MCP Server Guide
🚀 START HERE - Quick Reference for Claude
When searching for content in Optimizely CMS, ALWAYS follow this workflow:
# Step 1: Get help (if needed)
help({})
# Step 2: Discover available content types
discover({"target": "types"})
# Step 3: Discover fields for the content type you want
discover({"target": "fields", "contentType": "ArticlePage"})
# Step 4: Search using discovered information
search({"query": "your search", "contentTypes": ["ArticlePage"]})
Never use graph-query with guessed field names! Always discover first.
Overview
The Optimizely CMS MCP (Model Context Protocol) server is a multi-tenant, discovery-first integration designed to work with ANY Optimizely CMS instance without requiring hardcoded assumptions about content types, field names, or schema structures.
This server enables AI assistants like Claude to interact with Optimizely CMS through a standardized protocol, providing intelligent content management capabilities while adapting dynamically to each unique CMS configuration.
Core Principles
1. Zero Hardcoding Policy
- No hardcoded content types: No assumptions about "ArticlePage", "StandardPage", etc.
- No hardcoded field mappings: No predefined paths like "SeoSettings.MetaTitle"
- No hardcoded examples: All examples use placeholders that work universally
- Dynamic discovery: Every operation starts by discovering what's actually available
2. Discovery-First Architecture
Every interaction follows this pattern:
- Discover what's available in the CMS
- Analyze the discovered schema to understand requirements
- Execute operations using the discovered information
- Validate results against the discovered constraints
3. Multi-Tenant Design
- Works with any Optimizely CMS instance
- Adapts to custom content types and fields
- Supports different localization strategies
- Handles various composition patterns
Optimizely API Integration
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.
- 3d ago First seen · 297 lines · 2,566 tokens per session scan A 16abd3383c93
optimizely-cms-mcp CLAUDE.md is an instructions file published in the GitHub repository first3things/optimizely-cms-mcp (6 stars, last pushed 10mo ago), licensed MIT. It adds 2,566 tokens to every session, about $0.0128 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
payload CLAUDE.md
Instructions for payloadcms/payload, covering claude.md, project structure, key directories, architecture notes and quick start.
payload AGENTS.md
Instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.
tinkerpop AGENTS.md
Instructions for apache/tinkerpop, covering agents.md, primary guidance: agent skills, planning and memory: beads, canonical documentation and licensing and provenance.
graphiti AGENTS.md
Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
msagljs copilot-instructions.md
Instructions for microsoft/msagljs, covering copilot instructions for msagl-js, project overview, build, test, and lint, architecture and core data model (@msagl/core).
microfeed AGENTS.md
AGENTS.md instructions for microfeed/microfeed, covering repository guidance, development workflow, instance management and cloudflare deployment, source architecture and theme repositories.