Ferroscope
БесплатноНе проверенMCP server that enables AI assistants to debug Rust programs using LLDB and GDB
Описание
MCP server that enables AI assistants to debug Rust programs using LLDB and GDB
README
MCP server that enables AI assistants to debug Rust programs using LLDB and GDB.
Quick Start
1. Install
cargo install ferroscope
Alternative: Build from source
git clone https://github.com/douglance/ferroscope.git
cd ferroscope
cargo install --path .
2. Configure Your AI Assistant
Add this to your AI assistant's MCP settings:
{
"mcpServers": {
"ferroscope": {
"command": "ferroscope",
"args": [],
"env": {},
"description": "Rust debugging via LLDB/GDB"
}
}
}
3. Add Custom Instructions
Copy this snippet to your AI assistant's custom instructions:
When debugging Rust programs, use ferroscope with this workflow:
1. Load program: debug_run /path/to/project
2. Set breakpoints: debug_break main or debug_break src/main.rs:25
3. Start execution: debug_continue
4. At breakpoints: debug_eval variable_name to inspect values
5. Step through: debug_step (over), debug_step_into (into), debug_step_out (out)
6. Check state: debug_state to see current status
7. View stack: debug_backtrace when errors occur
Always start with debug_run, then set breakpoints before debug_continue.
For advanced debugging with optimized context usage, append our best practices to your CLAUDE.md:
curl -s https://raw.githubusercontent.com/douglance/ferroscope/main/best-practices.md >> CLAUDE.md
4. Start Debugging
Ask your AI assistant: "Debug this Rust program" and it will use ferroscope automatically.
Configuration by AI Assistant
Claude Code
The configuration above works for Claude Code. Add it to Settings → MCP Servers, then restart.
Cursor
Add to .cursor/config.json:
{"tools": {"ferroscope": {"command": "ferroscope", "description": "Debug Rust programs"}}}
Windsurf
Add to tools configuration:
{"customTools": [{"name": "ferroscope", "command": "ferroscope", "type": "mcp"}]}
Zed
Add to ~/.config/zed/settings.json:
{"assistant": {"tools": {"ferroscope": {"command": "ferroscope", "args": []}}}}
Other AI Assistants
For any MCP-compatible AI assistant, the command is ferroscope. Check your assistant's documentation for "MCP tools" or "external tools".
Available Tools
debug_run- Load and prepare Rust programs for debuggingdebug_break- Set breakpoints at functions or linesdebug_continue- Launch/continue program executiondebug_step- Step through code line by linedebug_step_into- Step into function callsdebug_step_out- Step out of current functiondebug_eval- Evaluate expressions and inspect variablesdebug_backtrace- Show call stackdebug_list_breakpoints- List all breakpointsdebug_state- Get current debugging session state
Requirements
- Rust toolchain
- LLDB (macOS) or GDB (Linux)
- Windows not currently supported (WinDbg integration planned)
Verification
Check ferroscope is installed and working:
# Verify installation
which ferroscope
# Test basic functionality
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' | ferroscope
# Run test suite (if built from source)
cargo run --bin comprehensive-test
# Expected output:
# 🧪 FERROSCOPE COMPREHENSIVE TEST SUITE
# ✅ MCP Protocol Test: PASSED
# ✅ Program Loading Test: PASSED
# ✅ Breakpoint Test: PASSED
# ... (more tests)
# 🎉 ALL TESTS PASSED! Ferroscope functionality verified!
Limitations
- Security: Currently runs with full user privileges without sandboxing. Only use with trusted code.
- Platform Support: Windows is not supported (WinDbg integration planned)
- Performance: No connection pooling or resource limits for concurrent debugging sessions
- Error Recovery: Limited error handling for malformed debugger output
- Binary Types: Only supports Rust binaries compiled with debug symbols
- Debugger Versions: Tested with LLDB 15+ and GDB 12+
Development and Releases
Ferroscope uses automated semantic versioning based on conventional commits. New versions are automatically published to crates.io when:
- Fixes are merged (patch release: 0.1.1 → 0.1.2)
- Features are added (minor release: 0.1.1 → 0.2.0)
- Breaking changes occur (major release: 0.1.1 → 1.0.0)
See CONTRIBUTING.md for contribution guidelines and release process details.
Ready to debug Rust programs with AI! 🦀
Установка Ferroscope
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/douglance/ferroscopeFAQ
Ferroscope MCP бесплатный?
Да, Ferroscope MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Ferroscope?
Нет, Ferroscope работает без API-ключей и переменных окружения.
Ferroscope — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Ferroscope в Claude Desktop, Claude Code или Cursor?
Открой Ferroscope на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
автор: lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare Ferroscope with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
