Thoughtful ClaudeSAFE
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine. This server provides Claude with access to DeepSeek's state-of-the-art reasoning model, developed through large-scale reinforcement learning.
🌟 Features
- Advanced Reasoning Integration
- Leverages DeepSeek R1's reasoning engine
- Seamlessly integrates with Claude's thought process
- Handles complex multi-step reasoning tasks
- Enterprise-Grade Security
- Environment variable support (.env file)
- Secure API key handling
- No key exposure in responses
- MCP Protocol Support
- Full MCP server implementation
- Streaming response handling
- Proper error management
- Modern Python Architecture
- Async/await for efficient processing
- Proper exception handling
- Clean code organization
📦 Installation
- Prerequisites
- Python 3.12+
- uv package manager
- DeepSeek API key (get one from platform.deepseek.com)
- Quick Start
# Clone repository git clone https://github.com/martinbowling/thoughtful-claude.git cd thoughtful-claude # Install MCP and dependencies pip install "mcp[cli]" httpx python-dotenv # Create .env file with your API key echo "DEEPSEEK_API_KEY=your_key_here" > .env # Install the MCP server with environment variables mcp install server.py -f .env
The mcp install command will:
- Register the server with Claude Desktop
- Set up the environment variables from
.env - Configure the server to run with the correct Python interpreter
You can verify the installation by checking for the 🔨 Tools icon in Claude Desktop's interface.
🚀 Usage
- Start the Server
The server will automatically start when you use Claude Desktop with the proper configuration.
- Basic Workflow
- Claude receives a query requiring reasoning
- Query is
50fa0f8b2ab1OBSERVED · 2026-10-08Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
reason | read | Process a query through DeepSeek |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
50fa0f8b2ab1full audit observations/trust-audit/mcp-server/martinbowling__thoughtful-claude.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 50fa0f8b2ab1 | SAFE | B | 89 | first audit |
Questions
What is the Thoughtful Claude MCP server?
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔
What tools does Thoughtful Claude expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Thoughtful Claude safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Thoughtful Claude need?
It reads DEEPSEEK_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (50fa0f8b2ab1), read on 2026-10-08. The repository is watched and re-audited when it changes.