The Code Reasoning MCP server enhances Claude's ability to solve complex programming tasks by providing structured, step-by-step thinking capabilities through sequential reasoning and thought branching. It offers tools for exploring multiple solution paths in parallel, revising reasoning as understanding improves, and includes safety limits to prevent infinite loops, along with pre-defined prompt templates for common development tasks. This server solves the problem of enabling more deliberate, organized problem-solving approaches for coding challenges that benefit from breaking down complexity into manageable steps.
A Model Context Protocol (MCP) server that enhances Claude's ability to solve complex programming tasks through structured, step-by-step thinking.
Configure Claude Desktop by editing:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json{
"mcpServers": {
"code-reasoning": {
"command": "npx",
"args": ["-y", "@mettamatt/code-reasoning"]
}
}
}
Configure VS Code:
{
"mcp": {
"servers": {
"code-reasoning": {
"command": "npx",
"args": ["-y", "@mettamatt/code-reasoning"]
}
}
}
}
To trigger this MCP, append this to your chat messages:
Use sequential thinking to reason about this.
Use ready-to-go prompts that trigger Code-Reasoning:

/help to see the specific commands.See the Prompts Guide for details on using the prompt templates.
--debug: Enable detailed logging--help or -h: Show help informationDetailed documentation available in the docs directory:
├── index.ts # Entry point
├── src/ # Implementation source files
└── test/ # Placeholder for future test utilities
This project is licensed under the MIT License. See the LICENSE file for details.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent