> ## Documentation Index
> Fetch the complete documentation index at: https://docs.peaka.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools reference

> Every tool the Peaka MCP server exposes, grouped by area.

The Peaka MCP server exposes the tools below to your AI assistant. Most are scoped to a single Peaka project — the assistant passes a `projectId` argument with each call. If the project hasn't been chosen yet, the assistant typically calls [`peaka_list_projects`](#peaka_list_projects) first.

The server also exposes two **resources** the assistant can pull in for context:

* **`peaka_sql_query_rule_set`** — guidelines for writing valid Peaka SQL.
* **`peaka_artifact_template`** — style guide and HTML template for generating visual reports, dashboards, and artifacts from query results.

## Projects

### `peaka_list_projects`

List all projects accessible with the current credentials. Under OAuth (remote) or a Partner API key, enumerates projects across all organizations and workspaces. Under a Project API key, returns the single project bound to the key.

## Metadata

### `peaka_get_project_metadata`

Get metadata for all catalogs, schemas, and tables in the project in a single call. Optionally filter by `catalogId` and/or `schemaName`.

### `peaka_list_catalogs`

List all available catalogs in the project. Returns catalog names, types, and connection info.

### `peaka_list_schemas`

List all available schemas for a given catalog.

### `peaka_list_tables`

List all available tables for a given catalog and schema.

### `peaka_list_columns`

List all columns for a given table. Returns column names, data types, and constraints.

### `peaka_get_relations`

Get table relationships (foreign keys) for a catalog. Useful for constructing accurate JOINs.

### `peaka_get_table_statistics`

Get column-level statistics for a table, including distinct-value fractions per column.

### `peaka_refresh_project_metadata`

Refresh project metadata for a specific catalog. Long-running; triggers the refresh and polls for completion.

### `peaka_get_metadata_refresh_status`

Check the current status of a metadata refresh job for a specific catalog.

## Query execution

### `peaka_execute_sql_query`

Run an arbitrary SQL query on Peaka.

### `peaka_query_golden_sqls`

Query the project's golden-SQL store for question/SQL pairs. If an existing golden query matches the user's question, the assistant can reuse it directly instead of generating new SQL.

## Cache

### `peaka_create_cache`

Create a cache for a single table. Caching improves query performance by storing the data locally.

### `peaka_create_cache_batch`

Create caches for multiple tables in a single call. Preferred over repeated `peaka_create_cache` calls.

### `peaka_get_cache_statuses`

Get all cache statuses for tables in the project, including current caching state, execution history, and progress.

### `peaka_refresh_cache_full`

Trigger a full refresh on an existing cache.

### `peaka_refresh_cache_incremental`

Trigger an incremental update on an existing cache, fetching only new or changed rows.

### `peaka_update_cache`

Update cache settings (schedules) on an existing cache. Replaces both schedules entirely on each call.

### `peaka_delete_cache`

Delete an existing cache. The underlying table is not affected.

## Saved queries

### `peaka_list_queries`

List all saved queries in the project. Returns query names, SQL content, and whether they are plain or materialized.

### `peaka_execute_query`

Execute a saved query by its ID.

### `peaka_create_query`

Create a named, saved query in the project's semantic layer. Returns the created query, including its ID.

### `peaka_update_query`

Update an existing saved query's display name and/or SQL body.

### `peaka_delete_query`

Delete a saved query from the project.

## Connections

### `peaka_list_connections`

List all data source connections in the project — each connection's id, name, type, and (for OAuth-based connections) callback URL.

### `peaka_get_connection_detail`

Get connection-specific configuration detail for a data source connection.

## Semantic catalogs

### `peaka_create_semantic_catalog`

Create a semantic catalog. A semantic catalog groups semantic tables (saved queries surfaced as queryable tables) under a single namespace.

### `peaka_create_semantic_table`

Create a semantic table inside a semantic catalog, backed by a saved query. Requires `catalogId`, `schemaName`, `tableName`, and `queryId`.

### `peaka_delete_semantic_table`

Delete a semantic table from a semantic catalog. The underlying saved query is not affected.

***

The canonical, version-pinned tool list lives in the [`peakacom/peaka-mcp-server` README](https://github.com/peakacom/peaka-mcp-server#readme).