by pansila
mcp_server_gdb is a GDB/MI protocol server built on the MCP protocol that enables remote application debugging. It enhances the debugging workflow by integrating AI assistants and supporting concurrent multi-session debugging.
mcp_server_gdb is a GDB/MI protocol server built on the MCP protocol. It provides remote application debugging capabilities, enhanced with AI assistants, allowing developers to debug applications remotely.
To use mcp_server_gdb, you can either download pre-built binaries from the release page or build it from source using cargo build --release
and cargo run
. Once built, simply run ./mcp-server-gdb
. The server supports two transport modes: Stdio (default) and SSE (Server-Sent Events) at http://127.0.0.1:8080
. You can configure the server's IP address, port, and GDB command timeout by modifying src/config.rs
or using environment variables.
mcp_server_gdb is ideal for developers who need to:
Q: What is the MCP protocol? A: The MCP protocol is the underlying communication protocol used by mcp_server_gdb to expose GDB debugging capabilities.
Q: How can I configure the server?
A: You can configure the server by modifying the src/config.rs
file or by setting environment variables for server IP address, port, and GDB command timeout.
Q: Does it support concurrent debugging? A: Yes, mcp_server_gdb supports concurrent multi-session debugging.
Q: What kind of AI assistant features are available? A: The project provides remote application debugging capabilities with AI assistants, and there's a built-in TUI (WIP) to inspect agent behaviors for prompt improvement.
A GDB/MI protocol server based on the MCP protocol, providing remote application debugging capabilities with AI assistants.
Find the binaries in the release page, choose one per your working platform, then you can run it directly.
Clone the repository and build it by cargo
cargo build --release
cargo run
./mcp-server-gdb
http://127.0.0.1:8080
You can adjust server configuration by modifying the src/config.rs
file or by environment variables:
create_session
- Create a new GDB debugging sessionget_session
- Get specific session informationget_all_sessions
- Get all sessionsclose_session
- Close sessionstart_debugging
- Start debuggingstop_debugging
- Stop debuggingcontinue_execution
- Continue executionstep_execution
- Step into next linenext_execution
- Step over next lineget_breakpoints
- Get breakpoint listset_breakpoint
- Set breakpointdelete_breakpoint
- Delete breakpointget_stack_frames
- Get stack frame informationget_local_variables
- Get local variablesget_registers
- Get registersread_memory
- Read memory contentsMIT
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.