What is ghidra-mcp AGENTS.md?

Project-specific instructions for ghidra-mcp, a tool that connects Ghidra—a program for examining compiled software—with AI tools. They describe the repository, its Java and Python parts, priorities, and development rules.

Use them when changing ghidra-mcp, especially for maintaining its Ghidra extension and Python bridge, keeping endpoint records aligned, running tests, and checking CI-related work.

An agent working in an unfamiliar repository can otherwise overlook its structure, required checks, or current maintenance priorities. These instructions provide that project context in one place.

How bethington/ghidra-mcp configures Codex and OpenCode

About the project

Ghidra MCP Server connects Ghidra, a software reverse-engineering tool for examining compiled programs, to AI tools through the Model Context Protocol (MCP), a standard way for applications to expose actions and data to language models. Reverse engineers use it to analyze binaries, automate batch work, and interact with Ghidra through graphical or headless operation. The catalogue entries provide instructions and MCP integration for working with the server.

bethington/ghidra-mcp · 3,728 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to bethington/ghidra-mcp. 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/bethington/ghidra-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bethington/ghidra-mcp

Made for: Codex, OpenCode.

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/bethington/ghidra-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/bethington/ghidra-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bethington/ghidra-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bethington/ghidra-mcp/agents-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/bethington/ghidra-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bethington/ghidra-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 575 This file is loaded in full into every session.

When invoked 575 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	$0.00575	$0.00575
Opus 5	$0.00287	$0.00287
Sonnet 5	$0.00115	$0.00115
Haiku 4.5	$0.00057	$0.00057

Measured 9d ago against content hash 558f248fb21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ghidra-mcp AGENTS.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 9d 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ghidra-mcp Project

You are a coding agent working on ghidra-mcp, a Model Context Protocol server that bridges Ghidra's reverse engineering capabilities with AI tools.

Project Context

Repo: https://github.com/bethington/ghidra-mcp
Version: 7.0.0
Language: Java (Ghidra extension) + Python (MCP bridge)
Key feature: 267 for binary analysis, knowledge database, BSim integration, headless server support, AI documentation workflows

Directory Structure

src/ — Java source for Ghidra extension and headless server
python/bridge_mcp_ghidra/ — Python MCP bridge package (bridge-mcp-ghidra console script / python -m bridge_mcp_ghidra)
pyproject.toml + uv.lock — uv project (ships the ghidra-mcp-bridge wheel; deps via PEP 735 groups)
docs/ — Documentation and workflow prompts
tests/ — Python unit tests and endpoint catalog
CHANGELOG.md — Version history

Current Priorities

Maintain headless server parity with GUI plugin endpoints
Keep tests/endpoints.json in sync with Java endpoint registrations
Maintain CI/CD pipeline health
Community PR reviews

Guidelines

Run tests before committing: pytest tests/unit/ -v --no-cov
Build: mvn clean package assembly:single -DskipTests
Quick compile check: mvn clean compile -q
Follow existing code style
Update CHANGELOG.md for user-facing changes
Create PRs for review (don't push directly to main)
Use python -m tools.setup bump-version --new X.Y.Z to bump version across all maintained files atomically

Commands

Build: mvn clean package assembly:single -DskipTests
Quick compile: mvn clean compile -q
Test (Python): pytest tests/unit/ -v --no-cov
Preflight: python -m tools.setup preflight --ghidra-path F:\ghidra_12.1.2_PUBLIC
Deploy: python -m tools.setup ensure-prereqs --ghidra-path F:\ghidra_12.1.2_PUBLIC then python -m tools.setup build then python -m tools.setup deploy --ghidra-path F:\ghidra_12.1.2_PUBLIC
Version bump: python -m tools.setup bump-version --new X.Y.Z

Read the full file on GitHub · 46 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.

9d ago First seen · 46 lines · 575 tokens per session scan A 558f248fb21f

Subscribe to this mod's changes

ghidra-mcp AGENTS.md is an instructions file published in the GitHub repository bethington/ghidra-mcp (3,728 stars, last pushed 5d ago), licensed Apache-2.0. It adds 575 tokens to every session, about $0.0029 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 2026-08-30.

Java Python binary-analysis ghidra mcp model-context-protocol

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

ghidra-mcp: Instructions file for Codex