- Home
- Skills
- Agents & Orchestration
- agent-ready-mcp
More screenshots
Works with the AI Agents you already use
Agent Ready Mcp
Audit any website for AI agent-readability via native MCP tool calls.
Free
agent-ready-mcp
Example session with this skill installed
Install the agent-ready mcp server in my Claude Desktop config and scan https://example.com/docs to see if it's agent-ready.
- Read your context and instructions
- Compiled the agent-ready-mcp
I've updated your Claude Desktop config with the Agent Ready MCP server.
Scan Result for example.com:
Score: 78/100 (Good)
llms.txt: Missing (Check L1)
Manifests: robots.txt found, but missing /ai-plugin.json (Check C2)
Top Fix: Add an llms.txt to the root to provide structured context.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The Agent Ready MCP skill equips your AI agent with the tools to audit any website for AI readiness. It installs the official Model Context Protocol (MCP) server, allowing your agent to run deep scans, retrieve historical reports, and query the Agent Ready knowledge base directly through native tool calls.
Why use this skill
Modern AI agents struggle with websites designed only for humans. This skill automates the technical discovery required to make your site "agent-friendly." By integrating via MCP, your agent avoids manual HTTP wiring or curl commands and gains access to specialized prompts for interpreting scan results and generating remediation plans.
Supported tools & workflows
- scan_site: Validates 60+ agent-readability signals (llms.txt, manifests, etc.).
- get_scan: Retrieves existing reports using a scan ID for historical comparison.
- ask: A local RAG tool to query definitions for specific agent-readability checks.
- Workflow Prompts: High-level wrappers for scanning, interpretation, and building prioritized fix-it docs.
Professional output
The skill produces structured summaries including an overall readability score (0–100), rating bands (e.g., "Excellent"), and a breakdown of failing technical checks with specific "How to Fix" instructions.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
- Requires Pro API key for scans.
- scan_site tool may timeout after 60s (requires get_scan callback).
- Limited to 10 requests per minute.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
6 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 months ago
- Free with an Agensi account
- Software
- Agent Ready MCP
Node.js