
pcm
MCP for reverse engineering
1
Github Watches
5
Github Forks
32
Github Stars
pcm
PCM (MCP but reversed), MCP for reverse engineering.
Features
- Analysis
- IDA
- repl (IDAPython)
- disassembly
- decompilation
- set types
- ...
- IDA
- Memory
- Engagement reports
- Engagement reports
Full list of features
- `get_function_by_name(name)`: Get a function by its name.
- `get_function_by_address(address)`: Get a function by its address.
- `get_current_address()`: Get the address currently selected by the user.
- `get_current_function()`: Get the function currently selected by the user.
- `list_functions()`: List all functions in the database.
- `decompile_function(address)`: Decompile a function at the given address using Hex-Rays.
- `disassemble_function(address)`: Get assembly code (address: instruction; comment) for a function.
- `get_entrypoints()`: Get all entrypoints in the binary.
- `get_function_blocks(address)`: Get all basic blocks in a function.
- `get_function_cfg(address)`: Get control flow graph for a function.
- `get_xrefs_to(address)`: Get all cross references to the given address.
- `get_xrefs_from(address)`: Get all cross references from the given address.
- `set_decompiler_comment(address, comment)`: Set a comment for a given address in the function pseudocode.
- `set_disassembly_comment(address, comment)`: Set a comment for a given address in the function disassembly.
- `rename_local_variable(function_address, old_name, new_name)`: Rename a local variable in a function.
- `rename_function(function_address, new_name)`: Rename a function.
- `set_function_prototype(function_address, prototype)`: Set a function's prototype.
- `set_local_variable_type(function_address, variable_name, new_type)`: Set a local variable's type.
- `create_structure_type(name, members, is_union)`: Create a new structure type.
- `get_metadata()`: Get metadata about the current IDB.
- `repl_idapython(content)`: Run IDAPython code and return the results with stdout/stderr captured.
- `add_note(title, content, address, tags)`: Add a new analysis note for the current binary.
- `update_note(note_id, title, content, tags)`: Update an existing note.
- `get_notes(file_md5, address, tag)`: Get analysis notes for a binary.
- `delete_note(note_id)`: Delete an analysis note.
Installations
Prerequisites:
- Clone the repository
git clone https://github.com/rand-tech/pcm
- Add
pcm
to you mcp config example{ "mcpServers": { "pcm": { "command": "uv", "args": [ "--directory", "path_to/pcm", "run", "server.py" ] } } }
- Use the MCP
Related projects:
- https://github.com/mrexodia/ida-pro-mcp
- https://github.com/MxIris-Reverse-Engineering/ida-mcp-server
Attribution: This project is based on IDA Pro MCP by Duncan Ogilvie (@mrexodia). Thank you
License: This project is licensed under the MIT License - see the LICENSE file for details. The original code is also licensed under the MIT License.
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
🧑🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Reviews

user_9Tw3qucI
I've been using PCM from rand-tech and it's remarkable! The versatility and functionality it offers are impressive. It's user-friendly, and the performance is top-notch. Highly recommended for anyone looking for reliable and efficient project management software. Check it out on GitHub!