About binary_ninja_cline_mcp
binary_ninja_cline_mcp bridges Cline with Binary Ninja so binaries can be analyzed through MCP. It is intended for setups using the Binary Ninja MCP Plugin and a local HTTP bridge.
Key features
- 01Connect Cline with Binary Ninja
- 02Enable binary analysis through MCP
- 03Bridge to a local HTTP server
Use cases
- 01Analyze an opened binary from Cline
- 02Connect Cline to a Binary Ninja MCP server
MCP support
Provides an MCP server for Cline and connects it to Binary Ninja through the Binary Ninja MCP Plugin and an HTTP bridge.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEbinary_ninja_cline_mcp
An MCP server for Cline that works with Binary Ninja (Personal License)
This repository contains an MCP server that allows Cline to analyze binaries using Binary Ninja. Note: Not all files will be used, there is also prototype of using headless Binary Ninja but my license is Personal so I can't test it.
Setup
- Install the latest of Binary Ninja MCP Plugin https://github.com/fosdickio/binary_ninja_mcp
- Open your binary and start the MCP server from within Binary Ninja.
- Open a terminal and run python binary_ninja_mcp_http_server.py --port 8088
- Open another terminal and run
npm start - Open Cline and add the following tool:{ Example:
{
"mcpServers": {
"BN MCP": {
"command": "node",
"args": ["/home/matteius/binary_ninja_cline/bn_cline_mcp/binaryninja-mcp-bridge.js"],
"env": {
"BN_HTTP_SERVER": "http://localhost:8088"
},
"autoApprove": [],
"disabled": false,
"timeout": 30
}
}
}
Comments
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.
