思路链 MCP 服务器
Anthropic 最近发表的文章“思考工具:让 Claude 在复杂的工具使用情况下停下来思考”表明,使用外部think工具可以显著提高SWE Bench的性能。
该 MCP 服务器使用 Groq 的 API 来调用 LLM,从而公开来自 Qwen 的qwq 模型的原始思路链标记。
安装
将此存储库克隆到您的本地机器。
运行
uv sync来安装依赖项从这里获取 Groq API 密钥。
使用以下命令更新您的 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"
}
}
}
该路径应为该仓库的本地路径。您可以通过在仓库根目录下的终端中运行pwd轻松获取该路径。
指示 AI 使用此 MCP 服务器
我个人更喜欢代理在每次请求时都调用此工具来提高性能。我将以下内容添加到代理规则中:
<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>
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
MCP 服务器使用 Groq 的 API 来公开来自 Qwen 的 qwq 模型的原始思路链标记,使 LLM 能够在响应之前逐步思考。
Related MCP Servers
- -security-license-qualityA MCP server that exposes GraphQL schema information to LLMs like Claude. This server allows an LLM to explore and understand large GraphQL schemas through a set of specialized tools, without needing to load the whole schema into the contextLast updated -1742MIT License
- Asecurity-licenseAqualityAn MCP server that enables managing multiple lines of thought with features like branch navigation, cross-references between related thoughts, and insight generation from key points.Last updated -115MIT License
- -security-license-qualityA minimal demonstration of an MCP service and client that integrates with the qwen API interface, showing basic functionality of a Model Control Protocol implementation.Last updated -MIT License
- -security-license-qualityAn intelligent server that connects applications to Groq's AI models, enabling text completion, audio transcription, vision analysis, and batch processing through the Model Context Protocol.Last updated -1MIT License