IDA Pro MCP

Simple MCP Server to allow vibe reversing in IDA Pro.

https://github.com/user-attachments/assets/6ebeaa92-a9db-43fa-b756-eececce2aca0

The binaries and prompt for the video are available in the mcp-reversing-dataset repository.

Prerequisites

• Python (3.11 or higher)
  • Use idapyswitch to switch to the newest Python version
• IDA Pro (8.3 or higher, 9 recommended), IDA Free is not supported
• Supported MCP Client (pick one you like)
  • Amazon Q Developer CLI
  • Augment Code
  • Claude
  • Claude Code
  • Cline
  • Codex
  • Copilot CLI
  • Crush
  • Cursor
  • Gemini CLI
  • Kilo Code
  • Kiro
  • LM Studio
  • Opencode
  • Qodo Gen
  • Qwen Coder
  • Roo Code
  • Trae
  • VS Code
  • VS Code Insiders
  • Warp
  • Windsurf
  • Zed
  • Other MCP Clients: Run ida-pro-mcp --config to get the JSON config for your client.

Installation

Install the latest version of the IDA Pro MCP package:

pip uninstall ida-pro-mcp
pip install https://github.com/mrexodia/ida-pro-mcp/archive/refs/heads/main.zip

Configure the MCP servers and install the IDA Plugin:

ida-pro-mcp --install

Important: Make sure you completely restart IDA and your MCP client for the installation to take effect. Some clients (like Claude) run in the background and need to be quit from the tray icon.

https://github.com/user-attachments/assets/65ed3373-a187-4dd5-a807-425dca1d8ee9

Note: You need to load a binary in IDA before the plugin menu will show up.

Prompt Engineering

LLMs are prone to hallucinations and you need to be specific with your prompting. For reverse engineering the conversion between integers and bytes are especially problematic. Below is a minimal example prompt, feel free to start a discussion or open an issue if you have good results with a different prompt:

Your task is to analyze a crackme in IDA Pro. You can use the MCP tools to retrieve information. In general use the following strategy:

- Inspect the decompilation and add comments with your findings
- Rename variables to more sensible names
- Change the variable and argument types if necessary (especially pointer and array types)
- Change function names to be more descriptive
- If more details are necessary, disassemble the function and add comments with your findings
- NEVER convert number bases yourself. Use the `int_convert` MCP tool if needed!
- Do not attempt brute forcing, derive any solutions purely from the disassembly and simple python scripts
- Create a report.md with your findings and steps taken at the end
- When you find a solution, prompt to user for feedback with the password you found

This prompt was just the first experiment, please share if you found ways to improve the output!

Another prompt by @can1357:

Your task is to create a complete and comprehensive reverse engineering analysis. Reference AGENTS.md to understand the project goals and ensure the analysis serves our purposes.

Use the following systematic methodology:

1. **Decompilation Analysis**
   - Thoroughly inspect the decompiler output
   - Add detailed comments documenting your findings
   - Focus on understanding the actual functionality and purpose of each component (do not rely on old, incorrect comments)

2. **Improve Readability in the Database**
   - Rename variables to sensible, descriptive names
   - Correct variable and argument types where necessary (especially pointers and array types)
   - Update function names to be descriptive of their actual purpose

3. **Deep Dive When Needed**
   - If more details are necessary, examine the disassembly and add comments with findings
   - Document any low-level behaviors that aren't clear from the decompilation alone
   - Use sub-agents to perform detailed analysis

4. **Important Constraints**
   - NEVER convert number bases yourself - use the int_convert MCP tool if needed
   - Use MCP tools to retrieve information as necessary
   - Derive all conclusions from actual analysis, not assumptions

5. **Documentation**
   - Produce comprehensive RE/*.md files with your findings
   - Document the steps taken and methodology used
   - When asked by the user, ensure accuracy over previous analysis file
   - Organize findings in a way that serves the project goals outlined in AGENTS.md or CLAUDE.md

Live stream discussing prompting and showing some real-world malware analysis:

Tips for Enhancing LLM Accuracy

Large Language Models (LLMs) are powerful tools, but they can sometimes struggle with complex mathematical calculations or exhibit "hallucinations" (making up facts). Make sure to tell the LLM to use the int_convert MCP tool and you might also need math-mcp for certain operations.

Another thing to keep in mind is that LLMs will not perform well on obfuscated code. Before trying to use an LLM to solve the problem, take a look around the binary and spend some time (automatically) removing the following things:

• String encryption
• Import hashing
• Control flow flattening
• Code encryption
• Anti-decompilation tricks

You should also use a tool like Lumina or FLIRT to try and resolve all the open source library code and the C++ STL, this will further improve the accuracy.

Transports & Headless MCP

You can run an SSE server to connect to the user interface like this:

uv run ida-pro-mcp --transport http://127.0.0.1:8744/sse

After installing idalib you can also run a headless MCP server. You can start with an initial binary:

uv run idalib-mcp --host 127.0.0.1 --port 8745 path/to/executable

Or start without a binary and open/close arbitrary files later with idalib_open(...) / idalib_close(...):

uv run idalib-mcp --host 127.0.0.1 --port 8745

For stdio-based clients, use:

uv run idalib-mcp --stdio

Note: The idalib feature was contributed by Willi Ballenthin.

