[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-4163":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},4163,"GhidraMCP","LaurieWired\u002FGhidraMCP","LaurieWired","MCP Server for Ghidra","",null,"Java",9192,934,68,47,0,9,74,357,48,39.91,"Apache License 2.0",false,"main",true,[],"2026-06-12 02:00:59","[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg)](https:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0)\n[![GitHub release (latest by date)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FLaurieWired\u002FGhidraMCP)](https:\u002F\u002Fgithub.com\u002FLaurieWired\u002FGhidraMCP\u002Freleases)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLaurieWired\u002FGhidraMCP)](https:\u002F\u002Fgithub.com\u002FLaurieWired\u002FGhidraMCP\u002Fstargazers)\n[![GitHub forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLaurieWired\u002FGhidraMCP)](https:\u002F\u002Fgithub.com\u002FLaurieWired\u002FGhidraMCP\u002Fnetwork\u002Fmembers)\n[![GitHub contributors](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002FLaurieWired\u002FGhidraMCP)](https:\u002F\u002Fgithub.com\u002FLaurieWired\u002FGhidraMCP\u002Fgraphs\u002Fcontributors)\n[![Follow @lauriewired](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Flauriewired?style=social)](https:\u002F\u002Ftwitter.com\u002Flauriewired)\n\n![ghidra_MCP_logo](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4986d702-be3f-4697-acce-aea55cd79ad3)\n\n\n# ghidraMCP\nghidraMCP is an Model Context Protocol server for allowing LLMs to autonomously reverse engineer applications. It exposes numerous tools from core Ghidra functionality to MCP clients.\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F36080514-f227-44bd-af84-78e29ee1d7f9\n\n\n# Features\nMCP Server + Ghidra Plugin\n\n- Decompile and analyze binaries in Ghidra\n- Automatically rename methods and data\n- List methods, classes, imports, and exports\n\n# Installation\n\n## Prerequisites\n- Install [Ghidra](https:\u002F\u002Fghidra-sre.org)\n- Python3\n- MCP [SDK](https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fpython-sdk)\n\n## Ghidra\nFirst, download the latest [release](https:\u002F\u002Fgithub.com\u002FLaurieWired\u002FGhidraMCP\u002Freleases) from this repository. This contains the Ghidra plugin and Python MCP client. Then, you can directly import the plugin into Ghidra.\n\n1. Run Ghidra\n2. Select `File` -> `Install Extensions`\n3. Click the `+` button\n4. Select the `GhidraMCP-1-2.zip` (or your chosen version) from the downloaded release\n5. Restart Ghidra\n6. Make sure the GhidraMCPPlugin is enabled in `File` -> `Configure` -> `Developer`\n7. *Optional*: Configure the port in Ghidra with `Edit` -> `Tool Options` -> `GhidraMCP HTTP Server`\n\nVideo Installation Guide:\n\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F75f0c176-6da1-48dc-ad96-c182eb4648c3\n\n\n\n## MCP Clients\n\nTheoretically, any MCP client should work with ghidraMCP.  Three examples are given below.\n\n## Example 1: Claude Desktop\nTo set up Claude Desktop as a Ghidra MCP client, go to `Claude` -> `Settings` -> `Developer` -> `Edit Config` -> `claude_desktop_config.json` and add the following:\n\n```json\n{\n  \"mcpServers\": {\n    \"ghidra\": {\n      \"command\": \"python\",\n      \"args\": [\n        \"\u002FABSOLUTE_PATH_TO\u002Fbridge_mcp_ghidra.py\",\n        \"--ghidra-server\",\n        \"http:\u002F\u002F127.0.0.1:8080\u002F\"\n      ]\n    }\n  }\n}\n```\n\nAlternatively, edit this file directly:\n```\n\u002FUsers\u002FYOUR_USER\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json\n```\n\nThe server IP and port are configurable and should be set to point to the target Ghidra instance. If not set, both will default to localhost:8080.\n\n## Example 2: Cline\nTo use GhidraMCP with [Cline](https:\u002F\u002Fcline.bot), this requires manually running the MCP server as well. First run the following command:\n\n```\npython bridge_mcp_ghidra.py --transport sse --mcp-host 127.0.0.1 --mcp-port 8081 --ghidra-server http:\u002F\u002F127.0.0.1:8080\u002F\n```\n\nThe only *required* argument is the transport. If all other arguments are unspecified, they will default to the above. Once the MCP server is running, open up Cline and select `MCP Servers` at the top.\n\n![Cline select](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F88e1f336-4729-46ee-9b81-53271e9c0ce0)\n\nThen select `Remote Servers` and add the following, ensuring that the url matches the MCP host and port:\n\n1. Server Name: GhidraMCP\n2. Server URL: `http:\u002F\u002F127.0.0.1:8081\u002Fsse`\n\n## Example 3: 5ire\nAnother MCP client that supports multiple models on the backend is [5ire](https:\u002F\u002Fgithub.com\u002Fnanbingxyz\u002F5ire). To set up GhidraMCP, open 5ire and go to `Tools` -> `New` and set the following configurations:\n\n1. Tool Key: ghidra\n2. Name: GhidraMCP\n3. Command: `python \u002FABSOLUTE_PATH_TO\u002Fbridge_mcp_ghidra.py`\n\n# Building from Source\n1. Copy the following files from your Ghidra directory to this project's `lib\u002F` directory:\n- `Ghidra\u002FFeatures\u002FBase\u002Flib\u002FBase.jar`\n- `Ghidra\u002FFeatures\u002FDecompiler\u002Flib\u002FDecompiler.jar`\n- `Ghidra\u002FFramework\u002FDocking\u002Flib\u002FDocking.jar`\n- `Ghidra\u002FFramework\u002FGeneric\u002Flib\u002FGeneric.jar`\n- `Ghidra\u002FFramework\u002FProject\u002Flib\u002FProject.jar`\n- `Ghidra\u002FFramework\u002FSoftwareModeling\u002Flib\u002FSoftwareModeling.jar`\n- `Ghidra\u002FFramework\u002FUtility\u002Flib\u002FUtility.jar`\n- `Ghidra\u002FFramework\u002FGui\u002Flib\u002FGui.jar`\n2. Build with Maven by running:\n\n`mvn clean package assembly:single`\n\nThe generated zip file includes the built Ghidra plugin and its resources. These files are required for Ghidra to recognize the new extension.\n\n- lib\u002FGhidraMCP.jar\n- extensions.properties\n- Module.manifest\n","ghidraMCP 是一个用于 Ghidra 的 Model Context Protocol 服务器，允许大语言模型自动进行应用程序的逆向工程。该项目通过提供一个 MCP 服务器和 Ghidra 插件，实现了对二进制文件的反编译与分析、方法和数据的自动重命名以及方法、类、导入导出列表的生成等功能。基于 Java 开发，并采用 Apache License 2.0 许可证发布。适用于需要利用 AI 技术辅助完成软件逆向工程任务的场景，如安全研究、漏洞分析等。",2,"2026-06-11 02:58:49","top_language"]