Ghidra Mcp Analysis logo

Ghidra Mcp Analysis

Organization
SpecterOps
ghidra-mcp-analysis

Use for reverse engineering and binary analysis with LaurieWired/GhidraMCP. Trigger for Ghidra MCP setup, bridge_mcp_ghidra.py usage, GhidraMCP plugin workflows, decompilation, function/string/import/export/xref analysis, renaming functions/data/variables, setting comments/types/prototypes, or producing Ghidra-backed RE notes.

Overview

PublisherSpecterOps
Repositoryskills
Skill nameghidra-mcp-analysis
Stars
706
Forks
80
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SpecterOps on GitHub. Read the source before you install it.

Installation

Install the Ghidra Mcp Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SpecterOps/skills/tree/main/plugins/reverse-engineering/skills/ghidra-mcp-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SpecterOps/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/reverse-engineering/skills/ghidra-mcp-analysis .claude/skills/ghidra-mcp-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ghidra Mcp Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ghidra Mcp Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ghidra Mcp Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Ghidra MCP Analysis

Implementation target

This skill assumes the Ghidra MCP implementation is LaurieWired/GhidraMCP. It uses:

  • a Ghidra extension/plugin that exposes a local HTTP server from Ghidra, defaulting to http://127.0.0.1:8080/
  • bridge_mcp_ghidra.py, a Python MCP bridge that talks to the Ghidra-side HTTP server
  • stdio transport by default for Codex MCP, with optional SSE mode for clients that need it

Setup checklist

  1. Install Ghidra and Python 3.
  2. Download a LaurieWired/GhidraMCP release ZIP.
  3. In Ghidra: File -> Install Extensions -> + -> select the GhidraMCP-*.zip release.
  4. Restart Ghidra.
  5. Enable GhidraMCPPlugin in File -> Configure -> Developer.
  6. Optionally configure the Ghidra-side HTTP port with Edit -> Tool Options -> GhidraMCP HTTP Server.
  7. Configure Codex to run the bridge:
toml
[mcp_servers.ghidra]
command = "python3"
args = [
  "/ABSOLUTE_PATH_TO/GhidraMCP/bridge_mcp_ghidra.py",
  "--ghidra-server",
  "http://127.0.0.1:8080/"
]

Restart Codex and verify the ghidra MCP server is visible under /mcp before using live analysis.

Available LaurieWired/GhidraMCP capabilities

Use these capabilities by their MCP tool names when available:

CapabilityTool(s)
Current contextget_current_address, get_current_function, get_function_by_address
Function listing/searchlist_methods, list_functions, search_functions_by_name
Classes/namespaceslist_classes, list_namespaces
Decompilation/disassemblydecompile_function, decompile_function_by_address, disassemble_function
Imports/exports/segments/datalist_imports, list_exports, list_segments, list_data_items
Stringslist_strings with optional filter
Xrefsget_xrefs_to, get_xrefs_from, get_function_xrefs
Renamingrename_function, rename_function_by_address, rename_data, rename_variable
Commentsset_decompiler_comment, set_disassembly_comment
Types/prototypesset_function_prototype, set_local_variable_type

Recommended workflow

  1. Orient

    • Confirm Ghidra has the target program open and analyzed.
    • Use get_current_function / get_current_address when the user points at something in the UI.
    • Use list_segments, list_imports, list_exports, and filtered list_strings for initial context.
  2. Survey efficiently

    • Prefer search_functions_by_name and list_strings(filter=...) over dumping everything.
    • Use pagination (offset, limit) for list_methods, list_classes, list_imports, list_exports, list_data_items, and list_strings.
  3. Analyze functions

    • Use decompile_function_by_address when an address is known.
    • Use decompile_function when a stable symbol/function name is known.
    • Use disassemble_function when decompiler output is ambiguous, optimized out, or missing low-level details.
  4. Trace relationships

    • Use get_xrefs_to / get_xrefs_from for address-oriented tracing.
    • Use get_function_xrefs for function-name-oriented tracing.
    • Build source -> transform -> sink chains with exact addresses and function names.
  5. Annotate only with evidence

    • Use rename_function_by_address or rename_function when behavior is confirmed.
    • Use rename_variable, rename_data, set_function_prototype, and set_local_variable_type incrementally.
    • Use set_decompiler_comment or set_disassembly_comment to record reasoning at important addresses.
  6. Report

    • Include addresses, original names, new names/comments/types applied, decompiler/disassembly evidence, xref paths, and confidence.
    • Separate confirmed behavior from hypotheses.

Reference loading

Read references/workflow.md for LaurieWired/GhidraMCP transport details, tool recipes, and output templates.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ghidra Mcp Analysis AI skill do?

Use for reverse engineering and binary analysis with LaurieWired/GhidraMCP. Trigger for Ghidra MCP setup, bridge_mcp_ghidra.py usage, GhidraMCP plugin workflows, decompilation, function/string/import/export/xref analysis, renaming functions/data/variables, setting comments/types/prototypes, or producing Ghidra-backed RE notes.

Why use Ghidra Mcp Analysis on TypingMind?

Because you install it once and use it with any model. Ghidra Mcp Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ghidra Mcp Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpecterOps/skills/tree/main/plugins/reverse-engineering/skills/ghidra-mcp-analysis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ghidra Mcp Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ghidra Mcp Analysis?

As many as you like. As long as a model supports skills, you can use Ghidra Mcp Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ghidra Mcp Analysis AI skill free?

Yes. It is published on GitHub by SpecterOps under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