Iceberg MCP is a server implementation that provides AI assistants with direct access to Apache Iceberg tables stored in AWS. The server exposes tools for exploring Iceberg catalogs, retrieving table schemas, examining table properties, and analyzing partition information. Built on top of PyIceberg with AWS Glue integration, it authenticates using AWS credentials from environment variables or profiles. This implementation is particularly useful for data engineers and analysts who need to explore and understand Iceberg table metadata without writing complex queries or code.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.