MCP tools
Use this reference to look up tool inputs and outputs. For connection, OAuth authorization, environment selection, and access scopes, see MCP setup.
This page lists public tools and their minimum scopes. Discovery in your client also depends on permissions, enabled features, and connected integrations. Behavior hints describe tool properties; the granted scope and resource permissions determine access.
ask
Minimum scope
ask_question
Minimum scope
comment_finding
Minimum scope
create_dashboard
Minimum scope
create_data_app
@altertable/data-app, and @altertable/data-app-react imports are allowed. The file is bundled before save, and declares the SQL queries the app runs by ID. The source defines its title and description. Returns the slug and URL.Minimum scope
create_insight
kind field and expects the matching definition: funnel + funnel_definition, journeys + journeys_definition, segmentation + segmentation_definition, retention + retention_definition, semantic + semantic_definition, or sql + sql_definition + sql_parameters. Returns the insight ID and slug.Minimum scope
create_knowledge
Minimum scope
create_memory
Minimum scope
create_sandbox
Minimum scope
create_task
Minimum scope
delete_data_app
Minimum scope
document_semantic_model
catalog from list_catalogs (same value as its catalog_name); schema and table match the lakehouse identifiers.Minimum scope
document_semantic_model_dimension
projection is the dimension name: alias (as) if set, otherwise the column name (same as listed under Columns/dimensions in get_catalog output).Minimum scope
execute_insight
insight for a saved insight or definition for a non-persisted insight, never both. A definition does not create or update a saved insight. Definitions dispatch on the kind field and expect the matching fields: funnel + funnel_definition, journeys + journeys_definition, segmentation + segmentation_definition, retention + retention_definition, semantic + semantic_definition, or sql + sql_definition + sql_parameters (x_axis_columns / y_axis_columns from SQL aliases). Definition-based funnel, journeys, segmentation, and retention kinds also require from, to, and interval inside definition. Preferred flow for new SQL results: validate the statement with query_lakehouse, then pass sql_definition and sql_parameters inside definition (visualization_options alone is not enough).Minimum scope
execute_lakehouse
truncation is set, re-issue the same statement with offset: <next_offset> to fetch the next page. Add a deterministic ORDER BY to any query that may be paginated; without it, continuation can duplicate or skip rows (especially for GROUP BY or joins). For read-only queries, prefer the query_lakehouse tool instead. Before writing your first statement, load the query-altertable skill by reading altertable://skills/query-altertable with read_resource, unless it is already loaded.Minimum scope
explain_sql
query-altertable skill by reading altertable://skills/query-altertable with read_resource, unless it is already loaded.Minimum scope
generate_dlt_pipeline
last_run_error to repair a pipeline whose task run failed. This spawns a sandbox and takes several minutes, so tell the user it is running and how long it takes before calling it, and call it once the target and the source are settled, not to explore options.Minimum scope
get_catalog
level: narrow with schemas and tables, and the tool automatically returns detailed schema for a small selection or a compact table overview for a large one. Use level: overview only when you explicitly want names and descriptions without columns; columns and full are explicit schema-depth overrides. After choosing a table, use profile_columns to inspect observed nulls, cardinality, uniqueness, ranges, and common values. Each table includes explicit semantic endorsement (draft, verified, excluded) labels. Tables whose semantic endorsement is excluded are omitted from the output. A column reported with contains_pii holds personally identifiable data: prefer aggregates over it and do not echo its values back to the user unless they ask for them. Typical flow: call with the default to discover tables. If more than one table could represent the requested concept, first inventory the schema without tables at level: overview; then pass tables: [...] for the specific tables you intend to query. When a table reports estimated_row_count, treat it as an approximate row count: on large tables keep query_lakehouse gentle with aggregates, selective filters, and LIMIT instead of scanning or returning every row.Minimum scope
get_finding
Minimum scope
get_neighbors
search_entities; read full content via altertable://ontology/entities/{slug}.Minimum scope
initialize
Minimum scope
list_catalogs
Minimum scope
list_dashboards
Minimum scope
list_events
Minimum scope
list_insights
Minimum scope
list_repositories
create_sandbox to clone specific repositories into a sandbox.Minimum scope
list_semantic_metrics
Minimum scope
list_tasks
type), target slug, and labels.Minimum scope
list_user_traits
Minimum scope
profile_columns
Minimum scope
query_lakehouse
truncation is set, re-issue the same statement with offset: <next_offset> to fetch the next page. Add a deterministic ORDER BY to any query that may be paginated; without it, continuation can duplicate or skip rows (especially for GROUP BY or joins). To write data, use the execute_lakehouse tool instead. Before writing your first statement, load the query-altertable skill by reading altertable://skills/query-altertable with read_resource, unless it is already loaded.Minimum scope
read_resource
altertable:// resource and returns its contents. altertable://skills/{name} returns a skill playbook and an additional_files manifest; altertable://skills/{name}/{directory}/{filename} returns a linked skill file (e.g. altertable://skills/analyze-product-behavior/references/match-recognize.md). altertable://ontology/entities/{slug} returns an entity in full; altertable://ontology/entities/{slug}/neighbors lists what it connects to; altertable://ontology describes the entity types. Use a URI already in context; otherwise find slugs with search_entities.Minimum scope
render_data_app
Minimum scope
render_insight
insight for a saved insight or definition for a non-persisted insight, never both. A definition does not create or update a saved insight. Definitions dispatch on the kind field and expect the matching fields: funnel + funnel_definition, journeys + journeys_definition, segmentation + segmentation_definition, retention + retention_definition, semantic + semantic_definition, or sql + sql_definition + sql_parameters (x_axis_columns / y_axis_columns from SQL aliases). Definition-based funnel, journeys, segmentation, and retention kinds also require from, to, and interval inside definition. Preferred flow for new SQL results: validate the statement with query_lakehouse, then pass sql_definition and sql_parameters inside definition (visualization_options alone is not enough).Minimum scope
report_finding
Minimum scope
run_sandbox_command
Minimum scope
search_docs
Minimum scope
search_entities
rrf_score for in-response ordering, a semantic_similarity (absolute relevance, present when the semantic branch matched), and matched_branches indicating which retrieval branches (lexical, semantic) fired per hit. Use node_types to scope by entity type; its schema lists every searchable type, and any other value is rejected. Read altertable://ontology for how types relate. Read a hit's resource_uri for its full content. Call get_neighbors to inspect directly related entities.Minimum scope
search_memory
Minimum scope
take_screenshot
Minimum scope
terminate_sandbox
create_sandbox. Safe to call more than once; a missing or already-expired sandbox is not an error.Minimum scope
update_dashboard
Minimum scope
update_data_app
@altertable/data-app, and @altertable/data-app-react. It replaces the title, description and queries with those it declares. Returns the slug and URL.Minimum scope
update_insight
funnel_definition, segmentation_definition, sql_definition, etc.) and matching *_parameters apply to the current or updated kind. Returns the insight ID, slug, and URL.Minimum scope
update_knowledge
Minimum scope
update_task
script and timeout_seconds of a dlt_run task. A task can carry a schedule and events at the same time; omitted fields are left unchanged. For a dlt_run task, catalog, schema and targets are fixed at creation; its script, timeout and the common task fields stay updateable.Minimum scope
validate_data_app
errors is empty, type errors included; warnings never fail validation.Minimum scope
validate_sql
query-altertable skill by reading altertable://skills/query-altertable with read_resource, unless it is already loaded.Minimum scope
web_search
Minimum scope