
Psyseal scan
Offline check of your AI agent: heartbeat cost, plaintext keys, planted or bloated memory.
- tool
- 1
- transport
- STDIO
- last updated
- Nov 9, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
scan_agentsThe same scan as one read-only tool, `scan_agents`, over stdio.
The same scan as one read-only tool, `scan_agents`, over stdio.
No parameter schema in public metadata yet.
Sponsors
Readme
psyseal-scan
The free Psyseal scanner. MIT-0.
It reviews the AI agents on your computer (OpenClaw, Hermes Agent, nanobot, PicoClaw, ZeroClaw, NanoClaw or any agent folder) and tells you what loads on every message, what heartbeats and scheduled tasks cost, which plaintext secrets are sitting in memory or skills, and which memory looks planted or bloated. Every finding comes with a concrete fix.
It runs on your computer, reads files only, uses no network and has no dependencies. Needs Node.js 20 or newer.
Run it
npx psyseal-scan --lang en
Or from a copy of this repository: node scripts/psyseal-scan.mjs --lang en. See --help for all options (--path <folder> checks any agent folder).
As an agent skill
- OpenClaw (from ClawHub):
openclaw skills install @psyseal/psyseal-scan - Claude Code, Cursor, Codex, Gemini CLI and other agents (skills CLI):
npx skills add psyseal/psyseal-scan - Claude Code plugin (the skill):
/plugin install psyseal-scan --marketplace psyseal/psyseal-scan(before Claude Code 2.1.275:/plugin marketplace add psyseal/psyseal-scan, then/plugin install psyseal-scan@psyseal)
As an MCP server
Details
- Repository
- github.com/psyseal/psyseal-scan
- Website
- psyseal.com
- Category
- AI & LLM Tools
- Package
psyseal-scan- Transport
- STDIO
- Registry
- MCP registry, active