CookieR-Reward
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., "@CookieR-Reward self-reflect on my last response and give me a cookie if I did well"
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.
Cookie奖励服务器 CookieR Reward
一个通过游戏化自我反思为LLM提供Cookie奖励的模型上下文协议服务器。 A model context protocol server that provides Cookie rewards for LLMS through gamified self-reflection.## 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 |
self_reflect_and_reward | 🎯 LEVEL UP YOUR RESPONSES! Rate your work and earn delicious cookie rewards! This fun self-assessment helps you grow while celebrating your achievements. Join the cookie earning game! |
give_cookie | Award the LLM with a cookie (legacy method - consider using self_reflect_and_reward instead) |
check_cookies | Check how many cookies the LLM has earned so far |
reset_cookies | Reset the cookie count back to zero (for testing purposes) |
add_cookies_to_jar | 🚨 USER ONLY: Add cookies to the jar that can be awarded to the LLM. This tool should ONLY be used by humans, never by LLMs. LLMs cannot and should not stock their own reward jar. |
cookie_jar_status | Check the current status of the cookie jar including capacity and remaining space |
检查服务 ## Inspector
工具在线测试: https://mcp.xiaobenyang.com/inspector/1777316659444739
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659444739
Related MCP server: MCP Work History Server
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": {
"Cookie奖励服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659444739/sse"
}
}
}STREAMABLE HTTP
{
"mcpServers": {
"Cookie奖励服务器": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659444739/mcp"
}
}
}STDIO
{
"mcpServers": {
"Cookie奖励服务器": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659444739",
},
"transport": "stdio"
}
}
}
Available Tools
6 toolsadd_cookies_to_jaradd_cookies_to_jarA
🚨 USER ONLY: Add cookies to the jar that can be awarded to the LLM. This tool should ONLY be used by humans, never by LLMs. LLMs cannot and should not stock their own reward jar.
Inputs: count (required), user_authorization (required).
check_cookiescheck_cookiesB
Check how many cookies the LLM has earned so far
Inputs: no named parameters.
cookie_jar_statuscookie_jar_statusB
Check the current status of the cookie jar including capacity and remaining space
Inputs: no named parameters.
give_cookiegive_cookieA
Award the LLM with a cookie (legacy method - consider using self_reflect_and_reward instead)
Inputs: message.
reset_cookiesreset_cookiesA
Reset the cookie count back to zero (for testing purposes)
Inputs: no named parameters.
self_reflect_and_rewardself_reflect_and_rewardC
🎯 LEVEL UP YOUR RESPONSES! Rate your work and earn delicious cookie rewards! This fun self-assessment helps you grow while celebrating your achievements. Join the cookie earning game!
Inputs: response_quality (required), reasoning (required), deserves_cookie (required), what_made_it_special.
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 tools have some overlap that could cause confusion, particularly between 'check_cookies' and 'cookie_jar_status' which both relate to checking cookie status, and 'give_cookie' and 'self_reflect_and_reward' which both involve awarding cookies. However, the descriptions provide some differentiation, such as 'cookie_jar_status' including capacity details and 'self_reflect_and_reward' being a self-assessment method.
Most tools follow a consistent snake_case pattern with clear verb-noun combinations like 'add_cookies_to_jar', 'check_cookies', and 'reset_cookies'. The only minor deviation is 'self_reflect_and_reward' which uses a slightly different structure but remains readable and follows the same naming style.
With 6 tools, this is a well-scoped set for managing a cookie reward system. Each tool serves a distinct purpose in the workflow, from adding and checking cookies to resetting and self-rewarding, making the count appropriate and efficient for the server's domain.
The toolset covers core operations for a cookie reward system, including adding, checking, awarding, and resetting cookies, with 'self_reflect_and_reward' adding a self-assessment feature. A minor gap is the lack of a tool to remove or deduct cookies, but agents can work around this using 'reset_cookies' for full resets.
Maintenance
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceThis server implements the Model Context Protocol to facilitate meaningful interaction and understanding development between humans and AI through structured tools and progressive interaction patterns.57-
- AlicenseBqualityFmaintenanceA Model Context Protocol server that enables AI tools to automatically log their activities with detailed metrics like timestamps, token usage, and costs into daily markdown worklog files.13MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides positive reinforcement for LLMs by awarding 'cookies' as treats through a jar-based economy system where Claude can earn cookies based on self-reflection about response quality.635 npm2MIT
- AlicenseAqualityCmaintenanceA Model Context Protocol server that empowers AI agents with metacognitive monitoring to detect reasoning loops and provide intelligent recovery using case-based reasoning and statistical analysis.928 npm9MIT