Updated March 2026

Install BinjaLattice MCP

Pick your client, copy the command, done.

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add -e "BNJLAT=${BNJLAT}" binja-lattice -- node "<FULL_PATH_TO_BINJA_LATTICE_MCP>/dist/index.js"

Replace <FULL_PATH_TO_BINJA_LATTICE_MCP>/dist/index.js with the actual folder you prepared in step 1.

Required:BNJLAT

Environment Variables

Set these before running BinjaLattice MCP.

VariableDescriptionRequired
BNJLATThe API key generated by the Binary Ninja plugin server.Yes

Available Tools (5)

Once configured, BinjaLattice MCP gives your AI agent access to:

get_binary_infoGet metadata about the binary including architecture, entry point, and segments.
get_function_pseudocodeGet decompiled C-like pseudocode for a specific function.
function_name
update_function_nameRename a function within the Binary Ninja database.
old_namenew_name
add_comment_to_addressAdd a comment at a specific memory address.
addresscomment
search_bytesSearch for hex byte patterns with wildcard support.
pattern

Try It Out

After setup, try these prompts with your AI agent:

Analyze the current binary and provide a summary of its architecture, entry point, and total function count.
Decompile the function 'main' and explain what it does in plain English.
Find all cross-references to the 'decrypt_data' function.
Rename the function at the current address to 'init_network_socket' and add a comment explaining its purpose.
Search for the byte pattern '48 89 ?? 24' to identify potential stack operations.
Prerequisites & system requirements
  • An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
  • Python 3.8+ with pip installed
  • BNJLAT — The API key generated by the Binary Ninja plugin server.
Alternative installation methods

Manual Installation

python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt

Keep this setup from going cold

Save the docs, env vars, and workflow around BinjaLattice MCP in Conare so Claude Code, Codex, and Cursor remember it next time.

Need the legacy visual installer? Open Conare IDE.
Remember this setup