"Travel" matching MCP servers:

Enables searching for relevant tables and retrieving data from Microsoft Sentinel's data lake using natural language, supporting security hunting scenarios like password-spray detection and impossible travel checks.

Provides AI agents an auditable memory layer with provable deletion via signed certificates, a tamper-evident hash-chained audit trail, and bi-temporal time-travel recall over SQLite or Postgres.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.

Enables governed, AI-safe access to traveler data through three typed tools, enforcing consent, PII removal, provenance, and audit at the MCP boundary.

Exposes exactly three MCP tools that check health, return deterministic mock output, and prepare bounded synthetic travel checklists as time-limited SQLite proposals. Each proposal is reviewed by an independently authenticated human operator who must explicitly approve saving it or reject it, with fingerprint checking, session CSRF protection, and rejection of replayed, tampered, or unauthorized decisions.

Enables agents to securely stage, validate, and submit binary data for on-premises storage, then list, inspect, process via registered server-side processors, and token-guarded delete those assets using opaque identifiers. Upload bytes travel over a separate data plane rather than through MCP JSON, with staging, validation, and prepare/apply/verify flows enforced throughout.