Tool Poisoning Scanner MCP server

by GuardBee·io.github.GuardBee/tool-poisoning-scanner·v0.2.7·1 stars

Scans MCP tool definitions for hidden instructions and confused-deputy sinks

A91/100grade A

What users say

No reviews yet

Safety scan

A91/100

Adoption

Growing

1 stars998 downloads/wk

Reviews

Nobody has reviewed Tool Poisoning Scanner yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

list_patterns
List every description-injection phrase and confused-deputy sink rule this scanner detects
scan_directory
Recursively scan a directory of MCP server source for tool-poisoning and confused-deputy patterns
scan_file
Scan a single file for tool-poisoning and confused-deputy patterns in MCP tool registrations
scan_text
Scan MCP server source for tool poisoning (hidden instructions embedded in a tool's `description` string, read by the calling LLM as trusted context) and confused-deputy tools (a name/description promising read-only behavior while the handler has a shell/eval/file-write/env-dump sink).

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

no findings

Code scan17 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 1 days ago15/15
Maintainer identityregistry namespace matches repository owner7/10

Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Runs npx -y @guardbee/mcp-tool-poisoning-scanner on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add tool-poisoning-scanner -- npx -y @guardbee/mcp-tool-poisoning-scanner

From the Tool Poisoning Scanner repository's README, as published. We do not edit it. Read it on GitHub

guardbee.ai — AI Security Copilot for websites.

GuardBee's family of MCP (Model Context Protocol) servers — a single monorepo, independent npm packages.

Nothing above is checked by us. What we check is on the safety report.

Is Tool Poisoning Scanner MCP server safe?: Yes, by our scan: it is graded A (91/100). Read the Tool Poisoning Scanner safety report
How do I install Tool Poisoning Scanner?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Tool Poisoning Scanner need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Tool Poisoning Scanner maintained?: The last commit was 2 days ago (2026-10-11). The latest release is v0.2.7.