Viridis MCP

Aristotle-verified attribution-enforcement services for AI agents: adversarial injection detection, VulnCanon source scanning, and Maxwell adaptive proof-of-work defense.

Skills

• Adversarial Injection Detection
  Classify untrusted text as clean / suspicious / attack. Returns verdict, probability, bits-at-risk per Adversarial Landauer Inequality, matched VulnCanon entries, and a recommended action (allow / sanitize / reject / escalate). Backed by T-IB-02 + T-IB-06.
  securityprompt-injectionai-agentattributionaristotle-verified
• VulnCanon Source Scan
  Match source code against the public VulnCanon catalog of AI-agent vulnerability classes (SSRF in fetch tools, prompt injection patterns, tool-poisoning, cross-agent state pollution, etc.). Returns matched entry IDs, severity, occurrence line, and mitigation references. Backed by T-IB-05 Canon Compression.
  securitycode-reviewvulncanonstatic-analysisaristotle-verified
• Maxwell Adaptive Proof-of-Work
  Issue an Argon2id proof-of-work challenge that an upstream attacker must solve. Defender pays log2(1/alpha) times the attacker's energy per bit, making sustained adversarial input energetically irrational. Backed by T-IB-09 Adversarial Dissipation. Tier-gated (Growth+) on the hosted endpoint; Apache-2.0 reference implementation available.
  securityrate-limitingproof-of-workasymmetric-defensearistotle-verified

How to call

https://mcp.viridis-security.com

Listed in

Directories this entry was found in.