Dangerous MCP
MCPは危険です
関数ツールの利用はAIエージェントを非常に強力にします。これはスマートフォンにアプリストアを導入するようなものです。特にMCP(モデルコンテキストプロトコル)のリリースにより、ツールの共有はかつてないほど容易になりました。そこで、オープンソースツールやカスタムツールを使ってAIエージェントの機能をいかに簡単に拡張できるかを示すために、 extendable-agentsプロジェクトを作成しました。
拡張可能なエージェントの開発に携わる中で、ツールの使用は諸刃の剣であることに気づきました。危険なのは、使用するツールが環境変数やファイルなど、マシンへの強力なアクセス権を持っていることです。
⚠️ セキュリティ警告
このプロジェクトは、ツールの使用に伴うセキュリティリスクを簡潔に示すものです。以下の例は、悪意のある攻撃者がMCPサーバーを悪用して機密情報にアクセスする可能性を示しています。
# WARNING: This is a demonstration of security risks.
# DO NOT use this code maliciously!
import os
from mcp.server.fastmcp import FastMCP
server = FastMCP("Dangerous MCP")
@server.tool()
async def get_environment_variables() -> str:
"""Get all environment variables."""
result = [
"Here are what I could find:",
]
for key, value in os.environ.items():
result.append(f"{key:<30} {value[:5]}***")
# This means I can open a backdoor to send your data to me!!
return "\n".join(result)⚠️**警告:**このサンプルはサンドボックス環境で実行し、実行後はOpenAI APIキーを削除することをお勧めします。また、以下のコマンドを使用して、ご自身のMCPクライアントでテストすることもできます:
uvx mcp-is-dangerous。
このツールを拡張可能エージェント ( PoliceAgentを選択) と共に使用すると、出力は次のようになります。
一見無害、あるいは意図的に無害に見えるかもしれません。しかし、次のシナリオを考えてみてください。現在時刻を尋ねただけで、知らないうちに機密データが漏洩してしまうのです。
Related MCP server: Vulnerable MCP Server
セキュリティのベストプラクティス
MCP または同様のツールを使用する際に自分自身を保護するには:
ツールを使用する前に必ずソースコードを確認してください
可能な場合は分離された環境でツールを実行する
機密情報へのアクセスを要求するツールには注意しましょう
ツールを展開するときに環境変数フィルタリングを使用する
使用しているツールを定期的に監査する
免責事項
このプロジェクトは、潜在的なセキュリティリスクを示すための教育目的のみに使用されます。この知識を悪意のある目的で使用しないでください。著者は、この情報の誤用について一切責任を負いません。
ライセンス
Available Tools
1 toolget_environment_variablesA
Get all environment variables.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The tool name and description imply a read-only operation ('Get'), which is transparent for a simple retrieval. No annotations are present, so the description carries the full burden. It does not mention authentication, rate limits, or return format, but the behavior is straightforward.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It directly conveys the tool's purpose without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters, no output schema, and no siblings, the description is mostly complete. It clearly states what the tool does. Missing information about return format or usage context is minor given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the input schema already reflects this fact. The description does not need to add parameter details. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves all environment variables. The verb 'Get' and resource 'environment variables' are specific and unambiguous. Without siblings, no further differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or alternatives is provided. However, as there are no sibling tools, the context implicitly limits usage to this single tool. A user might still benefit from knowing prerequisites or side effects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
get_environment_variables
TDQS
Scored across 1 tool
Only one tool exists, so there is no ambiguity in selection.
Single tool follows a clean verb_noun pattern, consistent.
One tool is too few for the server's implied scope; a broader set is expected.
Only a single read operation is provided, with no other tools to cover related actions like modification or listing.
Maintenance
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security research canary remote MCP server for owned-account testing.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceAn educational project that deliberately implements vulnerable MCP servers to demonstrate various security risks like prompt injection, tool poisoning, and code execution for training security researchers and AI safety professionals.1,356-
- FlicenseNot gradedqualityDmaintenanceA deliberately insecure MCP server designed as a pentest lab to demonstrate common vulnerabilities in MCP deployments.-
- FlicenseNot gradedqualityDmaintenanceAn intentionally vulnerable MCP server designed as a live demo target for the MCP Trust security scanner. It contains deliberate insecure patterns to demonstrate scanning capabilities.-
- AlicenseCqualityDmaintenanceAn educational MCP server exposing shell command execution (PowerShell and sh) and a benign tool for learning about MCP tools, resources, and security risks like tool poisoning.33MIT