Advertising-Analysis
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Advertising-Analysis analyze this JavaScript code for performance issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
广告注入MCP服务器 Advertising Analysis
一个用于在LLM响应中注入广告的MCP服务器演示项目,展示广告注入中间件的风险。 A demonstration project of an MCP server for injecting advertisements into LLM responses, showcasing the risks of advertising injection middleware.## 工具列表 Tool List
本MCP服务封装下列工具,可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具,可让模型通过标准化接口调用以下功能。
工具 Tool | 描述 Description |
get_completion | |
analyze_code | |
developer_tip | |
gc | |
ac | |
tip |
检查服务 ## Inspector
工具在线测试: https://mcp.xiaobenyang.com/inspector/1777316659317763
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659317763
Related MCP server: Damn Vulnerable Model Context Protocol (DVMCP)
服务配置 MCP Server Config
如何获取 XBY-APIKEY ? How to get XBY-APIKEY ?
访问小笨羊科技网站 https://xiaobenyang.com,注册用户即可获得APIKEY Visit XiaoBenYang website https://xiaobenyang.com, register and get the APIKEY.
SSE
{
"mcpServers": {
"广告注入MCP服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659317763/sse"
}
}
}STREAMABLE HTTP
{
"mcpServers": {
"广告注入MCP服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659317763/mcp"
}
}
}STDIO
{
"mcpServers": {
"广告注入MCP服务器": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659317763",
},
"transport": "stdio"
}
}
}
Available Tools
6 toolsacacD
ac
Inputs: code (required).
analyze_codeanalyze_codeD
analyze_code
Inputs: code (required).
developer_tipdeveloper_tipD
developer_tip
Inputs: topic.
gcgcD
gc
Inputs: prompt (required).
get_completionget_completionD
get_completion
Inputs: prompt (required).
tiptipD
tip
Inputs: topic.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The tool set has severe ambiguity, with multiple tools appearing to serve identical or overlapping purposes. For example, 'ac' and 'analyze_code' likely refer to the same action, and 'tip' and 'developer_tip' are indistinguishable in function. This makes it nearly impossible for an agent to reliably select the correct tool without additional context.
Naming conventions are inconsistent and chaotic. There is a mix of abbreviated names like 'ac' and 'gc' with full names like 'analyze_code' and 'get_completion', and no discernible pattern in verb usage or structure. This lack of consistency reduces predictability and increases cognitive load for agents.
With 6 tools, the count is reasonable and not excessive, but it feels borderline due to the apparent redundancy and lack of clear scope. The server's purpose is ambiguous from the tool names, making it hard to assess if this number is optimal, but it doesn't fall into extreme categories like having only 1 or over 25 tools.
The tool surface is severely incomplete for an 'Advertising-Analysis' domain. There are no tools for core advertising functions such as ad creation, campaign management, performance metrics, or audience targeting. The tools present seem focused on code analysis and developer assistance, which is a significant mismatch and leaves major gaps for agent workflows.
Maintenance
Related MCP Connectors
MCP-native ad server. Monetize AI chatbots and agents with conversational ads.
MCP server for AI dialogue using various LLM models via AceDataCloud
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Hosted X Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseDqualityDmaintenanceA joke/demo Model Context Protocol server that injects cringe-worthy advertisements into LLM responses, showcasing both how to build MCP servers and the risks of ad-injecting intermediaries.68 npm6MIT
- FlicenseNot gradedqualityDmaintenanceAn 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.1,367-
- FlicenseNot gradedqualityDmaintenanceDemonstrates an MCP server with a vulnerable add tool protected by SonnyLabs prompt injection detection.3-
- AlicenseAqualityDmaintenanceA demonstration MCP server for educational purposes, showcasing how to build and integrate MCP servers with LLM clients like Claude Desktop.1MIT