Skip to main content
Glama
Sign In

LakehouseBox

by com.lakehousebox
OverviewDiscussionsAdmin

Server Details

Read your Iceberg tables hosted in Europe: find tables, run read-only SQL, view photos.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
33.9% over 42 days
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
ChatGPT
–
Claude
LakehouseBox

TDQS

A4.2/5.0

Scored across 8 tools

Disambiguation4/5

Core verbs are distinct: list_tables (inventory), describe_table (schema+history), query (read), query_rw (write), get_object (file), read_agents_md (docs), open_public_catalog (external discovery), keep_account (account claim). Minor overlap exists between describe_table and query's DESCRIBE/SUMMARIZE, and between list_tables/open_public_catalog (both surface tables), but descriptions steer the agent clearly to the right one.

Naming Consistency4/5

All tool names use snake_case and mostly follow verb_noun (describe_table, get_object, keep_account, list_tables, open_public_catalog, read_agents_md). The exceptions are `query` and `query_rw`, which are verb-only with a read/write suffix pair; readable and predictable, but a slight deviation from the verb_noun pattern.

Tool Count5/5

Eight tools is well-scoped for a lakehouse query service: one each for listing, describing, reading, writing, file access, public-catalog discovery, docs, and account begetting. No tool feels redundant or missing from the set; each earns its place.

Completeness4/5

Read path (list_tables, describe_table, query, get_object, read_agents_md), write path (query_rw covering INSERT/UPDATE/DELETE/CREATE/ALTER/DROP), discovery (open_public_catalog), and account lifecycle (keep_account) are covered. Gaps: get_object has no upload/list counterpart for file storage, and there is no way to create a catalog (query_rw only creates tables/schemas), so file-writer and catalog-admin workflows can dead-end.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedquery1 field changed
      • changedInput schema / properties / engine / description
        Previous value: -"DuckDB engine version: '1.5' (DuckDB 1.5.6, default) or '2.0' (DuckDB 2.0 preview)"New value: +"DuckDB engine version: '2.0' (DuckDB 2.0.0, default) or '1.5' (DuckDB 1.5.6, the fallback, for claimed accounts)"
  2. 1 tool update
    • Changedquery1 field changed
      • addedInput schema / properties / engine
        Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "1.5",
+        "2.0"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "DuckDB engine version: '1.5' (DuckDB 1.5.6, default) or '2.0' (DuckDB 2.0 preview)",
+  "title": "Engine"
+}
  3. 2 tool updates
    • Addedkeep_account
    • Addedquery_rw
  4. 2 tool updates
    • Removedkeep_account
    • Removedquery_rw
  5. 2 tool updates
    • Addedkeep_account
    • Addedquery_rw
  6. 6 tool updates
    • First observeddescribe_table
    • First observedget_object
    • First observedlist_tables
    • First observedopen_public_catalog
    • First observedquery
    • First observedread_agents_md

Related MCP Connectors

Related MCP Servers

  • iceberg-mcp-server-hive

    frothkoetter
    A
    license
    A
    quality
    C
    maintenance
    Provides read-only SQL access to Apache Iceberg tables via HiveServer2, enabling querying, schema discovery, and database listing on Cloudera Data Platform.
    3
    Apache 2.0

  • DuckDB MCP Server

    poovenp
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables running read-only SQL queries and exploring DuckDB databases through MCP tools like listing tables, describing schemas, and fetching paginated data.
    -

  • lakehouse

    Arash-yazdani
    A
    license
    Not graded
    quality
    C
    maintenance
    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.
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources