//Topics
Articles tagged #mcp
#token-economy 8#finops 4#observability 4#prompt-injection 4#tokenization 3#agents 2#ai-cost 2#anthropic 2#cache 2#cfo 2#cost 2#mcp 2#multi-agent 2#opentelemetry 2#orchestration 2#prompt-caching 2#tra 2#adoption 1#agent 1#agent-debt 1#agentes 1#agentic 1#agentic-security 1#alfa 1#amplificacao-agentica 1#autonomy 1#avaliacao 1#calibracao 1#claude-opus 1#community 1#crise-dos-tokens 1#culture 1#custo-de-agentes 1#e-cache 1#echoleak 1#economics 1#finops-de-ia 1#gmail 1#interpretability 1#j-lens 1#lethal-trifecta 1#llm 1#llms-txt 1#mindset 1#model-routing 1#model-upgrade 1#n8n 1#observabilidade 1#organization 1#owasp 1#pricing 1#product 1#prompt 1#prompt-engineering 1#qwen 1#reasoning 1#state-machine 1#subagentes 1#supply-chain 1#token 1#token-crunch 1#token-resilience-architecture 1#tokenizer 1#tokens 1#tool-use 1
- AI Ops Sec
OWASP Agentic Top 10 mapped to a real stack: what each ASI demands from those who run agents
I took the ten OWASP risks for agentic applications and mapped each one to a concrete piece of a production stack. The table, the incidents, and the config that is missing.
- AI Ops Sec
The danger is not the connector. It is what gets into the model, and what it can do next
'Is this MCP secure?' has an answer. The missing question is another: what did I just authorise into a model that can also act? Two attack chains, what is at stake, and observability over MCPs.