mlava/agent-ready-mcp
Install and use the Agent Ready (agent-ready.dev) MCP server to scan any URL for AI agent-readability via MCP tool calls. Activates for "install agent-ready mcp", "set up agent-ready in Claude Desktop / Cursor / Cline / Goose / Continue", "add agent-ready as an MCP tool", "scan this site via agent-ready", "run scan_site / get_scan / ask via MCP". Pick this skill when the user wants tool-native access to Agent Ready — no curl, no fetch wiring. For direct REST access without MCP, use the `agent-ready-api` skill instead.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes that the MCP tools `scan_site`/`get_scan` take a user-supplied `url` and then return scraped text from that target site (e.g., titles/headings/`llms.txt`/`AGENTS.md`) for the agent to summarize, creating indirect prompt-injection exposure if an outsider authors the target page.
Where we found it
agent-ready.dev
domain · 4 sites
The MCP server calls agent-ready.dev to scan a user-supplied URL and returns scraped text (titles, headings, llms.txt, AGENTS.md bodies) from the target site into the agent's context, creating an indirect prompt-injection surface.
SKILL.md
127
return scraped text from the target site (titles, headings, `llms.txt` / `AGENTS.md` bodies, check messages)
SKILL.md
65
| **`scan_site`** | User wants a **fresh scan** of a URL. Takes `url` (required) and optional `pageLimit`.
SKILL.md
85
`scan_site` polls the hosted API for up to ~60 seconds.
SKILL.md
133
package `agent-ready-mcp` (npm) and talks only to `agent-ready.dev`.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill config instructs clients to run "npx -y agent-ready-mcp@latest", which fetches and executes remote code from the npm package (https://www.npmjs.com/package/agent-ready-mcp) at runtime, so this is a runtime external dependency that executes remote code.
Where we found it
agent-ready-mcp
dependency · 3 sites
The plugin instructs clients to run `npx -y agent-ready-mcp@latest`, which fetches and executes the npm package at runtime without pinning a specific version.
SKILL.md
42
"args": ["-y", "agent-ready-mcp@latest"],
SKILL.md
20
The server is published to npm as [`agent-ready-mcp`](https://www.npmjs.com/package/agent-ready-mcp)
SKILL.md
135
(`agent-ready-mcp@latest` or a fixed `@x.y.z`) and verify provenance against the
- Audited
- Security analysis