RespCode MCP Server
# RespCode MCP Server
Multi-architecture code execution for Claude Desktop via MCP.
## Installation
```bash
pip install respcode-mcp
```
## Setup
1. Get your API key at [respcode.com](https://respcode.com)
2. Configure Claude Desktop (`~/.config/claude/claude_desktop_config.json`):
```json
{
"mcpServers": {
"respcode": {
"command": "respcode-mcp",
"env": {
"RESPCODE_API_KEY": "your-api-key-here"
}
}
}
}
```
3. Restart Claude Desktop
## Available Tools
| Tool | Description | Credits |
|------|-------------|---------|
| `generate` | AI generates & executes code | 2-6 |
| `execute` | Run your own code | 1 |
| `compete` | Compare 4 AI models | ~15 |
| `collaborate` | Models refine each other | ~12 |
| `consensus` | Best-of-4 selection | ~15 |
| `history` | View past prompts | 0 |
| `credits` | Check balance | 0 |
## Architectures
- x86_64 (Intel/AMD)
- ARM64 (Apple Silicon, Raspberry Pi)
- RISC-V 64
- ARM32
- Verilog/VHDL simulation
## Example Usage in Claude
> "Generate a fibonacci function in Rust and run it on ARM64"
> "Compare all 4 AI models writing quicksort in C"
> "Execute this code on RISC-V: print('Hello RISC-V')"
## Links
- Website: https://respcode.com
- Docs: https://docs.respcode.com
- API: https://respcode.com/api
TDQS
Scored across 9 tools
There is significant overlap between the AI generation tools (collaborate, compete, consensus, generate), as they all involve generating and executing code with AI models, differing mainly in how models are combined. However, the descriptions help clarify the distinctions, and non-generation tools like credits, execute, history, history_search, and rerun have clear, non-overlapping purposes.
Most tools use a consistent verb-based naming pattern (e.g., collaborate, compete, generate, execute, rerun), which is readable and predictable. The only minor deviations are 'credits' (a noun) and 'history_search' (a compound word), but overall, the naming is largely consistent and follows a clear convention.
With 9 tools, the count is reasonable for a server focused on AI code generation and execution, covering generation variants, execution, history, and billing. It's slightly heavy due to multiple generation methods, but each tool has a defined role, making it well-scoped for the domain without being excessive.
The tool set covers core workflows for AI-powered code generation and execution, including multiple generation strategies, execution, history management, and billing. Minor gaps exist, such as no direct tool for editing or deleting history entries, but agents can likely work around this, and the surface is largely complete for the server's purpose.