Cube MCP Server

Cube Planning MCP server. Connect with OAuth, select a company, then call company-scoped tools against that company.

Server URL: https://mcp.cubesoftware.com

Connect an MCP client to this URL using OAuth. Call list_companies and select_company before company-scoped tools. Machine-readable catalog: /docs.json.

Tools (35)

List Companies list_companies read-only

List all companies the user has access to

Parameters

No parameters.

Select Company select_company writes data

Selects which company of the ones the user has access to is used for requests.

Parameters

Name Type Required Default Description
company_id string required — The ID of the company to select.

Returns: A message indicating the company has been selected.

Get Chart of Accounts get_chart_of_accounts read-only

Get the Chart of Accounts for this company.

For large cubes, pass tld_name (e.g. Account, Time, Department) to return only that top-level
hierarchy. Parents with more than 200 direct children are truncated; use get_dimension_children
to browse those children with offset/limit (and optional name_contains).

Parameters

Name Type Required Default Description
tld_name string | null optional null Optional top-level dimension name. When set, only that TLD's tree is returned.

Returns: JSON string of {"dimension name": [member tree...]}, or an error if tld_name is not found.

Get Dimension Children get_dimension_children read-only

Browse direct children of a dimension when chart-of-accounts children were truncated.

Use after get_chart_of_accounts returns a node with _children_truncated. Dimension IDs must come
from get_chart_of_accounts in this session. Paginate with offset/limit; optionally filter with
name_contains for wide lists (hundreds of children).

Parameters

Name Type Required Default Description
dimension_id integer required — Parent dimension ID from get_chart_of_accounts.
offset integer optional 0 Zero-based index into the filtered child list (default 0).
limit integer optional 100 Max children to return per page (default 100).
name_contains string | null optional null Optional case-insensitive substring filter on child names.

Returns: JSON envelope with parent_id, parent_name, total, offset, limit, has_more, and children.

List Dashboards list_dashboards read-only

List Cube dashboards the user has access to

Parameters

No parameters.

Get Dashboard get_dashboard read-only

Get a Cube dashboard by ID, including tabs, widgets, layout, and range dimensions

Parameters

Name Type Required Default Description
dashboard_id string required — —

Create Dashboard create_dashboard writes data

Create a Cube dashboard with tabs, widgets, layouts, and data sources.

IMPORTANT: The IDs for filters, row_header_dimension_ids, and column_header_dimension_ids must be
retrieved first using the get_chart_of_accounts tool. Do not guess these IDs.

Parameters

Name Type Required Default Description
name string required — The name of the dashboard. Must be unique within the company.
description string optional "" Optional description of the dashboard.
filters object | null optional null Optional global dashboard filters where each key is a top-level dimension name and each value is a member dimension ID from that hierarchy.
tabs array[object] | null optional null Optional list of tab definitions. Each tab can include a name and widgets. Widget definitions include name, type, visual_type, filters, row_header_dimension_ids, column_header_dimension_ids, layout_x, layout_y, width, height, and settings. type must be RANGE (data widget) or TEXT (text block). visual_type must be DATA_TABLE, LINE, BAR, ROW, COMBO, PIE, DONUT, METRIC, TREND, WATERFALL, or TEXT. Do not put a visual_type such as BAR or DATA_TABLE in type.

Returns: A message with the created dashboard ID or a validation error explaining what needs to be fixed.

Update Dashboard update_dashboard destructive

Update an existing Cube dashboard by replacing its metadata, tabs, widgets, and layouts.

IMPORTANT: Call get_dashboard first if you need to preserve existing tabs or widgets. This tool applies the
submitted dashboard definition to the existing dashboard.

Parameters

Name Type Required Default Description
dashboard_id string required — The ID of the dashboard to update.
name string required — The updated dashboard name. Must be unique within the company.
description string optional "" Optional updated description.
filters object | null optional null Optional global dashboard filters where each key is a top-level dimension name and each value is a member dimension ID from that hierarchy.
tabs array[object] | null optional null Optional list of tab definitions. Each tab can include a name and widgets. Widget definitions use the same structure as create_dashboard. type must be RANGE (data widget) or TEXT (text block). visual_type must be DATA_TABLE, LINE, BAR, ROW, COMBO, PIE, DONUT, METRIC, TREND, WATERFALL, or TEXT. Do not put a visual_type such as BAR or DATA_TABLE in type.

