What is ida-pro-mcp-multi CLAUDE.md?

A project instruction guide for an MCP server that connects AI tools to IDA Pro, a program used to inspect and reverse-engineer compiled software. It documents the server, its gateway, the IDA Pro plugin, and development commands.

Use it when developing, installing, or testing the IDA Pro MCP server, gateway, plugin, and interactive MCP inspector.

It gives contributors a shared explanation of how the parts communicate and how to run or test the project without having to discover the setup themselves.

How QYmag1c/ida-pro-mcp-multi configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QYmag1c/ida-pro-mcp-multi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QYmag1c/ida-pro-mcp-multi/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/QYmag1c/ida-pro-mcp-multi

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/qymag1c/ida-pro-mcp-multi/claude-md/github.svg)](https://agentmods.dev/instructions/qymag1c/ida-pro-mcp-multi/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/qymag1c/ida-pro-mcp-multi/claude-md"><img src="https://agentmods.dev/badge/instructions/qymag1c/ida-pro-mcp-multi/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/qymag1c/ida-pro-mcp-multi/claude-md"><img src="https://agentmods.dev/badge/instructions/qymag1c/ida-pro-mcp-multi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,766 This file is loaded in full into every session.

When invoked 2,766 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02766	$0.02766
Opus 5	$0.01383	$0.01383
Sonnet 5	$0.00553	$0.00553
Haiku 4.5	$0.00277	$0.00277

Measured 10d ago against content hash 2e8616f08c89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ida-pro-mcp-multi CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

IDA Pro MCP Server - enables LLM-assisted reverse engineering by bridging IDA Pro with Model Context Protocol clients through a JSON-RPC HTTP server.

Architecture: Multi-instance Gateway design

MCP Server (server.py): Python >=3.11, runs via uv, proxies to Gateway
Gateway Server (gateway.py): Routes requests to multiple IDA instances (port 13337)
IDA Plugin (ida_mcp.py): Runs inside IDA Pro, registers with Gateway, exposes MCP server over HTTP (ports 13338+)

AI Client ──MCP──> Gateway (port 13337) ──> IDA Instance 1 (port 13338)
                                        ──> IDA Instance 2 (port 13339)
                                        ──> IDA Instance N (port 1333N+1)

Development Commands

Testing MCP Server

# Interactive MCP inspector (web UI at http://localhost:5173)
uv run mcp dev src/ida_pro_mcp/server.py

Installation

# Install package + configure all MCP clients + install IDA plugin
pip install https://github.com/mrexodia/ida-pro-mcp/archive/refs/heads/main.zip
ida-pro-mcp --install

# Manual plugin install (creates symlinks or copies to IDA plugins folder)
uv run ida-pro-mcp --install

# Uninstall everything
uv run ida-pro-mcp --uninstall

Running

# Standard stdio transport (used by most MCP clients)
uv run ida-pro-mcp

# SSE transport for headless/remote use
uv run ida-pro-mcp --transport http://127.0.0.1:8744/sse

# Headless mode with idalib (no GUI)
uv run idalib-mcp --host 127.0.0.1 --port 8745 path/to/binary

# Enable unsafe debugger functions
uv run ida-pro-mcp --unsafe

Changelog Generation

# Direct commits to main since tag
git log --first-parent --no-merges 1.2.0..main "--pretty=- %s"

Architecture Deep Dive

Plugin Architecture (ida_mcp/)

Modular API: 9 specialized modules

api_core.py: IDB metadata, function/string/import listing
api_analysis.py: Decompilation, disassembly, xrefs, paths, patterns
api_memory.py: Read bytes/integers/strings, patch operations
api_types.py: Structures, type inference, type application
api_modify.py: Comments, assembly patching, renaming
api_stack.py: Stack frame operations
api_debug.py: Debugger control (unsafe, requires --unsafe flag)
api_python.py: Python code execution in IDA context
api_resources.py: MCP resources (24 URI patterns for RESTful access via ida:// URIs)

Read the full file on GitHub · 330 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 330 lines · 2,766 tokens per session scan A 2e8616f08c89

Subscribe to this mod's changes

ida-pro-mcp-multi CLAUDE.md is an instructions file published in the GitHub repository QYmag1c/ida-pro-mcp-multi (12 stars, last pushed 2mo ago), licensed MIT. It adds 2,766 tokens to every session, about $0.0138 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ida-pro-mcp-multi: Instructions file for Claude Code