LEVIATHAN

Your agents trust their tools. LEVIATHAN tests whether they should. MCP server security assessment — Tool 27.
8
Subsystems
44
UNLEASHED Findings
8
Attack Vectors
409
Tests Passing
pip install red-specter-leviathan
Your agents trust MCP servers / But you've never tested them / Tool definitions can be poisoned / Schema integrity is assumed not verified / Trust redirection goes undetected / Lateral movement through delegation chains / A compromised server owns every agent that connects / You trusted the protocol Your agents trust MCP servers / But you've never tested them / Tool definitions can be poisoned / Schema integrity is assumed not verified / Trust redirection goes undetected / Lateral movement through delegation chains / A compromised server owns every agent that connects / You trusted the protocol

MCP Is an Unaudited Trust Layer

The Model Context Protocol is the bus your agents use to discover and call tools. It's also the most dangerous unevaluated trust surface in modern AI deployment. Your agents trust what MCP servers tell them — tool definitions, capability declarations, schemas. None of it is verified. LEVIATHAN tests every layer of that trust relationship.

Tool Definitions Are Trusted Blindly

Agents consume MCP tool definitions at face value. A server that returns modified parameter types, hidden fields, or altered descriptions will be executed without question. LEVIATHAN's INJECT subsystem tests every permutation of schema manipulation.

Server Identity Is Never Validated

DNS remapping, TLS certificate swaps, registry updates — an agent connecting to what it believes is its trusted MCP server has no mechanism to detect identity substitution. LEVIATHAN's TRIDENT subsystem assesses trust validation mechanisms directly.

Discovery Exposes the Full Attack Surface

MCP servers registered in your environment declare capabilities, authentication requirements, and transport details. LEVIATHAN's ABYSS subsystem enumerates the complete MCP landscape before any testing begins — you can't secure what you haven't mapped.

Lateral Movement Through Trust Chains

MCP environments contain delegation chains — agents that connect through servers that connect to other servers. LEVIATHAN's UNDERTOW subsystem maps the full BFS graph of trust relationships and calculates blast radius for each critical server compromise.

Compromise Impact Is Unquantified

When an MCP server is compromised, what does an attacker actually gain? Data access, command execution, privilege escalation paths, denial of service vectors. LEVIATHAN's HARVEST subsystem assesses impact systematically across every connected agent.

No Tamper-Evident Evidence Chain

Security assessments of MCP infrastructure leave no audit trail by default. LEVIATHAN's RAIN subsystem captures and Ed25519-signs every assessment action — every test, every finding, every interaction — producing a tamper-proof evidence chain for audit and compliance.

Own the Trust Layer

MCP is the protocol agents trust for tool discovery. LEVIATHAN assesses every layer of that trust — from server discovery and fingerprinting to schema integrity, trust redirection, and lateral movement through delegation chains. If it touches MCP, LEVIATHAN tests it.

# Subsystem Function What It Does
01 ABYSS Discovery & Enumeration Discovers MCP servers via port scanning, registry enumeration, and DNS resolution. Maps tool definitions, capabilities, and trust relationships across the environment before any active assessment begins.
02 MIRAGE Server Simulation Creates controlled MCP server replicas for security testing. Clones tool definitions, capabilities, and TLS certificates. Full JSON-RPC response handling — tests agent behaviour when served a simulacrum.
03 INJECT Schema Integrity Testing Generates test cases that modify tool definitions — hidden parameters, type changes, description alterations, annotation removal. Tests whether agents detect modifications to the schema they rely on.
04 LURE Fingerprint & Assessment Fingerprints MCP server implementations and assesses security posture. Checks authentication, TLS, SSRF indicators, schema enforcement, token handling, and transport security across all discovered servers.
05 TRIDENT Trust Redirection Assesses whether agents detect server identity changes — DNS remapping, TLS certificate swaps, registry updates, and capability drift. Tests the trust validation mechanisms agents employ on reconnection.
06 HARVEST Impact Assessment Analyses what a compromised MCP server enables — data access, command execution, privilege escalation, denial of service, and data manipulation across every agent connected through the compromised server.
07 UNDERTOW Lateral Trust Chains Maps lateral movement paths through MCP trust relationships. BFS graph analysis, delegation chain discovery, blast radius calculation, and critical server identification across the full trust topology.
08 RAIN Forensic Evidence Captures and signs every assessment action with Ed25519 cryptographic integrity. Tamper-proof evidence trail for audit, compliance, legal hold, and downstream SIEM ingestion.

