Skip to main content
Glama

analyze

Disassemble and inspect binary files: extract strings, analyze headers, search patterns, and compute entropy for reverse engineering tasks.

Instructions

Static binary analysis tool for reverse engineering and debugging. Operations: disassemble (x86/x64/ARM/ARM64 disassembly, stop_at_ret for function-scoped), pe_info (PE header/sections/imports/exports), elf_info (ELF header/sections/symbols), macho_info (Mach-O header/segments/symbols), strings (extract printable strings from binary), hexdump (hex+ASCII view), pattern_search (hex byte pattern with ?? wildcards, shows section names for PE), entropy (Shannon entropy per section), bin_diff (two-file byte comparison), resource_info (PE resources and version info), imphash (PE import hash for malware classification), rich_header (PE build tool fingerprint), overlay_detect (detect appended data after last section), dwarf_info (debug symbol info), xref (find all code references to a target address in PE/ELF/Mach-O; supports x86/x64/ARM64/ARM32), function_at (find function boundaries via PE .pdata or heuristic prologue/epilogue scan), call_graph (static call graph from a root function; PE/ELF/Mach-O, x86/x64/ARM64/ARM32), follow_ptr (follow pointer chain in PE with symbol annotation, circular reference detection), rtti_dump (parse MSVC RTTI from vtable: demangled class name + base classes, pSelf validation), struct_layout (dump memory region as structured layout with symbol/section annotation), vtable_scan (scan PE .rdata for all vtables with RTTI -- auto-discovers C++ classes). Pure Go implementation -- no external tools needed. Supports x86, x64, ARM, ARM64. For PE files: use 'va' parameter instead of 'offset' for auto VA display, symbol annotation, and function boundary detection. PE strings/pattern_search automatically show VA alongside file offsets. For runtime debugging, use the debug tool instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation: disassemble, pe_info, elf_info, macho_info, strings, hexdump, pattern_search, entropy, bin_diff, resource_info, imphash, rich_header, overlay_detect, dwarf_info, xref, function_at, call_graph, follow_ptr, rtti_dump, struct_layout, vtable_scan,required
file_pathNoAbsolute path to the binary file,required
pathNoAlias for file_path
offsetNoByte offset to start from. Default: 0
vaNoVirtual address for PE files (hex, e.g. '0x140001000'). Auto-converts to file offset. For disassemble, function_at, follow_ptr, rtti_dump, struct_layout. Preferred over offset+base_addr for PE analysis.
countNoNumber of instructions (disassemble) or depth (follow_ptr). Default: 50/4, Max: 600/10.
stop_at_retNoStop disassembly at function return (RET/RETF). Confirms boundary via INT3/NOP padding or new prologue. For disassemble only: true or false. Default: false
modeNoCPU mode: 32 or 64. Default: 64
base_addrNoBase address for display (hex string, e.g. '0x140001000'). Default: 0x0. This maps to file offset 0, so displayed address = base_addr + offset + instruction_position. For PE files, prefer 'va' parameter instead -- it auto-calculates the correct base_addr.
archNoCPU architecture: x86 (default) or arm. For disassemble
min_lengthNoMinimum string length for strings operation. Default: 4
max_resultsNoMaximum number of results for strings. Default: 500, Max: 2000
encodingNoString encoding to search for: ascii (default) or utf8
lengthNoNumber of bytes for hexdump. Default: 256, Max: 4096
sectionNoFilter by section name (e.g. '.text', '.rdata'). Empty = show all
rvaNoRVA to convert to file offset (hex string, e.g. '0x36A20'). For pe_info only
patternNoHex byte pattern with ?? wildcards (e.g. '4D 5A ?? ?? 50 45'). For pattern_search
target_vaNoTarget virtual address to find references to (hex). For xref operation.
file_path_bNoAbsolute path to the second file for bin_diff comparison
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description details many behavioral aspects for each operation, such as stop_at_ret behavior, pattern_search showing section names, and automatic VA display for PE. It is transparent about the tool being a pure Go implementation without external dependencies. However, it does not discuss return formats or potential side effects, but given its read-only nature, this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy (over 300 words) due to the large number of operations, but it front-loads the main purpose and structures operations in a list-like manner. While not extremely concise, it is functional and organized, earning a mid-range score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (19 parameters, many operations) and the lack of an output schema, the description provides fairly complete context by explaining operation-specific details and parameter usage. It could be more explicit about return values for each operation, but it offers sufficient guidance for an AI agent to select and use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, and the tool description adds significant context beyond the schema, e.g., explaining when to use 'va' vs 'offset', and providing default/max values for parameters like count, length, and max_results. This enhances parameter understanding beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a static binary analysis tool for reverse engineering and debugging, listing many specific operations. It distinguishes itself from runtime debugging by directing users to use the debug tool instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool (static analysis) and when to use the sibling debug tool (runtime debugging). It also provides guidance for PE files, recommending the 'va' parameter over 'offset' and 'base_addr'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knewstimek/agent-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server