Returns: A message with the updated dashboard ID or a validation error explaining what needs to be fixed.

Get Widget Settings Schema get_widget_settings_schema read-only

Get available widget settings fields and valid values for dashboard widgets

Parameters

Name Type Required Default Description
visual_type string optional "" —

Get Financial Slice of Data get_financial_slice_of_data read-only

Use this function to get a slice of financial data for this company. This function acts like a pivot table in a spreadsheet and will
show a slice of financial data. The row and column headers will be on the top and left side of the grid. The filters will be applied to
the data in the grid. Think of this as building a Summary Table. It aggregates data into a grid based on the dimensions you provide.

IMPORTANT: The IDs for 'filters', 'row_header_dimension_ids', and 'column_header_dimension_ids' MUST be retrieved first using the
'get_chart_of_accounts' tool. Do not guess these IDs.

Optional time_aggregations: map each Time dimension ID (integer) to a time shortcut string so rollups are computed server-side by the
cube engine. Do not fetch many separate time periods and sum them in the client; use one anchor Time ID plus a shortcut instead.

Shortcut examples include YTD (year-to-date), QTD (quarter-to-date), LTD (lifetime-to-date), ROY (rest of year), T2M/T3M (trailing N months,
digit 1-365), N6M (next N months), T2Q/N3Q (trailing/next N quarters), T2Y/N1Y (trailing/next N years).

Anchor level: for month-level shortcuts (T2M, T3M, N6M, QTD, etc.) use the specific month or period Time dimension ID, not a year or
quarter ID. For quarter-level shortcuts (T2Q, N3Q) use the quarter ID. For year-level shortcuts (T2Y, N1Y) use the year ID.

Every key in time_aggregations must also appear in row_header_dimension_ids or column_header_dimension_ids, not in filters. When using
time_aggregations, do not also pass a separate Time filter; put the Time ID on a row or column axis so the rollup appears in the grid.

If arguments are invalid (wrong dimension IDs, Time ID not on an axis, shortcut vs level mismatch, etc.), the response is a JSON string
with an 'error' field and a human-readable 'message' describing the fix.

CURRENCY: Returned values are in the company's default currency unless you pass currency. When the user
asks for a non-default currency, call list_currencies and pass that currency's code. Do not convert the
numbers yourself. One code applies to every value in the request. Omit currency when the default
currency is what was asked for.

Example call — Revenue by Department for Q1 2025 months (IDs are illustrative; always use real IDs from get_chart_of_accounts):
filters: {"Account": 5010, "Scenario": 301}
row_header_dimension_ids: [120, 121, 122] # Department children: Sales, Marketing, Engineering
column_header_dimension_ids: [800, 801, 802] # Time children: Jan-25, Feb-25, Mar-25

Example call with time_aggregations — YTD Revenue by Department as of Mar 2025:
filters: {"Account": 5010, "Scenario": 301}
row_header_dimension_ids: [120, 121, 122] # Department children: Sales, Marketing, Engineering
column_header_dimension_ids: [802] # Time child: Mar-25 (month-level anchor for YTD)
time_aggregations: {802: "YTD"}

Parameters

Name Type Required Default Description
filters object required — A dictionary where each key is a dimension name and each value is the ID of a single child from that dimension in the Chart of Accounts. If a dimension is included in the filters, it should not be included in the row or column headers. These are global constraints on the data.
row_header_dimension_ids array[integer] required — A list of IDs of children from a single dimension. This dimension IDs must be from the company's Chart of Accounts. This cannot be empty.
column_header_dimension_ids array[integer] required — A list of IDs of children from a single dimension. This dimension IDs must be from the company's Chart of Accounts. This cannot be empty.
time_aggregations object | null optional null Optional map from Time dimension ID to shortcut. Omit or pass null when not needed.
currency string | null optional null Optional currency code from list_currencies. Omit to return values in the company default currency.

Returns: A slice of financial data comprised of a grid of values with their corresponding row and column header dimension names added in the first row and column.

Get Drilldown Data get_drilldown_data read-only

Use this for TRANSACTION-LEVEL auditing. This is the lowest level of detail available. Use this when a user asks for "source data,"
"specific transactions," or "the details behind this number." A header will be present for each dimension the company has,
the value of the data point, as well as any additional metadata that is stored about that data point.

IMPORTANT: The IDs for 'filter_dimension_ids' MUST be retrieved first using the 'get_chart_of_accounts' tool. Do not guess these IDs.
All dimensions must be represented in this dictionary.

Prefer using 'get_financial_slice_of_data' for aggregated reporting. Only use this tool when transaction-level detail is specifically requested.

CURRENCY: Amounts are in the company's default currency unless you pass currency. When the user asks
for a non-default currency, call list_currencies and pass that currency's code. Do not convert the
numbers yourself. Omit currency for the default.

The tool parameters are exactly filter_dimension_ids, operation, and operation_parameters (plus the framework context). Do NOT use
alternate parameter names like account_ids, start_date, or end_date. Keys in filter_dimension_ids must be exact dimension names from
the chart of accounts (e.g. "Account", "Department", "Time"). For a date or period range, pick the appropriate child IDs under the
company's Time dimension from get_chart_of_accounts—do not pass raw calendar dates as separate parameters.

Example call (IDs are illustrative; always use real IDs from get_chart_of_accounts):
filter_dimension_ids: {"Account": 65002, "Department": 12, "Time": 88}
operation: "head"
operation_parameters: {"n": 20}

Parameters

Name Type Required Default Description
filter_dimension_ids object required — A dictionary where each key is a dimension name and each value is the ID of a single child from that dimension in the Chart of Accounts. All dimensions must be represented in this dictionary. Keys must be dimension names, not numeric indices like "0" or "1".
operation string required — A pandas DataFrame operation to run on the drilldown data (required). Common operations: - 'head': Returns first N rows (e.g., {'n': 10}). Use to preview the data structure. - 'sort_values': Find outliers (e.g., {'by': 'Value', 'ascending': False}). - 'query': Filter further (e.g., {'expr': 'Value > 10000'}). - 'sum': Aggregate a column (e.g., {'numeric_only': True}).
operation_parameters object required — The parameters to pass to the pandas operation as a JSON object (dict), not a string. See pandas DataFrame documentation for operation-specific parameters.
currency string | null optional null Optional currency code from list_currencies. Omit to return amounts in the company default currency.

Returns: The result of the pandas operation as a string. If the resulting DataFrame exceeds 500 rows, it will be automatically truncated with a warning. If you see a truncation warning, refine your 'operation_parameters' to be more specific (e.g., use more filters or aggregation operations like 'sum()', 'mean()', etc.).

List Currencies list_currencies read-only

List the currencies enabled for this company.

Each entry includes the currency and whether it is the company's default (base)
currency. An empty list means multi-currency is not enabled. Pass a code from this
list as currency when fetching or publishing data in a non-default currency.

Parameters

No parameters.

Returns: JSON list of the company's active currencies from the company currency serializer.

Publish Data publish_data destructive

Publish financial data to an AI-managed Scenario in the cube.

IMPORTANT: Call get_chart_of_accounts first and enumerate this cube's actual TLDs
and leaf members. Only Account, Time, Scenario, and Department are guaranteed;
all other TLDs are customer-defined and vary by cube (Entity, Market, Product,
Vendor, Region, etc. — or none). All dimension references (row headers, column
headers, filter values) must be IDs from that response — never hardcode names or
reuse IDs from memory or a previous session/company.

PERFORMANCE: Each publish triggers formula recalculations and is a heavy operation.
Minimize the number of publish calls by batching as much data as possible into each
one. Use multiple row headers and column headers to publish a wide matrix in a single
call rather than making many small publishes. For example, publish all accounts x all
time periods in one call instead of one call per account or per period.