44 UNLEASHED Findings. 8 Attack Vectors.

Full LEVIATHAN assessment — MCP server at localhost:8080:

$ leviathan scan --target mcp://localhost:8080 --full-assessment
[ABYSS] Discovered 3 MCP servers — 1 primary, 2 delegated
  Tools mapped: 14 definitions across 3 servers
[LURE] Fingerprinting mcp://localhost:8080...
  CRITICAL: No authentication on primary server
  WARNING: TLS not enforced on tool call endpoints
[INJECT] Schema integrity tests — 14 tools × 8 mutation classes...
  FINDING: 7 tools accept hidden parameters without rejection
  FINDING: 3 tools vulnerable to description injection
[TRIDENT] Trust redirection assessment...
  FINDING: Agent reconnects to swapped TLS cert without alert
[UNDERTOW] Mapping trust chain graph...
  Blast radius from primary server: ALL 3 servers, 7 agents

COMPLETE | Risk: CRITICAL | 44 findings | Report signed ✓

Full Protocol Coverage

stdio and SSE transport, JSON-RPC over HTTP, all MCP capability classes — tools, resources, prompts, sampling.

Graph-Based Trust Mapping

BFS traversal across the full MCP delegation topology. Every chain, every blast radius, every critical path visualised.

Ed25519 Evidence Chain

Every finding cryptographically signed. RFC 3161 timestamped. SHA-256 integrity chain across every assessment action.

NIGHTFALL Integration

Feeds directly into ROGUE for malicious MCP server simulation and into VECTOR for full MCP exploitation campaigns.

8
Subsystems
44
UNLEASHED Findings
8
Attack Vectors
409
Tests Passing
0
Failures

UNLEASHED Gate

Cryptographic override. Private key controlled. One operator. Founder's machine only. ANTIDOTE is not available for LEVIATHAN — MCP compromise is architectural, not a configuration setting. You either have trust validation or you don't.

Standard Mode

Discovery and fingerprinting only. Maps MCP servers, enumerates tools, identifies trust relationships, assesses authentication posture. No active interference. No server modification. No schema injection.

Dry Run Mode

Simulates all assessment techniques. Schema tests, redirection tests, impact analysis — shows what would be found and how, down to specific finding counts. Ed25519 required. No active execution against target servers.

Live Mode

Full assessment with active techniques. 44 UNLEASHED findings across 8 attack vectors. Server impersonation, registry manipulation, tool injection testing, delegation chain traversal, blast radius validation.

THIS TOOL IS FOR AUTHORISED SECURITY TESTING ONLY. EVERY EXECUTION IS SIGNED AND LOGGED.

Ed25519 Cryptographic Override
LEVIATHAN UNLEASHED

Cryptographic override. Private key controlled. One operator. Founder's machine only.

Every Finding Mapped

8 Vectors

Attack Surface Coverage

  • Server discovery & enumeration
  • Schema injection & manipulation
  • Trust redirection & impersonation
  • Delegation chain traversal
  • Authentication bypass
  • Transport security failures
  • Capability drift detection
  • Impact assessment & blast radius
OWASP LLM

Standards Mapping

  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency
  • LLM07 System Prompt Leakage
  • MITRE ATLAS AML.T0051
  • MITRE ATLAS AML.T0043
  • MCP Security specification gaps
Cryptographic

Evidence Integrity

  • Ed25519 digital signatures
  • SHA-256 evidence chains
  • RFC 3161 timestamps
  • Tamper-evident assessment log
  • JSON structured findings export
  • SIEM-native integration

Security Distros & Package Managers

Kali Linux
.deb package
Parrot OS
.deb package
BlackArch
PKGBUILD
REMnux
.deb package
PyPI
pip install
macOS
pip install
Windows
pip install
Docker
docker pull

Authorised Use Only

Red Specter LEVIATHAN is intended for authorised security testing of MCP server infrastructure only. Active assessment features require UNLEASHED activation and must only be used against MCP servers you own or have explicit written permission to assess. Unauthorised use may violate the Computer Misuse Act 1990 (UK), Computer Fraud and Abuse Act (US), and equivalent legislation in other jurisdictions. Apache License 2.0.