Function And Class Signature Extraction With Metadata

via “function and symbol metadata retrieval with type information”

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

Unique: Queries IDA's native type information system and symbol table to provide structured function signatures and metadata, avoiding regex-based parsing and leveraging IDA's type inference engine for accuracy

vs others: IDA's type information system is more comprehensive than Ghidra for binaries with DWARF or PDB debug symbols; direct API access avoids parsing errors from manual symbol extraction

via “multi-language class structure extraction with metadata preservation”

Plugin for JADX to integrate MCP server

Unique: Uses JADX's JavaClass entity model to extract metadata directly from the decompiled AST, preserving type information and structural relationships. This is more accurate than parsing source code strings because it uses semantic information.

vs others: More accurate than regex-based parsing because it uses JADX's AST; more complete than javadoc extraction because it includes all metadata including private members and annotations.

via “function signature and parameter extraction with type information”

npx agentseed initAGENTS.md (https://agents.md) is a standard file used by AI coding agents to understand a repo (stack, commands, conventions).Agentseed generates it directly from the codebase using static analysis. Optional LLM augmentation is supported by bringing your own API key.Extra

Unique: Extracts and preserves type information from source code to generate agent-consumable function signatures that include parameter types and constraints, not just names

vs others: More precise than simple function name extraction because it includes type information; more reliable than runtime introspection because it works statically without executing code

Condense source code for LLM analysis by extracting essential highlights, utilizing a simplified version of Paul Gauthier's repomap technique from Aider Chat.

Unique: Extracts function and class signatures with type annotations and docstring summaries, creating a lightweight API reference that LLMs can use for code generation without processing full implementations

vs others: More efficient than sending full code to LLMs because it focuses on callable interfaces and public APIs, while remaining simpler than full IDE-style symbol resolution

via “elisp-function-signature-extraction-and-documentation”

** - elisp (Emacs Lisp) development support tools, running in Emacs.

Unique: Combines runtime introspection (via Emacs' function-documentation and help-function-arglist) with static AST parsing to handle both loaded and unloaded code, providing complete signature coverage

vs others: More complete than static-only analysis because it accesses live function objects with their actual arity and docstrings, and more reliable than pure runtime introspection because it falls back to parsing for unloaded code

via “function and class signature extraction”

Compact, language-agnostic codebase mapper for LLM token efficiency.

Unique: Combines regex-based pattern matching with lightweight context-aware parsing to extract signatures while preserving parameter names, types, and decorators in a structured format that LLMs can directly use for code generation and analysis without additional parsing

vs others: More efficient than running full language-specific compilers or type checkers because it extracts only the interface layer needed for LLM reasoning, reducing overhead while maintaining sufficient detail for code generation and documentation tasks