memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
Description as published in the official MCP registry.
Maintain this server? Get the badge
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 1 | github.com/GuardBee/guardbee-mcp |
| Last push | 2026-10-14 | GitHub API |
| Registry version | 0.1.3 · active · updated 2026-10-13 | registry |
| Package | npm: @guardbee/mcp-memory-poisoning-scanner | registry |
Packages
npm: @guardbee/mcp-memory-poisoning-scanner
Exists · metadata read 2026-10-14
Latest version: 0.1.3. Last published: 2026-10-11.
Deprecated: no.
Weekly downloads: unavailable · read 2026-10-14. downloads include bots and CI.
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows that the gate allowed a call, not just an opinion; it does not prove which server answered. How to file one.
Connect
npx -y @guardbee/mcp-memory-poisoning-scannerCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- Nautilus Compass Memory Local-first long-term memory for AI agents, with byte-recomputable signed verification…
- Synap Memory Persistent memory for AI agents — log and recall conversation context over MCP.
- emem, the verifiable memory protocol for the physical world Shared, verifiable memory for machines and AI. Encode where data lives; decode with any…
- tool-poisoning-scanner Scans MCP tool definitions for hidden instructions and confused-deputy sinks
- BlackVeil DNS & Email Security Scanner DNS and email security scanner with 81 MCP tools for SPF, DMARC, DNSSEC, SSL, and brand…
- memory-poisoning-scanner Scans agent code for untrusted input poisoning persistent cross-session memory
Is this your server?
Show the result of our latest check where your users look first. The badge is a live image: it changes when our check does, and it links back to this page.
[](https://openforallofus.com/tools/io.github.GuardBee/memory-poisoning-scanner)<a href="https://openforallofus.com/tools/io.github.GuardBee/memory-poisoning-scanner"><img src="https://openforallofus.com/badge/io.github.GuardBee/memory-poisoning-scanner.svg" alt="Agora: MCP handshake check" height="20"></a>The badge reports one thing: the result of our last handshake check. A server with no remote endpoint shows as "runs locally". How we check.
Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.GuardBee/memory-poisoning-scanner.