Headless idalib Session Model

idalib-mcp is a supervisor that keeps each open database in its own idalib worker process. Starting without an input_path is supported; use idalib_open(input_path, ...) to open databases dynamically and idalib_close(session_id) to close them. This allows one headless MCP server to work with arbitrary files over its lifetime.

If the requested IDB is already open in a GUI IDA instance running the plugin, idalib-mcp will use that GUI instance instead of spawning a duplicate headless worker. If the GUI instance later disappears, the next routed request reopens the database in a headless worker when possible. Unsaved GUI-only changes must be saved first if they should be visible after fallback.

Tools target either the database bound to the current MCP context or an explicit database argument.

uv run idalib-mcp --stdio --max-workers 4

Typical flow:

idalib_open("/path/to/binary_a.exe", session_id="binary_a")
idalib_open("/path/to/library.dll", session_id="library")

decompile("main", database="binary_a")
xrefs_to("ImportantExport", database="library")

database accepts a session ID, filename, or input path. If omitted, tools use the database bound to the active context.

Use --isolated-contexts to enable strict per-transport isolation:

uv run idalib-mcp --isolated-contexts --host 127.0.0.1 --port 8745 path/to/executable

Why use --isolated-contexts?

Use it when multiple agents connect to the same idalib-mcp server and you want deterministic context isolation:

• Prevent one agent from changing another agent's active database accidentally.
• Keep each transport context's default database explicit.
• Still allow intentional collaboration by passing database=... or binding multiple agents to the same session ID.

When --isolated-contexts is enabled:

• Each transport context has its own binding (Mcp-Session-Id for /mcp, session for /sse, stdio:default for stdio).
• Unbound contexts fail fast for IDB-dependent tools/resources unless database is provided.
• idalib_switch(session_id) and idalib_open(...) bind the caller context only.

Streamable HTTP behavior

With --isolated-contexts, strict Streamable HTTP session semantics are enabled, including Mcp-Session-Id validation.

Context tools

• idalib_open(input_path, ...): Open binary in a worker and bind it to the active context policy.
• idalib_switch(session_id): Rebind the active context policy to an existing session.
• idalib_current(): Return the session bound to the active context policy.
• idalib_unbind(): Remove the active context binding.
• idalib_list(): Includes is_active, is_current_context, bound_contexts, backend (worker or gui), and process IDs.

Worker controls:

• --max-workers N: maximum simultaneous database workers (0 = unlimited, default 4).
• IDA_MCP_MAX_WORKERS: environment default for --max-workers.

MCP Resources

Resources represent browsable state (read-only data) following MCP's philosophy.

Core IDB State:

• ida://idb/metadata - IDB file info (path, arch, base, size, hashes)
• ida://idb/segments - Memory segments with permissions
• ida://idb/entrypoints - Entry points (main, TLS callbacks, etc.)

UI State:

• ida://cursor - Current cursor position and function
• ida://selection - Current selection range

Type Information:

• ida://types - All local types
• ida://structs - All structures/unions
• ida://struct/{name} - Structure definition with fields

Lookups:

• ida://import/{name} - Import details by name
• ida://export/{name} - Export details by name
• ida://xrefs/from/{addr} - Cross-references from address

Core Functions

• lookup_funcs(queries): Get function(s) by address or name (auto-detects, accepts list or comma-separated string).
• int_convert(inputs): Convert numbers to different formats (decimal, hex, bytes, ASCII, binary).
• list_funcs(queries): List functions (paginated, filtered).
• list_globals(queries): List global variables (paginated, filtered).
• imports(offset, count): List all imported symbols with module names (paginated).
• decompile(addr): Decompile function at the given address.
• disasm(addr): Disassemble function with full details (arguments, stack frame, etc).
• xrefs_to(addrs): Get all cross-references to address(es).
• xrefs_to_field(queries): Get cross-references to specific struct field(s).
• callees(addrs): Get functions called by function(s) at address(es).

Modification Operations

• set_comments(items): Set comments at address(es) in both disassembly and decompiler views.
• patch_asm(items): Patch assembly instructions at address(es).
• declare_type(decls): Declare C type(s) in the local type library.
• define_func(items): Define function(s) at address(es). Optionally specify end for explicit bounds.
• define_code(items): Convert bytes to code instruction(s) at address(es).
• undefine(items): Undefine item(s) at address(es), converting back to raw bytes. Optionally specify end or size.

Memory Reading Operations

• get_bytes(addrs): Read raw bytes at address(es).
• get_int(queries): Read integer values using ty (i8/u64/i16le/i16be/etc).
• get_string(addrs): Read null-terminated string(s).
• get_global_value(queries): Read global variable value(s) by address or name (auto-detects, compile-time values).

Stack Frame Operations

• stack_frame(addrs): Get stack frame variables for function(s).
• declare_stack(items): Create stack variable(s) at specified offset(s).
• delete_stack(items): Delete stack variable(s) by name.

