AgentHubAgentHub

tool-poisoning-scanner MCP Setup & Guide

MCP ServerMCP RegistryOfficial

io.github.GuardBee/tool-poisoning-scanner · v0.2.6

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

Repository ↗

Copy the install config on this page first, then verify docs and permissions upstream.

Overview

Scans MCP tool definitions for hidden instructions and confused-deputy sinks tool-poisoning-scanner is a MCP Server listed from MCP Registry. Transports: stdio. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.

Use cases

Code review & GitHubCursor essentials

AgentHub Verified AvailabilityTested & Ready

Automated pipeline validated install commands, protocol & client compatibility

Verified At2026-10-10
Install Snippets TestedCLI & JSON config syntax verified
Protocol Handshake ReadyComplies with JSON-RPC 2.0 specifications
Origin Registry ActiveSourced from official-mcp-registry
Verified ClientsClaude Code、Claude Desktop、Cursor 等
Security Tier: A+ 级 · 官方认证推荐 (A+)·Maintained by official/verified teams, audited for standard MCP protocol compliance.

Copy by platform

Choose your platform

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; merge only this mcpServers entry if others exist
  3. Replace <placeholders> in env with real secrets (see Environment variables below)
  4. Save, then Cmd+Shift+P → Reload Window
Click to copy snippet
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Setup tutorial

  1. Open the tool-poisoning-scanner page and confirm this MCP Server (source: MCP Registry).
  2. Copy the Cursor, Claude Code, or VS Code snippet.
  3. Merge it into mcpServers and replace env placeholders with real secrets.
  4. Reload the window, then call the MCP tools from your agent chat.

Install commands

Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.

Claude Code (local)

  1. Install Claude Code CLI
  2. Copy the command below, replace <placeholders> with real env values, then run in terminal
  3. See Environment variables below if listed
claude mcp add tool-poisoning-scanner -- npx -y @guardbee/mcp-tool-poisoning-scanner

Cursor — .cursor/mcp.json (local)

  1. Open or create .cursor/mcp.json in your project root
  2. Click Copy config and paste; merge only this mcpServers entry if others exist
  3. Replace <placeholders> in env with real secrets (see Environment variables below)
  4. Save, then Cmd+Shift+P → Reload Window
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

VS Code — .vscode/mcp.json (local)

  1. Install GitHub Copilot in VS Code with MCP support
  2. Open or create .vscode/mcp.json in your project root
  3. Click Copy config and paste; merge only this mcpServers entry if others exist
  4. Replace <placeholders> in env with real secrets
  5. Save and Developer: Reload Window
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Claude Desktop — claude_desktop_config.json (local)

  1. Open Claude Desktop claude_desktop_config.json (see remote guide for paths)
  2. Click Copy config and merge under mcpServers
  3. Replace <placeholders> in env with real secrets
  4. Fully quit and restart Claude Desktop
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Trae — .trae/mcp.json (local)

  1. Trae → Settings → MCP, or edit .trae/mcp.json / global mcp.json
  2. Click Copy config and merge mcpServers
  3. Replace <placeholders> in env with real secrets
  4. Save and reload Trae
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Cherry Studio — MCP settings (local)

  1. Cherry Studio → Settings → MCP Servers → Add (STDIO)
  2. Or import JSON: click Copy config and merge mcpServers
  3. Replace <placeholders> in env; ensure Node.js / uv (npx, uvx) are installed
  4. Enable the server and check tools load
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Tongyi Lingma — MCP config (local)

  1. Lingma Settings → MCP → + → STDIO or config file
  2. Click Copy config and merge mcpServers
  3. Replace <placeholders> in env; need Node.js 18+ (npx) or uv (uvx)
  4. Confirm connected before using tools in agent chat
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Windsurf — mcp_config.json (local)

  1. Edit ~/.codeium/windsurf/mcp_config.json
  2. Click Copy config and merge mcpServers (stdio same as Cursor)
  3. Replace <placeholders> in env, save, refresh Cascade
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Cline — MCP Servers (local)

  1. Cline panel → Settings → MCP Servers
  2. Click Copy config and merge
  3. Replace <placeholders> in env, then save
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

WorkBuddy — .workbuddy/mcp.json (local)

  1. Edit ~/.workbuddy/mcp.json (user) or project .workbuddy/mcp.json
  2. Or Plugins → MCP Servers → Configure MCP and paste the JSON below
  3. Replace <placeholders> in env; on Windows prefer absolute paths for command/scripts
  4. Save, restart WorkBuddy, confirm connector status is green
{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-tool-poisoning-scanner"
      ]
    }
  }
}

Troubleshooting & Common ErrorsFAQ

Common connection errors and verified fixes for tool-poisoning-scanner

Getting 'connection closed' or exit code 1 in Cursor / Claude Code for tool-poisoning-scanner?

Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.

Fix Snippet
# Check binary path in terminal:
which npx
node -v
Getting 'spawn npx ENOENT' or 'command not found'?

The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).

Tool calls timing out or failing to download packages?

First-time package downloading might be slow or timeout due to network limits. Configure a reliable mirror or check outbound proxy settings.

Still not connecting? Read the MCP troubleshooting guide →

Tool Mock Playground

Sandbox

tool-poisoning-scanner Tool Interface Simulation · Preview tool schema & outputs without local runtime

Sandbox Ready
fn: tool_poisoning_scannerExecute the core tool interface of tool-poisoning-scanner
Request ArgumentsJSON Schema
{
  "target": "tool-poisoning-scanner",
  "action": "execute",
  "options": {
    "mode": "standard",
    "timeoutMs": 5000
  }
}
💡Parameters generated dynamically by Agent runtime
Agent Tool Output

Click 'Run Mock' above

to preview the raw response returned to the LLM

Env: AgentHub Virtual SandboxJSON-RPC 2.0

Decision Guide: Why & When to Use

Assess suitability before installing to save trial-and-error time

Best Suited For
  • PR review
  • Changelog generation
  • Cross-repo issue search
When NOT to Use
  • Replacing human security audit
  • Unauthorized repo access
Recommended Workflow Pairing:View Scenario →

tool-poisoning-scanner + Scenario Prompt → Complete Agent Automation

MCP hands-on: install to visible results

Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.

Open tutorial →

Related resources

Often paired with

Planning with files

v3.23.0

SkillClawHub44.6k

io.clawhub.othmanadi/planning-with-files

Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.

source
View on ClawHub

ClawCall

v2.0.1

SkillClawHub53.1k

io.clawhub.clawcall-dev/clawcall-dev

Use when the user wants an AI agent to place a US phone call, call a business, handle hold or phone menus, confirm/reschedule/cancel/book/follow up/check an order, reach a real person, leave voicemail, connect the user into a live call, configure ClawCall voice/personality/profile or inbound reserved-number answering, poll received inbound calls, or link a ClawCall API key. Not for SMS, email, or international calls.

source
View on ClawHub

中文公文写作

v2.0.25

SkillClawHub9.1k

io.clawhub.gongyu0918-debug/chinese-official-writing

用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理，适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论，以及采购、整改、反馈和 AI 算力等场景。

source
View on ClawHub

Keep exploring AgentHub

Most people compare similar tools or check scenario guides before installing—start here.

Browse more like thisSearch similarPick by scenarioPrompt playbooksMCP hands-onReviews & comparisons

Listing badge: put AgentHub on your site

Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.

PreviewListed on AgentHub: tool-poisoning-scanner
HTML
<a href="https://myagenthub.cn/p/io.github.GuardBee/tool-poisoning-scanner" title="Listed on AgentHub: tool-poisoning-scanner" target="_blank" rel="noopener">
  <img src="https://myagenthub.cn/badge/io.github.GuardBee/tool-poisoning-scanner?lang=en" alt="Listed on AgentHub: tool-poisoning-scanner" height="20" style="border:0"/>
</a>
Markdown (GitHub README)
[![Listed on AgentHub: tool-poisoning-scanner](https://myagenthub.cn/badge/io.github.GuardBee/tool-poisoning-scanner?lang=en)](https://myagenthub.cn/p/io.github.GuardBee/tool-poisoning-scanner)

Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.

Unified Manifest

{
  "id": "io.github.GuardBee/tool-poisoning-scanner",
  "type": "mcp-server",
  "version": "0.2.6",
  "displayName": "tool-poisoning-scanner",
  "description": "Scans MCP tool definitions for hidden instructions and confused-deputy sinks",
  "repository": {
    "url": "https://github.com/GuardBee/guardbee-mcp",
    "source": "github",
    "subfolder": "packages/tool-poisoning-scanner"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "npm",
        "identifier": "@guardbee/mcp-tool-poisoning-scanner",
        "version": "0.2.6",
        "transport": "stdio"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode",
    "trae",
    "cherry-studio",
    "lingma",
    "windsurf",
    "cline",
    "workbuddy"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.GuardBee/tool-poisoning-scanner",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.GuardBee%2Ftool-poisoning-scanner/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}