Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://ai.silverbackmarketing.com/api/mcpRun this in your terminal
claude mcp add --transport http ai-readiness https://ai.silverbackmarketing.com/api/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ai-readiness": {
"url": "https://ai.silverbackmarketing.com/api/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"ai-readiness": {
"type": "http",
"url": "https://ai.silverbackmarketing.com/api/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://ai.silverbackmarketing.com/api/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
The registry name was verified with the GitHub account silverbackmarketing, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 5 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Generate a complete suite of AI readiness files (GEO / generative engine optimization) for any website in a single command —
llms.txt,ai.txt, schema, RAG indexes, and more. Install it into Claude, Cursor, Windsurf, GitHub Copilot, Gemini, or Codex with onenpxcommand, or connect over MCP with no install.
📖 Live site & full docs: [ai.silverbackmarketing.com](https://ai.silverbackmarketing.com) · ⭐ Star this repo if it helps you get found by AI.
The AI Readiness Kit is a free, open-source set of 17 structured files you deploy at the root of your website — robots.txt, ai.txt, llms.txt, schema, RAG indexes, and more — that tell ChatGPT, Claude, Gemini, and Perplexity exactly who you are, what you offer, and how to represent you. Generate the whole set, tailored to any site, with a single command. Free forever (MIT); install with npx or run it over MCP with no install.
When someone wants a product recommendation, a service provider, or a straight answer, they often ask ChatGPT, Claude, Gemini, or Perplexity before they ever visit a website. If you are not giving those systems clear, current signals, they guess — and they often guess wrong.
AI readiness files are structured files you deploy at the root of your website to tell AI systems exactly who you are, what you offer, and where to send people. They speak a format AI already understands (the llmstxt.org standard, Schema.org, and emerging AI-crawler conventions), so assistants stop guessing about your brand based on stale training data and start representing you accurately in their answers.
This skill researches any site, classifies its industry, and generates all of those files for you — tailored to that business — in one command.
npx# Global skill install → ~/.agents/skills/ AND ~/.claude/skills/ (default)
npx @silverbackmarketing/ai-readiness install
npx @silverbackmarketing/ai-readiness install --agent agents
npx @silverbackmarketing/ai-readiness install --all
Primary targets:
| Target | Installs to |
|---|---|
skills | ~/.agents/skills/ai-readiness/ and ~/.claude/skills/ai-readiness/ (full skill — SKILL.md + scripts + references) |
agents | ./AGENTS.md — the standard read by Cursor, Codex, and a growing list of agents (adds a delimited block, keeps your existing content) |
claude | ~/.claude/skills/ai-readiness/ only |
For prompt-based agents, `AGENTS.md` is the default and recommended target — most modern agents now read it. Tool-specific files remain available if you prefer them:
| Opt-in target | Installs to |
|---|---|
cursor | ./.cursor/rules/ai-readiness.mdc |
windsurf | ./.windsurf/rules/ai-readiness.md |
copilot | ./.github/copilot-instructions.md (delimited block) |
gemini | ./GEMINI.md (delimited block) |
generic | ./ai-readiness.SKILL.md (paste into any system prompt) |
Non-Claude targets install into the current directory, so run the command from your project root. --all installs Claude + AGENTS.md. Add --force to overwrite, or --dir to change the target. Shared-file installs insert a marked block and update it in place on re-run, so they never clobber your other instructions.
ai-readiness.skill.SKILL.md into the assistant's system prompt or custom instructions.After installing, trigger it with /ai-readiness yoursite.com in Claude, or just ask any agent: *"create AI readiness files for yoursite.com."*
Connect your coding agent to the hosted MCP server instead of installing the skill locally. Same workflow — research a site and generate all the files.
Production: https://ai.silverbackmarketing.com/api/mcp
Example prompts once connected:
Generate AI readiness files for example.com
Use ai-readiness to list all output files Get the file spec for llms.txt from ai-readiness
Cursor — add to .cursor/mcp.json:
{
"mcpServers": { "ai-readiness": { "url": "https://ai.silverbackmarketing.com/api/mcp" } } }
Refresh MCP servers, then ask: *"Use ai-readiness to generate files for example.com"*
Claude Code — add .mcp.json to your project root:
{
"mcpServers": { "ai-readiness": { "type": "http", "url": "https://ai.silverbackmarketing.com/api/mcp" } } }
Or run:
claude mcp add --transport http ai-readiness https://ai.silverbackmarketing.com/api/mcp
Restart the session, run /mcp, then ask: *"Generate AI readiness files for mysite.com using ai-readiness"*
VS Code / Copilot — add to .vscode/mcp.json:
{
"servers": { "ai-readiness": { "type": "http", "url": "https://ai.silverbackmarketing.com/api/mcp" } } }
Open MCP: List Servers, confirm ai-readiness is running, then use agent mode in Copilot Chat.
