Sign In
beverm2391_chain_of_thought_mcp_server

beverm2391_chain_of_thought_mcp_server

by beverm2391
An MCP server that injects raw chain-of-thought tokens from a reasoning model using Groq's API.

Chain of Thought MCP Server

Overview

The Chain of Thought MCP Server is designed to inject raw chain-of-thought tokens from a reasoning model, enhancing AI performance in complex tool use situations. Inspired by Anthropic's "think" tool, this server leverages Groq's API to call LLMs, specifically Qwen's qwq model, to generate these tokens.

Installation

  1. Clone this repository to your local machine.
  2. Run uv sync to install dependencies.
  3. Obtain a Groq API key from Groq's Console.
  4. Update your MCP configuration with the following:
"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"
      }
    }
}

Ensure the path points to the local repository directory, which can be obtained by running pwd in the terminal from the repository root.

Instructing the AI to Use This MCP Server

To maximize performance, instruct the AI to call the chain_of_thought tool on every request. Add the following rules to your agent's configuration:

<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>

About

This project is an MCP server that injects raw chain-of-thought tokens from a reasoning model, improving AI decision-making and performance.

Resources

Stars

3 stars

Watchers

2 watching

Forks

2 forks

Languages

Features & Capabilities

Categories
mcp_server model_context_protocol python groq_api llm chain_of_thought reasoning_model api_integration

Implementation Details

View on GitHub

Stats

0 Views
0 Likes
3 GitHub Stars

Repository Info

beverm2391 Organization

Similar Servers

continuedev_continue by continuedev
0
cherryhq_cherry_studio by CherryHQ
0
bytedance_ui_tars_desktop by bytedance
0
2025© BestAI