List known Ghidra instances from UDS discovery and the active TCP fallback.

Returns JSON with each instance's project name, PID, open programs, and socket path or TCP URL. Also shows which instance is currently connected.

Switch the MCP bridge to a different Ghidra instance by project name.

IMPORTANT: Before calling this function only the static bridge tools are exposed (list_instances, connect_instance, tool-group management, debugger proxy). After a successful connect the bridge fetches the instance's /mcp/schema and registers Ghidra analysis tools dynamically. By default all tool groups are loaded on connect. When started with --lazy, only the default groups are loaded initially and clients may need to call load_tool_group() for additional categories. Clients that cache the initial tools/list and don't honor tools/list_changed must re-list tools after this call.

Use list_instances() first to see available instances.

Args: project: Project name (or substring) to connect to

List all available tool groups with their tool counts and loaded status.

Returns each category with: tool count, loaded status, and tool names. Use load_tool_group(group) to load a group's tools.

Load all tools in a category. Accepts a category name or "all" to load everything.

Use list_tool_groups() to see available categories.

Args: group: Category name (e.g. "function", "datatype") or "all"

Unload all tools in a category. Default groups are protected from unloading.

Args: group: Category name to unload

Check if specific tools are callable right now. Returns status for each tool: "callable", "not_loaded" (exists but group not loaded), or "not_found" (doesn't exist).

Args: tools: Comma-separated tool names, e.g. "rename_symbol,batch_set_comments,analyze_function_completeness"

Search the full Ghidra tool catalog by keyword — including tools whose group is not currently loaded. Use this to discover the right tool without paying the context cost of loading all groups (run the bridge with --lazy and search on demand). Matches against tool name, description, and category.

Each result reports whether the tool is callable right now; if not, it includes the exact load_tool_group(...) call needed to make it callable.

Args: query: Space-separated keywords, e.g. "rename function" or "xref struct". limit: Maximum number of results to return (default 15).

Import a binary file from disk into the current Ghidra project.

Imports the file, opens it in the CodeBrowser, and optionally starts auto-analysis. When analysis is enabled, sends a log notification when analysis completes.

For raw firmware binaries, specify language (e.g. "ARM:LE:32:Cortex") and optionally compiler_spec (e.g. "default"). Without language, Ghidra auto-detects the format (works for ELF, PE, Mach-O, etc.).

Args: file_path: Absolute path to the binary file on disk project_folder: Destination folder in the Ghidra project (default: "/") language: Language ID for raw binaries (e.g. "ARM:LE:32:Cortex", "x86:LE:64:default") compiler_spec: Compiler spec ID (e.g. "default", "gcc"). Uses language default if omitted. auto_analyze: Start auto-analysis after import (default: true)