Skip to main content
Glama

MCP RE Server

MCP server for Reverse Engineering & Binary Analysis with backend development tools.

Features

Reverse Engineering Tools

Tool

Description

ghidra_analyze

Analyze binary with Ghidra (headless mode)

ghidra_decompile

Decompile binary functions with Ghidra

yara_scan

Scan files with YARA rules for malware indicators

analyze_binary

Static analysis - extract strings, checksec, binary info

radare2_analyze

Analyze with Radare2 (functions, imports, strings)

pestudio_analyze

Analyze PE (Windows) files

dynamic_analysis

Behavioral analysis on suspicious files

network_analysis

Analyze pcap files for IOCs

memory_forensics

Memory dump analysis with Volatility commands

gdb_debug

Debug binaries with GDB

Backend Development Tools

Tool

Description

analyze_project

Analyze project structure, language, framework

review_security

Scan for hardcoded secrets, SQL injection, XSS

analyze_api

List all API endpoints

validate_api_structure

Check REST best practices

get_architecture_advice

Architectural recommendations

scaffold_project

Generate project with Docker & tests

add_docker

Add Docker configuration

add_tests

Add unit & integration tests

execute_command, read_file, write_file, list_directory

File operations

Related MCP server: Binary MCP Server

Quick Start

npm install
npm run server

Environment Variables

Variable

Description

Default

GHIDRA_PATH

Ghidra installation path

/opt/ghidra

YARA_RULES_PATH

Custom YARA rules directory

./rules

Usage Examples

- "Analyze binary /path/to/binary with Ghidra"
- "Scan malware.exe with YARA rules"
- "Run dynamic analysis on suspicious file"
- "Analyze network capture traffic.pcap"
- "Decompile main function from binary"
- "Check security of my binary (checksec)"
- "Analyze memory dump memory.dmp"
- "Debug binary with GDB at main"
- "Analyze PE file with PE Studio"

Claude Desktop Config

{
  "mcpServers": {
    "mcp-re": {
      "command": "npm",
      "args": ["run", "server"],
      "workdir": "/path/to/mcp"
    }
  }
}

Requirements

RE Tools (optional)

  • Ghidra - Binary analysis & decompilation

  • YARA - Malware scanning

  • Radare2 - Binary analysis

  • checksec - Binary security checks

  • strings - String extraction

  • Volatility - Memory forensics

  • tshark - Network analysis

  • GDB - Debugging

Install on Kali/RE Linux:

sudo apt install yara radare2 checksec binutils volatility tshark gdb

Available Tools

22 tools
add_dockerC

Add Docker configuration to existing project

Inputs: hasDb, language, framework.

add_testsC

Add unit and integration tests

Inputs: hasDb, language, framework.

analyze_apiC

Analyze API endpoints in the project

Inputs: path.

analyze_binaryA

Static analysis: extract strings, check security (checksec), binary info

Inputs: filePath (required).

analyze_projectC

Analyze project structure and provide architectural feedback

Inputs: path.

dynamic_analysisB

Run dynamic/behavioral analysis on suspicious file

Inputs: filePath (required), timeout.

execute_commandC

Execute a shell command

Inputs: command (required), cwd.

gdb_debugA

Debug binary with GDB (set breakpoint, run, inspect)

Inputs: filePath (required), breakpoint.

get_architecture_adviceC

Get architectural advice based on requirements

Inputs: requirements (required), language.

ghidra_analyzeC

Analyze binary with Ghidra (headless mode)

Inputs: filePath (required), analysisType.

ghidra_decompileB

Decompile binary functions with Ghidra

Inputs: filePath (required), functionName.

list_directoryC

List directory contents

Inputs: path (required).

memory_forensicsC

Analyze memory dump - provides Volatility commands and quick wins

Inputs: dumpFile (required).

network_analysisB

Analyze network capture (pcap) for IOCs and traffic

Inputs: pcapFile (required).

pestudio_analyzeC

Analyze PE (Windows) file with PE Studio features

Inputs: filePath (required).

radare2_analyzeA

Analyze binary with Radare2 (functions, imports, strings)

Inputs: filePath (required).

read_fileD

Read a file

Inputs: path (required).

review_securityC

Review code for security vulnerabilities

Inputs: path (required).

scaffold_projectC

Generate project scaffold with Docker and tests

Inputs: language (required), requirements (required), outputDir.

validate_api_structureC

Validate API follows REST best practices

Inputs: path.

write_fileC

Write content to a file

Inputs: path (required), content (required).

yara_scanC

Scan file with YARA rules for malware indicators

Inputs: filePath (required), rulesPath.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 22 tools

    Disambiguation4/5

    Most tools target distinct resource+action pairs, but there is some overlap among binary analysis tools (analyze_binary, ghidra_analyze, radare2_analyze, pestudio_analyze) and between analyze_project and get_architecture_advice. Descriptions help differentiate them, so ambiguity is limited.

    Naming Consistency2/5

    Naming conventions are inconsistent: verb_noun (analyze_project, execute_command), tool_prefix_action (ghidra_analyze, yara_scan), and noun_phrase (network_analysis, memory_forensics) are mixed. While tool_prefix is consistent within the RE tools, overall there is no single predictable pattern.

    Tool Count3/5

    With 22 tools, the server is on the heavy side, and the mix of project development tools (scaffold_project, add_docker) with reverse engineering tools makes the scope feel broad. The count is within the 16-25 range but feels over-scoped for a supposed 'RE Server'.

    Completeness4/5

    The reverse engineering domain is well-covered: static analysis, dynamic analysis, memory forensics, network analysis, YARA scanning, and debugging. Minor gaps exist (e.g., no dedicated disassembly tool), but Ghidra/Radare2 handle that. The extra non-RE tools don't detract from RE completeness.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A headless Ghidra server that enables AI agents to perform deep reverse-engineering tasks such as disassembly, decompilation, and patching via the Model Context Protocol. It supports extensive automation of analysis workflows in sandboxed environments through a catalog of over 200 specialized tools.
      199
      GPL 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides 7 reverse-engineering tools (hexdump, disasm, strings, xref, Ghidra decompilation, angr symbolic execution, OLLVM deobfuscation) for LLM agents like hermes-agent and Claude Desktop.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to locally analyze and reverse engineer binaries through a compact 12-tool MCP interface for triage, function discovery, disassembly/decompilation, cross-references, strings/imports, call graphs, memory reads, annotations, and binary diffs.
      1
      MIT