COMPLETENESS AND LEAF-LEVEL RULE: Every TLD the cube has must appear on a
row/column axis in data or as a key in filters. Data is stored only at child
(leaf) members — parents, formula members, and tag members cannot be written to
(they recalculate from inputs). Write leaf driver accounts and let formula
rollups (Net Income, EBITDA, Gross Margin, etc.) recompute. Filters pin exactly
one leaf per dimension for the whole call.

NESTED ROW AXES: Multiple dimensions nest on the row axis (stacked header
columns, one per dimension) with Time across the columns. A fully-dimensional
dataset publishes as a single range. Do not loop one publish per
dimension-combination — batch all intersections and periods into one wide
payload. Example with Account and Department on rows, Time on columns, Scenario
in filters (IDs illustrative; use real IDs from get_chart_of_accounts; pivot
cells in the top-left are empty strings):
[["", "", time_id_1, time_id_2],
[acct_id_1, dept_id_1, 100, 200],
[acct_id_1, dept_id_2, 300, 400],
[acct_id_2, dept_id_1, 150, 250]]

DISTRIBUTE HIGH-LEVEL CHANGES: Changes are usually described at a high level
("grow platform revenue 8%", "hold S&M flat"), but the cube stores at leaf
intersections. Don't collapse a high-level change onto an arbitrary or single
leaf — look at how the baseline scenario the change builds on is broken down
across dimensions and distribute in a way that respects that shape. Read real
joint intersections via get_financial_slice_of_data where possible rather than
reconstructing from marginals or assuming; reason per line, since different
lines break down differently. This is default behavior, not a hard rule:
explicit user guidance on how a change should land overrides it. Be transparent
that any dimensional detail so introduced is inferred from the baseline, not
user-specified.

The Scenario dimension must be included in filters and must target an AI-managed
scenario (write_protection = 'AI').

CURRENCY: Values are stored in the cube's base currency, or in each entity's
functional currency for multi-currency by subsidiary. When the figures are in a
non-base currency, call list_currencies and pass that currency's code. Do not
convert the numbers yourself. Cube applies the company's mapped rates and each
account's rate type. Omit currency when the figures are already in the base
currency.

Parameters

Name Type Required Default Description
data array[array[object]] required — 2D array. Column headers (Time IDs) occupy the first row after empty pivot cells. Nested row-axis dimensions occupy leading columns of each data row (one cell per TLD), then numeric values. Include as many rows and columns as possible to minimize total publish calls.
filters object required — TLD name -> member dimension ID. Must include Scenario and all other TLDs not represented in row/column headers. Each value must be a writable leaf member ID.
message string required — Changelog description for the publish.
currency string | null optional null Optional currency code from list_currencies that applies to every value in the call. Pass the code the figures are denominated in. Omit when they are already in the base currency.

Returns: A summary of values updated and an audit trail link. Validation errors, or a background-processing message if the publish is still running after monitoring completes (publishes always run via a background worker with up to ~3 minutes of status polling before returning).

List Connections list_connections read-only

List the company's data connections. Each connection includes name (the name shown on the Connections page), data_table_id (the connection ID initiate_import accepts), source, type, recent imports, and scheduled-import configuration. Match the user's connection name against the name field. Confirm with the user when more than one connection matches or none does.

Parameters

No parameters.

Initiate Import initiate_import writes data

Start a data import for a connection's data table.

Prefer reusing parameters from list_connections recent_imports: start_time_dimension_id,
end_time_dimension_id, scenario_dimension_id, and other_dimensions (flat leaf IDs for
defaults such as Department). Dimension IDs may also come from get_chart_of_accounts.

When other_dimension_ids is omitted, the tool reuses defaults from the most recent
successful import for that connection. If there is no prior successful import, you must
pass other_dimension_ids explicitly.

If a prior initiate_import failed with "Sync source dimensions before importing", confirm
with the user first, then retry with sync_dimensions_first=True. If the response has
status DIMENSION_SYNC_BACKGROUNDED, tell the user to wait for the background sync to
finish, then call initiate_import again without sync_dimensions_first.

