@lakehouse/mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAKEHOUSE42_API_KEY | Yes | API key for Lakehouse42 | |
| LAKEHOUSE42_BASE_URL | No | Base URL for the Lakehouse42 API | https://api.lakehouse42.com |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_toolsA | Find available tools by name, tag, or description. Returns tool info at specified detail level. |
| searchB | Hybrid search (dense+sparse+BM25). Returns ranked chunks with cursor pagination. |
| ask_questionC | RAG-based Q&A. Returns AI answer with source count. |
| get_documentB | Get document by ID. Optionally include full content. |
| list_documentsC | List documents with filters. Cursor pagination. |
| list_collectionsB | List all collections. Cursor pagination. |
| upload_documentB | Upload text document. Auto-chunked and indexed. |
| time_travel_queryC | Query historical Iceberg data at snapshot/timestamp. |
| time_travel_diffB | Compare two snapshots. Returns added/deleted/changed counts. |
| list_snapshotsB | List Iceberg table snapshots for time-travel. |
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 10 tools
Tools are largely distinct: search_tools is meta, search and ask_question target different retrieval modes, and time_travel tools are clearly separated. Some confusion could arise between search and ask_question since both retrieve information, but descriptions clarify the intent.
Most tools follow a verb_noun pattern (get_document, list_documents, upload_document). A few deviate like 'search' (bare verb) and 'time_travel_diff' (noun-heavy), but overall naming is predictable and readable.
With 10 tools, the server is well-scoped. Each tool serves a distinct function within the two core domains (document search/RAG and time-travel on Iceberg), and none feel redundant or unnecessary.
The document side covers upload, retrieval, and search but lacks update and delete operations, which are common CRUD gaps. The time-travel features are useful but assume knowledge of tables/snapshots without a listing mechanism; overall the surface is functional but not fully comprehensive.