mcpField
M
mcp-capstone

mcp-capstone

Local
github.com/daedalusDeveloper Tools0Updated 27w ago
Repository

About mcp-capstone

mcp-capstone exposes Capstone 5.0.7 disassembly functions to LLMs through MCP tools and resources. It supports instruction analysis across architectures including x86, ARM, RISC-V, and WebAssembly.

Key features

  1. 01Full, lightweight, and quick disassembly
  2. 02Support checks and architecture listing
  3. 03Architecture and mode constants
  4. 04Operand, group, and error constants

Use cases

  1. 01Disassemble binary instructions
  2. 02Analyze instruction details across architectures

MCP support

Exposes Capstone disassembly functions and related architecture information as MCP tools and resources for MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "daedalus-mcp-capstone": {
      "command": "uvx",
      "args": [
        "mcp-capstone"
      ]
    }
  }
}
Run commanduvx mcp-capstone

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-capstone0.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-capstone

MCP server that exposes Capstone 5.0.7 disassembly framework functionalities as tools and resources, enabling LLMs to perform binary disassembly, reverse engineering, and instruction analysis.

PyPI Python

Install

pip install mcp-capstone

Usage

CLI
mcp-capstone
Python
from mcp_capstone import disasm, get_version

# Get version
version = get_version()
print(f"Capstone {version['major']}.{version['minor']}")

# Disassemble x86-64 code
instructions = disasm("8b440404", arch="x86", mode="64")
for insn in instructions:
    print(f"0x{insn['address']:x}: {insn['mnemonic']} {insn['op_str']}")

Supported Architectures

  • x86 (16/32/64-bit)
  • ARM (ARM, Thumb, ARM mode)
  • AArch64 (ARMv8)
  • MIPS (MIPS32/64, MIPS2/3, R6)
  • PowerPC (32/64-bit, SPE, QPX)
  • RISC-V (RV32/64GC)
  • SPARC (V8/V9)
  • SystemZ
  • M68K (68000-68060)
  • M680X (6301/6309/6800/6805/6808/6809/6811/CPU12/HCS08)
  • TriCore
  • TMS320C64X
  • WebAssembly
  • XCore
  • BPF (Classic/Extended)
  • EVM (Ethereum Virtual Machine)

Tools

ToolDescription
get_versionGet Capstone version
check_supportCheck architecture support
list_architecturesList all architectures
disasmFull disassembly with details
disasm_liteLightweight disassembly
disasm_quickQuick disassembly
get_architecturesAll architecture constants
get_modesAll mode constants
get_optionsAll option constants
get_operandsAll operand type constants
get_groupsAll instruction group constants
get_errorsAll error constants

Development

git clone https://github.com/daedalus/mcp-capstone.git
cd mcp-capstone
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

mcp-name: io.github.daedalus/mcp-capstone

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.