Reverence
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GHIDRA_HOME | No | Set to the Ghidra install directory (the one containing support/analyzeHeadless). Required only for the ghidra_decompile tool. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| capabilitiesA | List which analysis engines are available in this install. Use this first if a tool reports a missing dependency, to see what is installed (pefile, lief, capstone, jsbeautifier) and which optional external engines are present (radare2/r2pipe, Ghidra, YARA). |
| analyzeA | One-shot triage of a binary: identification + format summary + notable strings + entry-point disassembly. Start here when handed an unknown file (.exe/.dll/.so/.dylib/.wasm/etc.); then drill in with the specific tools. |
| identify_fileA | Identify a file: format (by magic bytes), size, MD5/SHA1/SHA256 hashes, and entropy (flags likely packing/encryption). Cheap first look. |
| extract_stringsA | Extract printable strings (ASCII + UTF-16LE) with file offsets. |
| hexdump_fileB | Hex + ASCII dump of a byte window (like |
| pe_infoA | Full PE/PE32+ analysis for Windows .exe/.dll/.sys: headers, machine, subsystem, entry point, timestamp, imphash, security mitigations (ASLR/DEP/CFG/SEH), Authenticode signing state, PDB path, TLS callbacks, sections with per-section entropy, imports (by DLL), and exports. |
| elf_infoB | ELF analysis (Linux/Unix): header, arch, PIE/NX, interpreter, needed libraries, sections, imported and exported functions. |
| macho_infoA | Mach-O analysis (macOS/iOS), including fat/universal binaries: header, CPU type, PIE/NX, code-signature presence, linked libraries, segments, imports and exports. |
| disassembleB | Disassemble a window of machine code from a file offset with Capstone. |
| disassemble_entrypointA | Resolve a PE or ELF entry point to its file offset and virtual address, then disassemble from there. The fastest way to see where execution begins. |
| radare2A | Run static radare2 commands via r2pipe (requires the r2 binary). |
| ghidra_decompileA | Decompile to pseudo-C with Ghidra's headless analyzer (requires Ghidra; set GHIDRA_HOME). function: a name or address to decompile just one function; omit to decompile all (slower). Large binaries take minutes. |
| deobfuscate_javascriptA | Beautify/unminify JavaScript and flag suspicious patterns (eval,
Function(), base64, char-code building, hex/unicode blobs, network calls,
anti-debug). Provide either a file |
| wasm_infoA | Parse a WebAssembly (.wasm) module: version, section layout, and imported/exported names (functions, memories, globals, tables). |
| fetch_web_assetA | Read-only GET of a remote text/script/wasm asset so it can be analyzed (e.g. a site's bundle.js). Returns the content and content-type; it is not executed. http(s) only. |
| yara_scanA | Scan a file with YARA (requires yara-python). Provide inline
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
Most tools target clearly distinct actions (pe_info vs elf_info vs macho_info, disassemble vs disassemble_entrypoint, radare2 vs ghidra_decompile). The one real overlap is `analyze`, which bundles identification, strings, and entry-point disassembly that identify_file, extract_strings, and disassemble_entrypoint also do alone, but the descriptions explicitly frame analyze as a triage entry point, which mitigates confusion.
Nearly all tools use snake_case with a predictable verb_noun or noun_info shape (identify_file, extract_strings, pe_info, wasm_info, yara_scan). Minor deviations exist: `radare2` is a bare engine name, and `capabilities`/`analyze` are bare nouns/verbs rather than following the noun_info pattern, but the set remains readable and coherent.
16 tools is reasonable for a multi-engine reverse-engineering toolkit covering several file formats and analysis techniques. Each tool maps to a distinct capability (per-format parsers, decompilers, scanners), though the count sits at the upper edge of the comfortable 3-15 range.
Strong lifecycle coverage for static binary analysis: identification, hashing/entropy, strings, hexdump, disassembly, per-format PE/ELF/Mach-O/WASM parsers, JS deobfuscation, YARA, radare2, and Ghidra decompilation. Minor gaps include no section/segment extraction or dumping and no WASM disassembly beyond metadata, but core read-only analysis workflows are well covered.