Achriom Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Achriom Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
Access your Achriom library from Claude, ChatGPT, or any MCP-compatible client.
29 tools · 10 prompts · 5 media types · Free for all accounts
Everything the in-app librarian uses:
Plus 10 librarian prompts that shape how AI engages with your collection.
Requires a paid Claude plan (Pro, Max, Team, or Enterprise).
Requires Developer Mode (Plus or Pro).
mcp.achriom.com/mcpFor Cursor, Windsurf, and any HTTP MCP client, use your personal API key:
https://mcp.achriom.com/mcp?api_key=YOUR_KEYGet your API key from account settings.
The in-app librarian knows things external clients don't — your conversation history, current research focus, how to present results visually. It's built for the experience.
External clients get the raw tools. Capable, but less context. Use the app when you want the full experience. Use MCP when you want your data somewhere else.
Free Achriom account required. MCP access is included on all plans.
For developers and agents: docs/ contains detailed tool and prompt specifications.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.