Should AI Agents Use Screens, APIs or MCP?
Compare screen automation, APIs and MCP for AI agent billing and claims workflows, with PII input controls, tokenization and human approvals.
Research topic
MCP
Research on MCP for AI agent workflows, with tokenization, access controls and evidence for teams handling sensitive business data.
What Are the Risks of Connecting SAP Joule Agents to Non-SAP Systems?
SAP's authorization model stops at the boundary: Agent Hub gates inbound requests, but outbound A2A or MCP calls are where injection enters. Map each one.
RedactSure vs Arcade: 2026 Comparison & Alternative
Arcade authorizes each tool call through the user's OAuth grant and vaults the token. RedactSure replaces values on the page before a model reads it.
How Do I Keep API Keys Out of Claude Code's Context Window?
Deny the files and variables that hold keys in sandbox.credentials and mask the ones the agent must use. The Read tool, MCP servers.
How Many Prompt Injection Vulnerabilities Have Been Published?
At least 150 published vulnerability records describe prompt injection against AI systems, and 92 of them appeared in the past four quarters against 29 in the four before. Only 21 records carry the weakness category created for prompt injection, so counts that rely on that tag miss most of the problem.