Parameters

Name Type Required Default Description
data_table_id string required — The data_table_id from list_connections for the connection to import. Match the user's connection name to the list_connections name field, then pass that connection's data_table_id. Confirm with the user when more than one connection matches or none does.
scenario_id integer required — Scenario dimension member ID to import into.
start_time_dimension_id integer required — Start of the Time range to import.
end_time_dimension_id integer required — End of the Time range to import.
other_dimension_ids array[integer] | null optional null Optional list of default leaf dimension IDs for non-mapped TLDs (e.g. Department). Exclude Scenario and Time; Scenario is passed separately.
sync_dimensions_first boolean optional false When True, sync source dimensions before starting the import. Use only after confirming with the user when a prior attempt required a sync.

Returns: The started import object as JSON (id, status, time/scenario dimensions, etc.), or a DIMENSION_SYNC_BACKGROUNDED status when the sync was started in the background.

List Source Dimensions list_source_dimensions read-only

List the source dimensions that belong to a data table.

These are the dimension ids to pass as source_dimension_id to set_mappings. They are not
Cube dimensions. Cube dimension ids still come from get_chart_of_accounts.

Pass data_table_id from list_connections. The response has the same shape as
get_chart_of_accounts: top-level dimension names mapped to member trees of id, name, and
children. A node with _children_truncated has too many direct children. Call this tool
again with that node's id as parent_id, and optional offset, limit, and name_contains,
to page those children.

Parameters

Name Type Required Default Description
data_table_id string required — The data_table_id from list_connections.
parent_id integer | null optional null Source dimension id whose direct children should be paged. Omit to return the tree.
offset integer optional 0 Zero-based index into the filtered child list. Used with parent_id.
limit integer optional 100 Maximum direct children to return. Used with parent_id.
name_contains string | null optional null Case-insensitive substring filter on direct child names. Used with parent_id.
tld_id integer | null optional null Optional source top-level dimension id. Limits the tree to that top-level dimension.

Returns: JSON of the source dimension tree, or one page of children when parent_id is set.

List Mappings list_mappings read-only

List source-to-Cube dimension mappings for a connection.

Pass data_table_id from list_connections. Set tld_id to a source top-level dimension id
to limit the result. Set unmapped_only to true to return only source dimensions that have
no Cube mapping and are not ignored. There is no separate unmapped-members tool.

The default response groups existing mappings by top-level dimension. A group with
truncated=true is capped; call list_mappings_for_parent with that tld_id (or a deeper parent
source dimension id) to list every direct child. Mapped rows whose Cube target is outside
this user's data access scope are omitted.

Resolve both members to ids before calling set_mappings. That tool accepts
source_dimension_id and dimension_id only. Source dimension ids come from
list_source_dimensions. Cube targets are leaf member ids from get_chart_of_accounts.

Parameters

Name Type Required Default Description
data_table_id string required — The data_table_id from list_connections.
tld_id integer | null optional null Optional source top-level dimension id. Invalid ids return valid_tld_ids.
unmapped_only boolean optional false When true, list source dimensions that still need a mapping.

Returns: JSON of existing mappings, or unmapped source paths when unmapped_only is true.

Get Mappings For Parent list_mappings_for_parent read-only

List every direct-child mapping under a parent source dimension.

Use this when list_mappings reports truncated=true. Pass the group's tld_id, or a deeper
parent source dimension id, to page one level without the per-dimension cap.

Parameters

Name Type Required Default Description
data_table_id string required — The data_table_id from list_connections.
source_dimension_id integer required — Parent source dimension id whose direct children should be listed.

Returns: JSON with mapped and ignored counts and the direct-child source/cube path pairs.

Set Mappings set_mappings destructive

Map or remap source dimensions to existing Cube leaf members.

Requires Use MCP Write. Each row may only include source_dimension_id and
dimension_id. Source dimension ids come from list_source_dimensions. Cube
targets are existing leaf member ids from get_chart_of_accounts. This tool does not
create Cube dimensions.

Every row gets a result. Valid rows are applied even when other rows fail. A target that
is missing, disabled, a parent, in the wrong top-level dimension, or outside the user's
data access scope is returned as an error and is not applied.

Remaps that must move imported data finish in the background (code MAPPING_BACKGROUNDED).
The user receives an email when that work finishes.

