RespCode MCP Server
Enables code execution and testing on x86_64 architectures, specifically supporting AMD processors.
Provides support for running and testing code on Apple Silicon (ARM64) architectures.
Supports code execution across multiple ARM architectures, including ARM64 and ARM32.
Enables code execution and testing on x86_64 architectures, specifically supporting Intel processors.
Allows for code execution and testing environments targeting Raspberry Pi hardware.
Provides tools for the simulation and execution of code on RISC-V 64 architectures.
Supports the generation and execution of Rust code across various hardware architectures.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RespCode MCP Server Generate a Fibonacci function in Rust and run it on ARM64"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RespCode MCP Server
Multi-architecture code execution for Claude Desktop via MCP.
Installation
pip install respcode-mcpRelated MCP server: Claude Jester MCP
Setup
Get your API key at respcode.com
Configure Claude Desktop (
~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"respcode": {
"command": "respcode-mcp",
"env": {
"RESPCODE_API_KEY": "your-api-key-here"
}
}
}
}Restart Claude Desktop
Available Tools
Tool | Description | Credits |
| AI generates & executes code | 2-6 |
| Run your own code | 1 |
| Compare 4 AI models | ~15 |
| Models refine each other | ~12 |
| Best-of-4 selection | ~15 |
| View past prompts | 0 |
| 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
Available Tools
9 toolscollaborateC
Models work together: first generates, others refine, then execute final result.
Inputs: prompt (required), architecture, models.
competeC
Generate with ALL 4 AI models and execute each. Compare which produces best code!
Inputs: prompt (required), architecture.
consensusC
All 4 models generate solutions, Claude picks/merges best one, then execute.
Inputs: prompt (required), architecture.
creditsB
Check your credit balance and see pricing.
Inputs: no named parameters.
executeB
Execute YOUR code (no AI generation). Just run it on the sandbox. 1 credit.
Inputs: code (required), architecture.
generateC
Generate code with ONE AI model and execute it. Default: deepseek-coder on x86.
Inputs: prompt (required), architecture, model.
historyB
View your recent prompts and execution results.
Inputs: limit.
history_searchC
Search your prompt history by keyword.
Inputs: query (required), limit.
rerunC
Re-run a previous prompt on a different architecture.
Inputs: prompt_id (required), architecture (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Maintenance
Related MCP Connectors
Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.
Multi-brand AI code review for Claude: up to 12 reviewers and a judge, no install.
People and AI agents build software together in persistent cloud sessions for Claude Code.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceGives Claude access to multiple AI models (Gemini, OpenAI, OpenRouter, Ollama) for enhanced development capabilities including extended reasoning, collaborative development, code review, and advanced debugging.-
- FlicenseNot gradedqualityDmaintenanceTransforms Claude from a code generator into a programming partner capable of testing, debugging, and optimizing code automatically through a secure execution environment.-
- FlicenseNot gradedqualityNot gradedmaintenanceGives Claude Desktop access to multiple AI models (Gemini, OpenAI, OpenRouter, Ollama) for enhanced development capabilities including extended reasoning, collaborative development, code review, debugging, and large context analysis with conversation threading.40 npm1-
- AlicenseNot gradedqualityCmaintenanceEnables Claude to consult over 17 AI platforms and 800,000+ models to provide alternative perspectives, code reviews, and diverse feedback. It features a unique personality system and supports multi-AI group discussions and debates directly within the chat interface.46MIT