Skip to main content
Glama
Sign In
re-audit-mcp

re-audit-mcp

by TLSRUF
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
full_auditA

Run the complete static audit on a file (auto-detects ELF/PE/Mach-O/APK).

Combines string extraction, hardcoded-secret scanning, binary exploit mitigation checks, and (for APKs) manifest/permission analysis into one report with a summary_findings list. Only use on files the caller is authorized to test.

detect_file_typeA

Identify whether a file is an ELF, PE, Mach-O binary, APK, JAR, or unknown, by magic bytes.

scan_stringsC

Extract printable strings from a file and classify URLs, IPs, paths, and risky API names.

scan_secretsA

Scan a file's extracted strings for hardcoded credential/token/key patterns and high-entropy blobs.

Matches are redacted in the output. These are heuristic candidates -- verify manually before treating any match as a confirmed live secret.

scan_binary_mitigationsB

Check an ELF/PE/Mach-O binary's exploit mitigations (NX, PIE/ASLR, RELRO, stack canary, CFG) and list imported functions historically associated with memory-corruption bugs.

scan_apkB

Static security audit of an Android APK: debuggable/backup/cleartext flags, dangerous permissions, and exported components (activities/services/receivers/providers) lacking guards.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 6 tools

Disambiguation4/5

Each scan_* tool targets a distinct analysis dimension (strings, secrets, mitigations, APK manifest), so boundaries are mostly clear. The only overlap is intentional: full_audit orchestrates the same checks, and an agent could be unsure whether to call it or the granular tools for a single check.

Naming Consistency4/5

Names are snake_case with predictable verb_noun structure (detect_file_type, scan_strings, scan_secrets, scan_binary_mitigations, scan_apk). full_audit is the one deviation, lacking a verb prefix, but it stays within the same convention and remains readable.

Tool Count5/5

Six tools is well-scoped for a static binary/APK audit server: one aggregator plus five focused analyzers. No tool feels redundant or missing at this granularity.

Completeness4/5

The surface covers file typing, strings, secrets, native mitigations, and APK manifest issues for ELF/PE/Mach-O/APK. Minor gaps: detect_file_type recognizes JAR but no JAR-specific scan exists, and APK signing/certificate verification is absent, though agents can work around these.

Resources