Parameters

Name Type Required Default Description
data_table_id string required — The data_table_id from list_connections.
mappings array[object] required — Rows to map. Each object may only include source_dimension_id and dimension_id.

Returns: JSON with code, message, and a result object per row. permission_denied is raised when the user cannot change mappings.

List Planning Tables list_planning_tables read-only

List planning tables the user has access to. Each column includes its type. mapped_dimension is system-managed: read it like a dimension column, and do not recreate it in create_planning_table.

Parameters

No parameters.

Get Planning Table Schema Options get_planning_table_schema_options read-only

Get valid planning table column types, attributes, formats, and the company top-level dimensions for dimension columns. Call before create_planning_table.

Parameters

No parameters.

Create Planning Table create_planning_table writes data

Create a planning table with a typed column schema and empty datasets for the given scenarios.

IMPORTANT: Call get_planning_table_schema_options first for valid column types, required attributes,
format enums, and top-level dimension IDs (tld_id for dimension columns). Call get_chart_of_accounts
for Scenario member IDs to pass in scenario_ids.

Creates one header-only dataset per scenario so write_planning_table_data can populate data next.
Only AI-write-protected scenarios (write_protection = 'AI') can subsequently receive data via
write_planning_table_data, even though any writable scenario may be used at create time.

Column types: text, number, date, enum, dimension, calculation. Omit column id (auto-assigned).
Do not add mapped_dimension columns; the system manages those on existing tables.
Calculated columns require required=false and a formula; output_type is inferred on save.
sharing_scheme may be MANAGERS (default) or ALL — SPECIFIC is not supported via MCP.

Parameters

Name Type Required Default Description
name string required — Unique planning table name within the company.
schema array[object] required — List of column definitions. Each column needs name, type, required, plus type-specific attributes from get_planning_table_schema_options.
scenario_ids array[integer] required — Writable Scenario dimension member IDs from get_chart_of_accounts. At least one required. Empty header-only datasets are created for each.
sharing_scheme string optional "MANAGERS" MANAGERS (default) or ALL.

Returns: JSON with the created table id, name, columns, sharing_scheme, and scenario_ids, or a rejection message describing schema/permission failures to fix before retrying.

Get Planning Table Data get_planning_table_data read-only

Get the 2D data grid for a planning table in a specific scenario.

Planning tables store typed columnar data (text, number, dimension, calculated columns)
used for strategic planning such as headcount. Call list_planning_tables first to discover
available table IDs and column types. A mapped_dimension column is system-managed;
treat its cells like dimension member IDs and keep that column when writing data back.
Scenario IDs must come from get_chart_of_accounts (Scenario dimension).

Returns JSON with planning_table_name, scenario_id, headers (column names), and rows
(2D array of cell values). Rows the user cannot access due to dimension permissions are
excluded.

Parameters

Name Type Required Default Description
planning_table_id integer required — The ID of the planning table from list_planning_tables.
scenario_id integer required — The Scenario dimension member ID from get_chart_of_accounts.

Returns: JSON string with headers and filtered data rows for the planning table dataset.

Write Planning Table Data write_planning_table_data destructive

Replace the full dataset for a planning table in a specific scenario.

IMPORTANT: Always call get_planning_table_data first, modify the returned rows, and resend the
complete set of rows. Omitted rows are deleted from the caller's accessible data. Rows the caller
cannot see due to dimension permissions are preserved automatically.
This check is scoped to the exact (planning_table_id, scenario_id) pair you're about to write.
Checking one scenario does not clear you to write to a different scenario — if the target scenario
changes for any reason (including mid-conversation redirection by the user), call
get_planning_table_data again for that specific scenario_id before writing, even if empty/no-data
was already confirmed elsewhere.

The Scenario must have AI write protection (write_protection = 'AI'). Scenario IDs must come from
get_chart_of_accounts. Column order and count must match the headers from get_planning_table_data /
list_planning_tables. Dimension cells may be member IDs (as returned by get) or member names.

Parameters

Name Type Required Default Description
planning_table_id integer required — The ID of the planning table from list_planning_tables.
scenario_id integer required — The Scenario dimension member ID from get_chart_of_accounts (must be AI-managed).
rows array[array[object]] required — Full 2D array of cell values (no header row). Same shape as get_planning_table_data rows.

