mem
MCP server for live process memory introspection and debugging on Linux x86_64. Enables reading/writing process memory, searching patterns, ptrace attach/registers, running commands, and valgrind execution.
README
mem — MCP server for process memory introspection
Live process memory introspection, debugger, and valgrind runner. Linux-only (x86_64). Runs as an MCP stdio server for the pi agent.
Tools
| Tool | What it does |
|---|---|
maps |
Read /proc/<pid>/maps — memory layout of a running process |
mem_read |
Read bytes from a process's address space (process_vm_readv) |
mem_write |
Write bytes into a process's address space (process_vm_writev) |
mem_search |
Search process memory for a hex byte pattern |
run |
Spawn a command as a child of this server (makes it inspectable) |
children |
List supervised child processes |
attach |
ptrace-attach to a process (stops it) |
registers |
Read CPU registers (PTRACE_GETREGS, x86_64) |
detach |
ptrace-detach from a process (resumes it) |
valgrind_run |
Run a command under valgrind |
valgrind_status |
Poll a running valgrind job |
Requirements
- Linux (process_vm_readv/writev, ptrace, /proc)
ptrace_scope= 0 (or useruntool to spawn child processes)- valgrind (optional, for valgrind_run)
ptrace_scope limitation
On Ubuntu (default ptrace_scope=1), process_vm_readv and ptrace only
work on direct child processes of the MCP server. To inspect a program:
- Use
runto spawn it — the server is its parent, all tools work - Or set
ptrace_scope=0:echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope - Or use
CAP_SYS_PTRACE
The run tool makes the child fully inspectable without any sysadmin
changes.
Debugging workflow
1. run → spawns the target program, returns PID
2. maps → read its memory layout
3. mem_read → read bytes from any address
4. attach → ptrace-stop the process
5. registers → read CPU registers (rip, rsp, rax, etc.)
6. mem_write → patch a variable or instruction
7. detach → resume execution
8. valgrind_run → check for memory errors
Wiring
pi.mcpServers in package.json declares the server; the hub merges it
into pi's mcp.json when the package is registered (this workspace is a
watched hub workspace, so a new package dir wires itself). The command is
relative to this dir on purpose — hub resolves it. Build first, then restart
pi: pi reads mcp.json at startup.
mem stays wired by default: it is the live-process debugger for Rust/Odin/etc.
binaries (ptrace introspection + valgrind runner). Reach for it when a binary
leaks, crashes in ways rustc can't explain, or grows RSS — pair the valgrind_run
tool with the valgrind skill's prose for the flags and quirks.
Build
cd /home/feb/dev/_pi_extensions/mem
cargo build --release
Safety
mem_writecan crash or corrupt the target process.attachstops the target process. Alwaysdetachwhen done.- valgrind jobs run with a timeout (default 300s).
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。