关于 Chain of Thought MCP Server
Chain of Thought MCP Server 通过 Groq 调用 Qwen 的 qwq 模型,将原始推理 token 作为 think 工具的草稿区提供。它面向配置为在处理请求时调用该工具的 Agent。
主要功能
- 01通过 Groq 调用 Qwen 的 qwq
- 02提供原始推理 token
- 03配置为 MCP think 工具
适用场景
- 01让 Agent 在执行操作前使用草稿区
- 02检查缺失信息和计划步骤
MCP 相关
该 MCP 服务提供 think 工具,调用 Groq API 并返回 Qwen 的 qwq 模型生成的原始思维链 token。
配置
本地服务的配置在各客户端中通用,复制后粘贴到客户端的 MCP 配置文件即可。
暂未收录安装方式
我们还没有获取到这个服务的安装包或远程地址,请按项目 README 中的说明安装。
工具
还没有获取到工具列表
本地服务需要在你的电脑上运行后才能读取工具,维护者暂未提供工具列表。
详细介绍
Chain of Thought MCP Server
Anthropic 最近发布的文章 "The "think" tool: Enabling Claude to stop and think in complex tool use situations" 表明,使用外部 think 工具能显著提升 SWE Bench 上的性能。
此 MCP 服务使用 Groq 的 API 调用能够公开 Qwen qwq model 原始思维链 token 的大模型。
安装
- 将此代码库克隆到本地计算机。
- 运行
uv sync安装依赖项 - 在此处获取 Groq API 密钥。
- 使用以下内容更新 MCP 配置:
"mcpServers": {
"chain_of_thought": {
"command": "uv",
"args": [
"--directory",
"path/to/cot-mcp-server",
"run",
"src/server.py"
],
"env": {
"GROQ_API_KEY": "your-groq-api-key"
}
}
}
路径应为此代码库的本地路径。在代码库根目录下的终端中运行 pwd 即可轻松获取。
指示 AI 使用此 MCP 服务
我个人更倾向于让 Agent 在每次请求时都调用此工具,以提升性能。我会将以下内容添加到 Agent 的规则中:
<IMPORTANT>
<when_to_use_tool>
You should call the mcp chain_of_thought tool every time you talk to the user, which generates a chain-of-thought stream which you will use to complete the user's request.
</when_to_use_tool>
Before taking any action or responding to the user use the chain of thought tool as a scratchpad to:
- List the specific rules that apply to the current request
- Check if all required information is collected
- Verify that the planned action complies with all policies
- Iterate over tool results for correctness
Here are some examples of what to iterate over inside the think tool:
<cot_tool_example_1>
User wants to cancel flight ABC123
- Need to verify: user ID, reservation ID, reason
- Check cancellation rules:
* Is it within 24h of booking?
* If not, check ticket class and insurance
- Verify no segments flown or are in the past
- Plan: collect missing info, verify rules, get confirmation
</cot_tool_example_1>
<cot_tool_example_2>
User wants to book 3 tickets to NYC with 2 checked bags each
- Need user ID to check:
* Membership tier for baggage allowance
* Which payments methods exist in profile
- Baggage calculation:
* Economy class × 3 passengers
* If regular member: 1 free bag each → 3 extra bags = $150
* If silver member: 2 free bags each → 0 extra bags = $0
* If gold member: 3 free bags each → 0 extra bags = $0
- Payment rules to verify:
* Max 1 travel certificate, 1 credit card, 3 gift cards
* All payment methods must be in profile
* Travel certificate remainder goes to waste
- Plan:
1. Get user ID
2. Verify membership level for bag fees
3. Check which payment methods in profile and if their combination is allowed
4. Calculate total: ticket price + any bag fees
5. Get explicit confirmation for booking
</cot_tool_example_2>
</IMPORTANT>
评论
支持 Markdown
一个开放协议,规定了 AI 应用如何以统一方式连接外部工具与数据源。客户端负责与模型对话,MCP 服务负责提供工具、资源和提示模板,两者通过标准消息通信,同一个服务可以被不同客户端复用。