Chain of Thought MCP Server
Servidor MCP de cadena de pensamiento
El artículo reciente de Anthropic "La herramienta "pensar": permitir que Claude se detenga y piense en situaciones complejas de uso de herramientas" muestra que el uso de una herramienta think externa aumenta notablemente el rendimiento en SWE Bench .
Este servidor MCP utiliza la API de Groq para llamar a los LLM que exponen tokens de cadena de pensamiento sin procesar del modelo qwq de Qwen.
Instalación
Clone este repositorio en su máquina local.
Ejecute
uv syncpara instalar las dependenciasObtenga una clave API de Groq desde aquí .
Actualice su configuración de mcp con:
"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"
}
}
}La ruta debe ser la ruta local de este repositorio. Puede obtenerla fácilmente ejecutando pwd en la terminal desde la raíz del repositorio.
Related MCP server: Local LLM MCP Tool
Dar instrucciones a la IA para que utilice este servidor MCP
Personalmente, prefiero que el agente llame a esta herramienta en cada solicitud para mejorar el rendimiento. Añado esto a mis reglas para el agente:
<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>Available Tools
1 toolchain_of_thoughtD
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
chain_of_thought
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'chain_of_thought' stands alone with a distinct purpose, making disambiguation trivial.
The tool name 'chain_of_thought' uses a consistent snake_case format. Since there is only one tool, naming consistency is inherently perfect with no deviations or mixed conventions to evaluate.
A single tool is generally too few for most server purposes, as it limits functionality and scope. This suggests the server may be under-scoped or incomplete, unless the domain is extremely narrow, which is not indicated here.
With only one tool, the surface is severely incomplete. It lacks any CRUD operations, lifecycle coverage, or complementary functions, making it impossible to perform meaningful workflows or tasks in the domain implied by the server name.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for Qwen Image 3 AI image generation
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
Related MCP Servers
- FlicenseBqualityDmaintenanceA lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.6739-
- AlicenseNot gradedqualityDmaintenanceA local MCP server that runs Llama models entirely on your machine. No API keys, no cloud costs, 100% private and offline-capable.MIT
- AlicenseNot gradedqualityDmaintenanceA VRAM-aware MCP server that offloads token-heavy development tasks to local Ollama models, saving API tokens for complex reasoning.783 npmMIT
- FlicenseNot gradedqualityDmaintenanceA proof-of-concept MCP server that enables LLMs to read local text files and fetch real-time weather data through external tools.-