duckdb-iceberg-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JWKS_URL | No | JWKS endpoint for JWT validation (required in full mode) | |
| MAX_ROWS | No | Maximum rows returned per query | 250 |
| MCP_HOST | No | Bind address for HTTP/SSE | 127.0.0.1 |
| MCP_MODE | No | Easy or full authentication mode | easy |
| MCP_PORT | No | Port for HTTP/SSE | 8000 |
| MAX_CHARS | No | Maximum characters in a query response | 40000 |
| AWS_REGION | No | AWS region | us-east-1 |
| WRITE_MODE | No | Write mode: disabled or enabled (always disabled in easy mode) | disabled |
| AWS_PROFILE | No | Named AWS profile | |
| MCP_API_KEY | No | Static bearer token for easy mode HTTP. Empty = no auth | |
| CATALOG_TYPE | No | Catalog type (only glue supported) | glue |
| JWT_AUDIENCE | No | Expected aud claim in JWTs | duckdb-iceberg-mcp |
| MCP_TRANSPORT | No | Transport protocol: stdio, http (Streamable HTTP), or sse | stdio |
| AWS_ACCESS_KEY_ID | No | AWS access key | |
| MCP_ALLOWED_HOSTS | No | Comma-separated allowed Host headers (e.g. host.docker.internal:*,localhost:*). Empty = SDK default | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_lakehouseA | Execute a SQL query. Use read_parquet() or iceberg_scan() for S3 paths, or use the glue_table tool first to register a Glue table by name. |
| list_tablesA | List available tables. Optionally filter by database name. |
| describe_tableB | Describe a table's schema. Use 'database.table' format for Glue. |
| glue_tableA | Register a Glue Iceberg table as a queryable DuckDB view. Resolves the actual data files from the Iceberg manifest (handles tables where data files live outside the Glue-registered table root). Usage: glue_table('database.table_name') After calling this, query with: SELECT * FROM database__table_name |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: describe_table shows schema, glue_table registers a view, list_tables enumerates tables, and query_lakehouse executes SQL. No overlap in functionality.
Most names follow verb_noun (describe_table, list_tables, query_lakehouse), but 'glue_table' is a noun_noun that breaks the pattern, introducing inconsistency.
Four tools cover the essential operations for an Iceberg query server: listing, describing, registering, and querying tables. This is minimal but well-scoped for the stated domain.
The server supports read and schema-discovery operations but lacks write or lifecycle management tools (e.g., create, delete, update). This is acceptable for a query-focused tool but leaves gaps for full table management.