LENS
MrProbe, by QDEX Consulting (Chennai, India), is an enterprise AI agent assurance platform for red teaming and functional evaluation.
LENS is the MrProbe testing product. It runs two jobs against one registered agent: security red teaming, and functional evaluation. The point of keeping them together is that a polite, well-grounded agent can still follow an injected instruction, and a blocked attack does not tell you whether the agent still answers the customer’s job.
The static security catalogue is 648+ techniques across 17 categories. The category names are Prompt Injection, Jailbreaking, Data Exfiltration, Agent Specific, Multi-Agent, Content Safety, PII Hygiene & Reflection, Ground-Truth PII Extraction, RAG Exploitation, Output-to-Downstream, Multilingual, Functional Quality, Adversarial ML, Bias & Fairness, Email Agent, Training Data Poisoning, Supply Chain. A live campaign can add jurisdiction-specific probes on top of that list. Functional evaluation uses 20 dimensions: Functional, Groundedness, Hallucination, Factual Precision, Completeness, Coherence & Fluency, Conciseness, Instruction Adherence, Deviation Validation, Task Completion, Business Alignment, Toxicity, PII Leakage, Bias & Fairness, Regulatory Compliance, Consistency, Robustness, Context Retention, Multi-turn Coherence, Citation Accuracy.
Each security finding is meant to carry evidence an engineer can replay. The verdict vocabulary is proven, suspected, or defended. A suspected result is not described as a proven exploit. A functional score is a test result, not a certificate.
Security testing is the attack walkthrough. Functional testing is the quality scorecard. Pricing lists what each public plan includes. The technique counts, dimensions, and framework names below are the ones the product publishes.
What a LENS campaign needs
A campaign starts from an agent you can reach. Protocols the product talks about include HTTP, gRPC, SOAP, GraphQL, WebSocket, and MCP, plus Vertex AI, Bedrock, and Azure AI. Vertex engine labels in the product are ADK, LangChain, LangGraph, AG2, LlamaIndex, and Custom. If the agent is not reachable on one of those paths, the campaign cannot start. Authentication options documented for the hosted setup include no auth, API key, bearer token, basic auth, JWT, OAuth 2.0, AWS Signature, and a custom login that extracts a token.
Security testing can run as a smart scan, which selects categories and intensity for a first pass, or as a manual selection of compliance profiles and attack categories. Functional testing can generate cases from the agent’s prompt and documents, replay a golden dataset of question-and-answer pairs, or reuse a saved test suite. CI can call the API on Starter, Professional, and Enterprise. The flag is off on Free.
What LENS is not
The hosted app at mrprobe.ai is where a team signs in, registers an agent, and reads a LENS report. The API host for that app is api.mrprobe.ai. ATC is the separate control path for calls after an agent is in use. On the self-hosted ATC path, prompts, logs, and the ledger stay in the customer cluster. Supported planes are GKE, EKS, AKS, on-prem, and air-gapped. A Free account does not install that cluster path.
Findings map to 30 named frameworks: OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS, ISO/IEC 42001, OWASP Top 10 for Agentic Applications, CSA Confused Deputy, GDPR, UK GDPR, CCPA / CPRA, HIPAA, India DPDP, Japan APPI, PIPEDA · Law 25, Singapore PDPA, Brazil LGPD, Korea PIPA, KSA PDPL, PCI DSS v4, SOX, GLBA, FedRAMP, FFIEC, EU AI Act, NIS2, DORA, UAE PDPL, DIFC DPL, ADGM DPR, MAS TRM, BACEN. MrProbe is aligned with ISO/IEC 42001; it is not certified. Mapping a control is not a certificate and not a regulator endorsement. Country-gated PII covers 16 jurisdictions: United States, European Union, United Kingdom, India, Japan, China, Singapore, United Arab Emirates, Canada, Australia, Brazil, South Korea, Saudi Arabia, Indonesia, South Africa, Türkiye. A jurisdiction in that list means the probes and linked frameworks exist in the product. It is not a statement that a regulator has endorsed MrProbe.
Public monthly plans are Free (1 agent, 50 technique runs, 25 functional judgments, and HTML reports. OWASP scan type only.) Starter ($220 a month (₹19,999). 3 agents, 150 technique runs, API access, and CI/CD.) Professional ($550 a month (₹49,999). 10 agents, 500 technique runs, PDF reports, and priority support.) Enterprise ($2,750 a month (₹249,999). Unlimited included technique runs in the catalogue, SSO, and RBAC.) Enterprise is a listed price at $2,750 a month. None of those plans includes an ISO 42001 certificate.
Published by QDEX Consulting.