x64dbg-MCP Server is a native Model Context Protocol plugin that lets AI assistants control the x64dbg debugger over HTTP. It is for reverse engineering and debugging tasks involving breakpoints, stepping, memory, registers, modules, disassembly, and related binary-analysis operations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add duty1g/x64dbg-mcp-server --skill x64dbg-mcp-servergit clone --depth 1 https://github.com/duty1g/x64dbg-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/duty1g/x64dbg-mcp-server/x64dbg-mcp-server)<a href="https://agentmods.dev/skills/duty1g/x64dbg-mcp-server/x64dbg-mcp-server"><img src="https://agentmods.dev/badge/skills/duty1g/x64dbg-mcp-server/x64dbg-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/duty1g/x64dbg-mcp-server/x64dbg-mcp-server"><img src="https://agentmods.dev/badge/skills/duty1g/x64dbg-mcp-server/x64dbg-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03583 |
| Opus 5 | $0.00000 | $0.01792 |
| Sonnet 5 | $0.00000 | $0.00717 |
| Haiku 4.5 | $0.00000 | $0.00358 |
Grade A, and why
x64dbg-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x64dbg Reverse Engineering — MCP Workflow Guide
You are controlling x64dbg through MCP tools.
Transport matters:
- SSE clients receive push notifications for debugger events (breakpoints, exceptions, state changes) in real time.
- HTTP clients must poll — call
WaitForEventto long-poll for events, or read the[state]and[event:*]lines included in every tool response.
Treat every assumption about debugger state as stale until verified by a tool response.
Rule 1: Always Know Your State
Before every action, call GetDebugState. No exceptions.
NO_TARGET— nothing loaded. UseLoadBinaryorAttachProcessfirst.PAUSED— target is stopped. You can read memory, disassemble, inspect registers.RUNNING— target is executing. You CANNOT read memory, disassemble, or inspect anything. CallWaitForPauseorPauseDebugfirst.
Every tool response includes a [state] line at the end showing the current debugger status — PAUSED with address/module/instruction, RUNNING, or NO_TARGET. Always read it. This is your primary state awareness mechanism.
Every tool response may also include [event:*] lines — queued debugger events (breakpoints hit, exceptions, DLL loads) that occurred since your last call. Always read these too.
If the user says "paused", "hit breakpoint", "stopped", or "debugger is paused" — immediately call GetDebugState to see where you are. Do not guess.
Rule 2: Never Assume State Between Calls
MCP is request/response. Between your tool calls, anything can happen — breakpoints can hit, exceptions can fire, the user can interact with the debugger. Every time you are about to act, verify first.
Bad:
SetBreakpoint → run → Disassemble (wrong: run blocks but verify anyway)
Good:
GetDebugState → SetBreakpoint → run → GetDebugState → Disassemble
Rule 3: Core Workflows
Load and analyze a binary
GetDebugState
LoadBinary (path)
WaitForPause — target pauses at system breakpoint
GetDebugState — confirm PAUSED, note the address
GetAllRegisters — see initial state
ListModules — see what's loaded
Disassemble — look at current code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 301 lines · 0 tokens per session scan A d15cfc0d27f1
x64dbg-mcp-server is a skill published in the GitHub repository duty1g/x64dbg-mcp-server (1,937 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,583 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
IDA-Skill
A skill for reverse-engineering software with IDA Pro, a program for examining compiled applications. It uses IDAPython scripts to inspect disassembly, decompiled code, strings, imported functions, and references between code locations.
reverse-engineering-workbench
Coordinate EVOKORE reverse-engineering work across Ghidra-style static analysis, semantic recovery, and debugger-guided triage. Use when opening an unfamiliar binary, planning a decompilation workflow, or choosing between static and dynamic analysis paths.
ida-reverse-engineering
Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware using Ghidra with specialized scripts for function recovery, string extraction, and type reconstruction in stripped Go binaries.
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…