adversarial-rea
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADV_REA_ALLOWED_ROOTS | No | For an MCP client that should see only one directory, set ADV_REA_ALLOWED_ROOTS=/absolute/path/to/targets in its server environment. Without it, any readable local regular file can be submitted for inspection. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_binaryC | Extract binary metadata, symbols, strings, and security info from a target |
| get_symbolsC | Extract symbols (functions, imports, exports) from binary |
| get_stringsC | Extract and classify strings from binary (credentials, URLs, paths, etc.) |
| check_securityA | Check binary security mitigations (PIE, NX, canary, RELRO, FORTIFY) |
| disassembleC | Disassemble binary or specific function |
| get_sectionsB | List binary sections with sizes and attributes |
| get_headersC | Extract binary headers (architecture, entry point, etc.) |
| find_dangerous_patternsC | List unverified imports, strings, and mitigation signals for manual review |
| trace_callsC | Observed direct native call instructions; flow and exploitability remain unknown |
| inspect_carrierC | Bounded file/container metadata only; does not claim vulnerability analysis |
| inspect_flow_fixtureC | Reproduce in-memory flow in a bounded .flow.json fixture only; not native evidence |
| find_gadget_candidatesC | Byte-verified ELF64 x86_64 gadget candidates, not runtime exploit addresses |
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 12 tools
Most specialized tools target distinct artifacts (symbols, strings, sections, headers, security flags, disassembly), but analyze_binary acts as an umbrella that overlaps several of them. find_dangerous_patterns also overlaps with check_security, get_symbols, and get_strings, so an agent may be unsure whether to call the aggregate or specialized tools.
Most names follow a predictable verb_object pattern: get_symbols, check_security, find_dangerous_patterns, inspect_carrier, and trace_calls. The main deviation is disassemble, which is a bare verb, and some tool names are more verbose than others, but the set remains readable and consistent overall.
Twelve tools is well within the appropriate range for a binary analysis server. Each tool appears to cover a specific static-analysis concern, from headers and sections to symbols, strings, security mitigations, disassembly, call tracing, and gadget candidates.
The surface covers the core static binary-analysis lifecycle: metadata, headers, sections, symbols, strings, security checks, disassembly, dangerous pattern inspection, call tracing, and gadget discovery. Minor gaps remain around operations like byte-level inspection, cross-references, binary diffing, or patching, but the main analysis workflows are represented.