Structure Operations

• read_struct(queries): Read structure field values at specific address(es).
• search_structs(filter): Search structures by name pattern.

Debugger Operations (Extension)

Debugger tools are hidden by default. Enable with ?ext=dbg query parameter:

http://127.0.0.1:13337/mcp?ext=dbg

Control:

• dbg_start(): Start debugger process.
• dbg_exit(): Exit debugger process.
• dbg_continue(): Continue execution.
• dbg_run_to(addr): Run to address.
• dbg_step_into(): Step into instruction.
• dbg_step_over(): Step over instruction.

Breakpoints:

• dbg_bps(): List all breakpoints.
• dbg_add_bp(addrs): Add breakpoint(s).
• dbg_delete_bp(addrs): Delete breakpoint(s).
• dbg_toggle_bp(items): Enable/disable breakpoint(s).

Registers:

• dbg_regs(): All registers, current thread.
• dbg_regs_all(): All registers, all threads.
• dbg_regs_remote(tids): All registers, specific thread(s).
• dbg_gpregs(): GP registers, current thread.
• dbg_gpregs_remote(tids): GP registers, specific thread(s).
• dbg_regs_named(names): Named registers, current thread.
• dbg_regs_named_remote(tid, names): Named registers, specific thread.

Stack & Memory:

• dbg_stacktrace(): Call stack with module/symbol info.
• dbg_read(regions): Read memory from debugged process.
• dbg_write(regions): Write memory to debugged process.

Advanced Analysis Operations

• py_eval(code): Execute arbitrary Python code in IDA context (returns dict with result/stdout/stderr, supports Jupyter-style evaluation).
• analyze_funcs(addrs): Comprehensive function analysis (decompilation, assembly, xrefs, callees, callers, strings, constants, basic blocks).

Pattern Matching & Search

• find_regex(queries): Search strings with case-insensitive regex (paginated).
• find_bytes(patterns, limit=1000, offset=0): Find byte pattern(s) in binary (e.g., "48 8B ?? ??"). Max limit: 10000.
• find_insns(sequences, limit=1000, offset=0): Find instruction sequence(s) in code. Max limit: 10000.
• find(type, targets, limit=1000, offset=0): Advanced search (immediate values, strings, data/code references). Max limit: 10000.

Control Flow Analysis

• basic_blocks(addrs): Get basic blocks with successors and predecessors.

Type Operations

• set_type(edits): Apply type(s) to functions, globals, locals, or stack variables.
• infer_types(addrs): Infer types at address(es) using Hex-Rays or heuristics.

Export Operations

• export_funcs(addrs, format): Export function(s) in specified format (json, c_header, or prototypes).

Graph Operations

• callgraph(roots, max_depth): Build call graph from root function(s) with configurable depth.

Batch Operations

• rename(batch): Unified batch rename operation for functions, globals, locals, and stack variables (accepts dict with optional func, data, local, stack keys).
• patch(patches): Patch multiple byte sequences at once.
• put_int(items): Write integer values using ty (i8/u64/i16le/i16be/etc).

Key Features:

• Type-safe API: All functions use strongly-typed parameters with TypedDict schemas for better IDE support and LLM structured outputs
• Batch-first design: Most operations accept both single items and lists
• Consistent error handling: All batch operations return [{..., error: null|string}, ...]
• Cursor-based pagination: Search functions return cursor: {next: offset} or {done: true} (default limit: 1000, enforced max: 10000 to prevent token overflow)
• Performance: Strings are cached with MD5-based invalidation to avoid repeated build_strlist calls in large projects

Comparison with other MCP servers

There are a few IDA Pro MCP servers floating around, but I created my own for a few reasons:

1. Installation should be fully automated.
2. The architecture of other plugins make it difficult to add new functionality quickly (too much boilerplate of unnecessary dependencies).
3. Learning new technologies is fun!

If you want to check them out, here is a list (in the order I discovered them):

• https://github.com/taida957789/ida-mcp-server-plugin (SSE protocol only, requires installing dependencies in IDAPython).
• https://github.com/fdrechsler/mcp-server-idapro (MCP Server in TypeScript, excessive boilerplate required to add new functionality).
• https://github.com/MxIris-Reverse-Engineering/ida-mcp-server (custom socket protocol, boilerplate).

Feel free to open a PR to add your IDA Pro MCP server here.

Development

Adding new features is a super easy and streamlined process. All you have to do is add a new @tool function to the modular API files in src/ida_pro_mcp/ida_mcp/api_*.py and your function will be available in the MCP server without any additional boilerplate! Below is a video where I add the get_metadata function in less than 2 minutes (including testing):

https://github.com/user-attachments/assets/951de823-88ea-4235-adcb-9257e316ae64

To test the MCP server itself:

npx -y @modelcontextprotocol/inspector

This will open a web interface at http://localhost:5173 and allow you to interact with the MCP tools for testing.

For testing I create a symbolic link to the IDA plugin and then POST a JSON-RPC request directly to http://localhost:13337/mcp. After enabling symbolic links you can run the following command:

uv run ida-pro-mcp --install

Generate the changelog of direct commits to main:

git log --first-parent --no-merges 1.2.0..main "--pretty=- %s"