Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

License GitHub release (latest by date) GitHub stars GitHub forks GitHub contributors Follow @lauriewired

ghidra_MCP_logo

ghidraMCP

ghidraMCP is an Model Context Protocol server for allowing LLMs to autonomously reverse engineer applications. It exposes numerous tools from core Ghidra functionality to MCP clients.

https://github.com/user-attachments/assets/36080514-f227-44bd-af84-78e29ee1d7f9

Features

MCP Server + Ghidra Plugin

  • Decompile and analyze binaries in Ghidra
  • Automatically rename methods and data
  • List methods, classes, imports, and exports

Installation

Prerequisites

Ghidra

First, download the latest release from this repository. This contains the Ghidra plugin and Python MCP client. Then, you can directly import the plugin into Ghidra.

  1. Run Ghidra
  2. Select File -> Install Extensions
  3. Click the + button
  4. Select the GhidraMCP-1-2.zip (or your chosen version) from the downloaded release
  5. Restart Ghidra
  6. Make sure the GhidraMCPPlugin is enabled in File -> Configure -> Developer
  7. Optional: Configure the port in Ghidra with Edit -> Tool Options -> GhidraMCP HTTP Server

Video Installation Guide:

https://github.com/user-attachments/assets/75f0c176-6da1-48dc-ad96-c182eb4648c3

The Python MCP client can be installed with either pipx install GhidraMCP or uv tool install GhidraMCP.

MCP Clients

Theoretically, any MCP client should work with ghidraMCP. Three examples are given below.

Example 1: Claude Desktop

To set up Claude Desktop as a Ghidra MCP client, go to Claude -> Settings -> Developer -> Edit Config -> claude_desktop_config.json and add the following:

{
  "mcpServers": {
    "ghidra": {
      "command": "python",
      "args": [
        "/ABSOLUTE_PATH_TO/bridge_mcp_ghidra.py",
        "--ghidra-server",
        "http://127.0.0.1:8080/"
      ]
    }
  }
}

Alternatively, edit this file directly:

/Users/YOUR_USER/Library/Application Support/Claude/claude_desktop_config.json

The server IP and port are configurable and should be set to point to the target Ghidra instance. If not set, both will default to localhost:8080.

If the GhidraMCP Python client was installed with pipx or uv tool, the first argument can be replaced with bridge_mcp_ghidra instead of giving an absolute path.

Example 2: Cline

To use GhidraMCP with Cline, this requires manually running the MCP server as well. First run the following command:

python bridge_mcp_ghidra.py --transport sse --mcp-host 127.0.0.1 --mcp-port 8081 --ghidra-server http://127.0.0.1:8080/

Or if the GhidraMCP Python client was installed with pipx or uv tool:

bridge_mcp_ghidra --transport sse --mcp-host 127.0.0.1 --mcp-port 8081 --ghidra-server http://127.0.0.1:8080/

The only required argument is the transport. If all other arguments are unspecified, they will default to the above. Once the MCP server is running, open up Cline and select MCP Servers at the top.

Cline select

Then select Remote Servers and add the following, ensuring that the url matches the MCP host and port:

  1. Server Name: GhidraMCP
  2. Server URL: http://127.0.0.1:8081/sse

Example 3: 5ire

Another MCP client that supports multiple models on the backend is 5ire. To set up GhidraMCP, open 5ire and go to Tools -> New and set the following configurations:

  1. Tool Key: ghidra
  2. Name: GhidraMCP
  3. Command: python /ABSOLUTE_PATH_TO/bridge_mcp_ghidra.py

If the GhidraMCP Python client was installed with pipx or uv tool, the command can be bridge_mcp_ghidra without needing to specify the python interpreter or giving an absolute path.

Building from Source

  1. Copy the following files from your Ghidra directory to this project's lib/ directory:
  • Ghidra/Features/Base/lib/Base.jar
  • Ghidra/Features/Decompiler/lib/Decompiler.jar
  • Ghidra/Framework/Docking/lib/Docking.jar
  • Ghidra/Framework/Generic/lib/Generic.jar
  • Ghidra/Framework/Project/lib/Project.jar
  • Ghidra/Framework/SoftwareModeling/lib/SoftwareModeling.jar
  • Ghidra/Framework/Utility/lib/Utility.jar
  • Ghidra/Framework/Gui/lib/Gui.jar
  1. Build with Maven by running:

mvn clean package assembly:single

The generated zip file includes the built Ghidra plugin and its resources. These files are required for Ghidra to recognize the new extension.

  • lib/GhidraMCP.jar
  • extensions.properties
  • Module.manifest

Metadata

Release files for ghidramcp 0.0.dev0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ghidramcp 0.0.dev0
File Size Uploaded
ghidramcp-0.0.dev0.tar.gz 9.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ghidramcp 0.0.dev0
File Interpreter ABI Platform
ghidramcp-0.0.dev0-py3-none-any.whl Python 3 none any Details

Total release size: 20.1 kB

Release files / ghidramcp-0.0.dev0.tar.gz

Download URL ghidramcp-0.0.dev0.tar.gz
Size 9.8 kB
Tags Source
SHA-256 checksum
How to use checksums
a2200060526ffbb67ead87196651771378402a11b164fb503fa5b962218e324e
BLAKE2b-256 checksum
How to use checksums
88c50cc986544362c7a2b2b3616553600701d11d33deeef5a674dc46ec58318d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 14, 2025.

Transparency log

Release files / ghidramcp-0.0.dev0-py3-none-any.whl

Download URL ghidramcp-0.0.dev0-py3-none-any.whl
Size 10.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0e47952c9046988d8fe25584adb894223bd94ece39e57f0a184f789e3cccc850
BLAKE2b-256 checksum
How to use checksums
18c653176a1c855570b737f4560451fe217b770846c9110dc5f8f95e69ffccc1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 14, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.0.dev0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page