Claude Desktop — use mcp-remote in ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": { "ai-readiness": { "command": "npx", "args": ["-y", "mcp-remote", "https://ai.silverbackmarketing.com/api/mcp"] } } }
Fully quit and reopen Claude Desktop after saving.
OpenAI Codex — add to ~/.codex/config.toml:
[mcp_servers.ai-readiness]
url = "https://ai.silverbackmarketing.com/api/mcp" enabled = true
Or run codex mcp add ai-readiness --url https://ai.silverbackmarketing.com/api/mcp, then /mcp in a session.
Antigravity — Agent panel → … → MCP Servers → Manage → View raw config:
{
"mcpServers": { "ai-readiness": { "serverUrl": "https://ai.silverbackmarketing.com/api/mcp" } } }
Antigravity uses serverUrl (not url). Save, refresh, then try in agent mode.
Perplexity — two ways to use the kit:
| Field | Value |
|---|---|
| Name | AI Readiness |
| MCP Server URL | https://ai.silverbackmarketing.com/api/mcp |
| Authentication | None |
| Transport | Streamable HTTP |
Check the acknowledgement box, click Add, then click the connector card to enable it. Ask: *"Use ai-readiness to generate files for example.com."* (Full steps: Perplexity's Adding Custom Remote Connectors guide.)
SKILL.md into a thread (or attach it), then ask: *"Using these AI readiness instructions, generate AI readiness files for example.com."*Quick test:
curl -X POST 'https://ai.silverbackmarketing.com/api/mcp' \
-H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":1}'
More client configs: ai.silverbackmarketing.com/#mcp
Run /ai-readiness yoursite.com and the AI will research the site, classify its industry, and generate production-ready files that tell AI systems (ChatGPT, Claude, Gemini, Perplexity, and others) exactly what the site is, what it offers, and where to send users.
When deployed to a web root, these files improve how a site appears in AI-generated answers, summaries, and recommendations — a must-have for any business that wants to show up in the AI-driven web.
The skill generates 18 files. Of these, 17 deploy to your web root across 7 categories (16 if you omit the optional .well-known/ai-plugin.json); the 18th, README.md, is project documentation for your team. This matches the 17-file kit described on the live site.
| # | File | Purpose | Deployed |
|---|---|---|---|
| 1 | ai.txt | Primary AI identity declaration | ✅ |
| 2 | llms.txt | Concise LLM-readable site summary | ✅ |
| 3 | llms-full.txt | Comprehensive LLM knowledge base | ✅ |
| 4 | ai-sitemap.xml | AI-optimized sitemap | ✅ |
| 5 | sitemap.md | Human-readable sitemap for AI context | ✅ |
| 6 | ai-entities.json | Structured entity definitions | ✅ |
| 7 | ai-intent.json | User intent and query mappings | ✅ |
| 8 | ai-schema.json | Schema.org structured data | ✅ |
| 9 | rag-index.json | RAG retrieval knowledge base | ✅ |
| 10 | rag-index.jsonl | JSONL format for embedding pipelines | ✅ |
| 11 | ai-disclosure.txt | AI content transparency statement | ✅ |
| 12 | training-data-policy.txt | Data usage and training policy | ✅ |
| 13 | .well-known/ai-plugin.json | Plugin manifest for AI agents (optional) | ➖ |
| 14 | structured-data-guide.md | Implementation guide for developers | ✅ |
| 15 | manifest.json | Web app manifest | ✅ |
| 16 | deployment-checklist.md | Step-by-step deployment guide | ✅ |
| 17 | robots.txt | AI crawler directives | ✅ |
| 18 | README.md | Project documentation (not deployed) | ➖ |
In Claude Cowork, type:
/ai-readiness yoursite.com
Or use natural language:
create AI readiness files for aOnly the beginning is shown; read the rest in the repo