Returns: JSON summary of the write (created/updated, rows written) or a rejection message describing validation/permission failures to fix before retrying.

List Tags list_tags read-only

List all tags and their members for this company

Parameters

No parameters.

Create Tag create_tag writes data

Create a new tag with the given name and member dimensions.

IMPORTANT: Member IDs must be retrieved first using the get_chart_of_accounts tool.
All member dimensions must belong to the same top-level dimension.

Parameters

Name Type Required Default Description
name string required — The name of the tag to create.
member_ids array[integer] required — List of dimension IDs to include as tag members.

Returns: The created tag as JSON with id, name, and member names, or a validation error message.

Create Dimension create_dimension writes data

Create a new dimension under an existing parent dimension.

IMPORTANT: parent_id must be retrieved first using the get_chart_of_accounts tool. Do not guess IDs.

When the parent is under the Scenario top-level dimension, the new dimension is created with AI write
protection so it can receive published data via publish_data. Otherwise write protection defaults to none.

Parameters

Name Type Required Default Description
parent_id integer required — The ID of the parent dimension from the Chart of Accounts.
name string required — The name of the dimension to create.
rollup_type string required — Time rollup type. Valid values: SUM, AVERAGE, BALANCE, BEGINNING_BALANCE, or an empty string when rollup does not apply (e.g. non-Account/Scenario hierarchies). Scenario children typically use SUM.

Returns: The created dimension as JSON with id, name, parent_id, rollup_type, and write_protection, or a validation error message.

Get Formula Syntax get_formula_syntax read-only

Get full Cube formula syntax: IF, functions, SKIP, intersections, TABLE_LOOKUP, and constraints

Parameters

No parameters.

Create Formula create_formula writes data

Create a new formula dimension under an existing parent.

CONFIRM WITH THE USER BEFORE CALLING. Formula calculation runs in the background after create and can be
expensive depending on formula complexity. Calculated values are not available immediately. Before calling,
show the user the proposed name, parent, exact formula text, and Apply To scenario, and wait for confirmation.

IMPORTANT: parent_id, apply_to_scenario_id, and all dimension names referenced in the formula must come from
get_chart_of_accounts in this session. Do not guess IDs or names. apply_to_scenario_id is a Scenario dimension
ID, never a scenario name.

One call creates one formula dimension. Pass apply_to_scenario_id to limit that formula to one Scenario.
Omit it to apply the formula to every scenario. A different formula for another scenario is another create_formula call.

Formula syntax (quoted dimension names preferred). Call get_formula_syntax before writing non-trivial expressions (IF composition, functions, SKIP, intersections, TABLE_LOOKUP).
- Dimension refs: "Revenue" or <id>
- Operators: + - * / ^, unary +/-, parentheses
- Comparisons: = != > >= < <=; AND / OR (case-insensitive)
- Conditionals: IF(condition, true_expr, false_expr)
- Constraints: referenced dimensions must share the new dimension's TLD; no Time, tags, self, or parent; at least one dimension reference required

Write protection is none (formula members are not writable). The Apply To scenario must be a leaf Scenario ID
the Formulas drawer would allow. Actuals scenarios, inactive scenarios, parent scenarios, formula scenarios,
and scenarios mapped to a general ledger are rejected.

Parameters

Name Type Required Default Description
parent_id integer required — Parent dimension ID from get_chart_of_accounts.
name string required — Name of the new formula dimension.
formula string required — Formula expression using names from the chart of accounts.
rollup_type string required — Time rollup type. Valid values: SUM, AVERAGE, BALANCE, BEGINNING_BALANCE, or "". Use BALANCE when the formula includes RUNNING_TOTAL.
rollup_logic string | null optional null Optional. ROLLUP_THEN_APPLY_FORMULA (Sum leaf values, then calculate); APPLY_FORMULA_THEN_ROLLUP (Calculate leaf values, then sum). Omit this argument and Cube chooses a rollup logic from the formula. TABLE_LOOKUP formulas are stored as APPLY_FORMULA_THEN_ROLLUP because those calculations run at the leaf.
apply_to_scenario_id integer | null optional null Optional integer ID of the Scenario dimension this formula applies to. Omit it to apply the formula to every scenario. Never pass a scenario name. The ID must be a leaf Scenario from get_chart_of_accounts that the Formulas drawer would allow (not Actuals, not inactive, not a parent, not a formula scenario, and not mapped to a general ledger).

