Tool Poisoning Scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Connector by GuardBee · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Tool Poisoning Scanner?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/guardbee-tool-poisoning-scanner
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security-scanning
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 4 read · 0 write · 0 deleteRead-only
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 4
Read from the source code; the running server may list different tools.
Read 4 · Look things up without changing anything.
list_patternsscan_directoryscan_filescan_text
Files it touches
- Any path the agent passes to its tools
Tools (4)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
list_patternsList every description-injection phrase and confused-deputy sink rule this scanner detects
scan_directoryRecursively scan a directory of MCP server source for tool-poisoning and confused-deputy patterns
scan_fileScan a single file for tool-poisoning and confused-deputy patterns in MCP tool registrations
scan_textScan 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).
Compare and alternatives
Featured in
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 14
- Weekly downloads
- 1,081
- Last commit (this folder)
- Oct 22, 2026 (8 days ago)
- Last release
- Oct 22, 2026 (8 days ago)
- Last package publish
- Oct 22, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.GuardBee/tool-poisoning-scanner- Version
- 0.3.2
- Auth
- No auth
- Packages
- npm @guardbee/mcp-tool-poisoning-scanner
- License
- MIT
- Repository
- github.com/GuardBee/guardbee-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Same server elsewhere
Copies of this server published by others; search shows only one of them.
More from GuardBee
- 0.732score
Toxic Flow Auditor
GuardBee
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
ConnectorAFreshness: ALocalRead-only★ 1↓ 1.1K/wkClaude Code +5 - 0.732score
Document Scanner
GuardBee
Finds PII and credentials in PDFs, screenshots and scanned documents
ConnectorAFreshness: ALocalRead-only★ 1↓ 1.1K/wkClaude Code +5 - 0.732score
Prompt Injection Scanner
GuardBee
Scans RAG content/scraped pages for indirect prompt injection
ConnectorAFreshness: ALocalRead-only★ 1↓ 1K/wkClaude Code +5 - 0.651score
Security Proxy
GuardBee
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
ConnectorAFreshness: ALocal★ 1↓ 1.3K/wkClaude Code +5 - 0.636score
Threat Rules
GuardBee
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
ConnectorAFreshness: ALocalRead-only★ 1↓ 886/wkClaude Code +5 - 0.635score
OAuth Auditor
GuardBee
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
ConnectorAFreshness: ALocalRead-only★ 1↓ 813/wkClaude Code +5
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Tool Poisoning Scanner running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Tool Poisoning Scanner MCP server. Agent Mart. https://agentmart.dev/connectors/guardbee-tool-poisoning-scanner (last updated 2026-10-24)