Joern-MCP is a server implementation that provides AI assistants with access to Joern's code analysis capabilities through a Python interface. This server enables querying and analyzing Code Property Graphs (CPGs) by exposing tools for loading CPGs, retrieving method and class code, examining call relationships, and executing custom queries against the Joern backend. Built on the FastMCP framework, it handles communication with a remote Joern instance via HTTP requests, making it particularly valuable for security researchers and developers who need to perform static code analysis, identify vulnerabilities, or understand code structure and dependencies through AI assistants.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Highlight AIRetrieve methods by their exact name using indexed lookup. This tool performs an efficient search based on method names.
Obtain the entire call chain for a method, including its full name and code, while skipping JDK/framework callees. This operation is performed in one HTTP round-trip.
Retrieve the names of the entire call chain for a method without including the code, optimizing for performance.
Access the server-side functionality to get the call chain for a method, improving efficiency by reducing the number of HTTP round-trips required.