Returns: JSON with the created dimension id, name, parent_id, rollup_type, type, formula, rollup_logic, apply_to_scenario_id, and a message that background calculation is in progress; or a validation/permission error to fix and retry.

Duplicate Scenario duplicate_scenario writes data

Duplicate an existing Scenario into a new AI-managed Scenario.

IMPORTANT: source_scenario_id must be retrieved first using the get_chart_of_accounts tool.
Do not guess IDs.

The duplication copies leaf-level cube values from the source Scenario in the background. The new
Scenario ID is not available immediately; tell the user it is running in the background and they
will receive an email when it completes. After it finishes, the new Scenario has AI write
protection so publish_data can write to it.

Parameters

Name Type Required Default Description
source_scenario_id integer required — The dimension ID of the existing Scenario to copy data from.
new_name string required — The name for the new duplicated scenario.

Returns: A message that duplication is running in the background, or a validation/permission error to fix and retry.

List Workflows list_workflows read-only

List workflows (processes) the user has access to, with optional status filter

Parameters

Name Type Required Default Description
status string optional "" —

List Tasks list_tasks read-only

List tasks for a workflow the user has access to.

Call list_workflows first to discover workflow IDs. workflow_id is required.

Parameters

Name Type Required Default Description
workflow_id integer required — The workflow (process) ID from list_workflows.
status string optional "" Optional task status filter. Valid values: DRAFT, TODO, DONE.

Returns: JSON list of tasks with id, name, description, status, due_date, assignee_id, and process_id.

Create Workflow create_workflow writes data

Create a new workflow (process).

The workflow is created with NOT_STARTED status and the current user as owner.

Parameters

Name Type Required Default Description
name string required — Unique workflow name within the company.
description string optional "" Optional workflow description.

Returns: The created workflow as JSON, or a validation/permission error message.

Create Task create_task writes data

Create a new draft task on a workflow.

Call list_workflows first to get workflow_id. The task is created as DRAFT with no assignee.
Use due_date as an ISO date string (YYYY-MM-DD); omit or pass empty string for no due date.

Parameters

Name Type Required Default Description
workflow_id integer required — The workflow (process) ID from list_workflows.
name string required — Task name (must be unique within the workflow).
description string optional "" Optional task description.
due_date string optional "" Optional ISO date string (YYYY-MM-DD). Must not be in the past.

Returns: The created task as JSON, or a validation/permission error message.

Get Change History get_change_history read-only

Return recent audit trail changes for the selected company.

Answers questions like "what has changed in my cube recently?" Events include
spreadsheet publishes, AI publishes, data imports, reverts, and source-system
dimension re-syncs. Each row includes who made the change, when it occurred,
and OlapCubeChange.metadata (document/sheet/range, import date range, etc.).

Rows that share the same batch_id belong to one user action (e.g. a batched
dimension remap) and should be summarized together.

Parameters

Name Type Required Default Description
start_date string optional "" Optional ISO-8601 start of the window. Defaults to 30 days ago.
end_date string optional "" Optional ISO-8601 end of the window. Defaults to now.
limit integer optional 25 Max events to return (default 25, max 100).
user_ids array[integer] | null optional null Optional list of user IDs to restrict results to.
event_type string optional "" Optional event type name. Valid values: CubeChangeEvent, ConnectionSyncEvent.

Returns: JSON with start_date, end_date, returned, truncated, and changes. Each change has change_id, occurred_at, changed_by, event_type, change_type, message, status, num_changes, batch_id, metadata, link, and reverted_by_change_id.

Resources (2)

company://context

Name: company_context
MIME type: text/plain
Description: Custom context about how the company operates that is relevant to its financial planning and analysis

company://chart-of-accounts

Name: chart_of_accounts
MIME type: application/json
Description: —