Sandbox
@pwno-io/pwno-mcp

MCP server for GDB and pwndbg

pwno-mcp wraps GDB, pwndbg, and exploit-driver workflows in an MCP service. It gives agents stateful debugging sessions, execution control, snapshots of registers and stack, and helpers for working with commands, processes, Python, repos, and RetDec.

281 stars25 forksPythonUpdated 6mo ago
Who it's for

Builders who want their agent to debug binaries and drive exploit workflows through MCP.

What it delivers

You can inspect and steer binary analysis sessions without manually re-entering debugger context.

What it does

Stateful debugger sessions

Keeps GDB + pwndbg sessions alive so the agent can continue from the same state.

Deterministic execution control

Uses GDB/MI to control execution in a repeatable way.

Context snapshots

Captures registers, stack, disassembly, source, and backtrace for fast agent context.

Exploit-driver workflows

Supports interactive exploit I/O through `pwncli`.

Multi-session support

Lets the agent run parallel analysis or exploitation workflows.

Workspace automation helpers

Adds helpers for commands, processes, Python, repositories, and RetDec.

HTTP and stdio transport

Offers both HTTP and stdio endpoints for MCP clients.

How to get it

  1. 1Create a local workspace directory, put your target binary there, then run the container.
    mkdir -p ./workspace
    cp ./path/to/your/binary ./workspace/chal
    chmod +x ./workspace/chal
  2. 2Run
    docker run --rm -p 5500:5500 \
      --cap-add=SYS_PTRACE \
      --cap-add=SYS_ADMIN \
      --security-opt seccomp=unconfined \
      --security-opt apparmor=unconfined \
      -v "$PWD/workspace:/workspace" \
      ghcr.io/pwno-io/pwno-mcp:latest
  3. 3Default MCP endpoint
    http://127.0.0.1:5500/mcp

README

pwno-mcp bannerpwno-mcp banner

stateful system for autonomous pwn and binary research, designed for LLM agents.

Overview

pwno-mcp runs GDB + pwndbg in an isolated environment and exposes stateful debugging, exploit I/O, and helper tooling over MCP for agentic coding clients.

Features

  • Stateful debugger sessions via GDB + pwndbg
  • Deterministic execution control via GDB/MI
  • Fast context snapshots for registers, stack, disassembly, source, and backtrace
  • Interactive exploit-driver workflows with pwncli
  • Multi-session support for parallel workflows
  • Workspace automation helpers for commands, processes, Python, repos, and RetDec
  • HTTP and stdio transport support

Documentation

The full documentation is available at docs.pwno.io.

Quick Start

Create a local workspace directory, put your target binary there, then run the container.

mkdir -p ./workspace
cp ./path/to/your/binary ./workspace/chal
chmod +x ./workspace/chal
docker run --rm -p 5500:5500 \
  --cap-add=SYS_PTRACE \
  --cap-add=SYS_ADMIN \
  --security-opt seccomp=unconfined \
  --security-opt apparmor=unconfined \
  -v "$PWD/workspace:/workspace" \
  ghcr.io/pwno-io/pwno-mcp:latest

Default MCP endpoint:

http://127.0.0.1:5500/mcp

For stdio mode, client configs, health checks, and attach-helper details, use the docs site: docs.pwno.io/quickstart.

Development

For local development, architecture, and contributing guidance, see docs.pwno.io/development.

Usage

  • non-profit: yes
  • commercial: oss@pwno.io

Future Enhancements

  • WebSocket endpoint for streaming I/O
  • Advanced memory analysis tools
  • Heap exploitation helpers
  • ROP chain generation
  • Symbolic execution integration

License

This project is licensed under CC BY-NC-ND 4.0.

See LICENSE for details.

Contributing

Issues and pull requests are welcome.

Files in the repo

Repository payload21 top-level entries
  • .github
  • assets
  • docs
  • pwnomcp
  • tests
  • .dockerignore
  • .gitignore
  • .python-version
  • AGENTS.md
  • cloudbuild.yaml
  • deploy.sh
  • docker-build.cloud.sh
  • docker-build.local.sh
  • docker-compose.yml
  • Dockerfile
  • LICENSE
  • opencode.json
  • pwnomcp.service
  • pyproject.toml
  • README.md
  • uv.lock

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k