Create a data feed
create_data_feedSaves a data slice or an Export Data job as a data feed that Power BI, Excel Power Query or any tool that reads a URL can refresh on a schedule. For a slice feed, I read the slice once to check it and pin the members it resolved. For a job feed, I save the job definition without running it. I store the feed under this user's connection and policy and return the link to the Feeds page where the user creates the feed key. The key is created in the portal, not in chat; this tool stores no secret. Use it when the user wants the numbers they are looking at to flow into Power BI or another BI tool. For a Power BI dashboard, first use find_members for Revenue, COGS and Opex and let the user choose their totals. The user chooses the account map. Dashboard feeds include every year and Actual, Plan (Budget when Plan is absent) and Forecast by default, without asking. Saved business definitions take precedence, then names or Default aliases. Only non-empty cells are kept. Ask for entity (offer the top entity), one version, one currency when present, and the other shared dimensions. Pass accountGroups and dashboard to build totals and children across the chosen entities, all YearTotal leaf periods, scenarios and years. I count the cells and refuse a dashboard that exceeds policy or the cache/body size limit. The demo uses the same flow; offer Revenue, COGS and OpEx for its account map. For a write, I require a preview first, then confirm: true and its confirmationToken. The token lasts ten minutes and works once.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>"
},
"name": "create_data_feed"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| pov | No | Members for any other dimension, for example { Version: "NSP_Base", Currency: "USD" }; dimensions you leave out use their top member | |
| kind | No | slice (the default) saves an export_data_slice; job saves an Export Data job definition run by export_data | |
| name | Yes | A short name for the feed, unique per person, for example Revenue by month | |
| rows | No | Dimension names to put on rows, e.g. ["Account", "Department"]. Defaults to the account dimension. | |
| year | No | Year member, e.g. FY26 or FY24 | |
| where | No | For kind job: keep only rows whose column contains the text, e.g. { "Point-of-View": "FY24" } | |
| entity | No | Entity member, e.g. North America. Goes to the cube's entity-like dimension (Entity, Subsidiary, Company). | |
| period | No | Period member or comma-separated list, e.g. Jan, Q1 or TP1,TP2,TP3. Member functions such as ILvl0Descendants(YearTotal) work. Defaults to level 0 members under YearTotal. | |
| account | No | Account member or comma-separated list, e.g. Revenue or Descendants(Net Income). Defaults to all level 0 accounts. | |
| appName | No | Application name. Defaults to the connection's application. | |
| columns | No | Dimension names to put on columns, e.g. ["Period"] or ["Period", "Scenario"]. Defaults to the period dimension. | |
| confirm | No | Set true after the user has approved the previewed change | |
| jobName | No | For kind job: the Export Data job definition name, exactly as list_job_definitions shows it | |
| maxRows | No | For kind job: the most rows the feed returns (default 5000) | |
| planType | No | Cube (plan type) to export from, e.g. Plan1 or NSP_NFS. When the application has one cube it is used; with several, pass one. Otherwise Plan1. | |
| scenario | No | Scenario member, e.g. Actual, Plan, NSP_Actual | |
| dashboard | No | Build a dashboard slice. Omit scenarios and years to include the default scenarios and every year without asking. Explicit lists narrow an oversized feed. Entity defaults to the top entity; Currency is required only when the cube has it. Use pov for any other shared dimensions. | |
| connection | No | Connection id or label from list_connections. Defaults to the user's default connection. | |
| povMembers | No | For kind job: Oracle's povMembers override, e.g. NSP_Actual,FY24,Subsidiary | |
| rowMembers | No | For kind job: Oracle's rowMembers override, e.g. ILvl0Descendants(Account) | |
| cacheSeconds | No | How long a result is served from cache before Oracle is read again, 0 to 3600 seconds, admins only. Omit to use the organization setting, then the server default (60). Zero reads Oracle on every refresh, up to 6 live runs a minute. | |
| planningData | No | Set true to read through the application's form engine (Smart List labels, form-level security) instead of the plain cube export. The cube export is the default because the form engine returns nothing when a parent member is in the point of view. | |
| accountGroups | No | Optional exact account totals. Use find_members and ask the user to choose each total. Required for a dashboard. | |
| columnMembers | No | For kind job: Oracle's columnMembers override, e.g. TP1,TP2,TP3 | |
| confirmationToken | No | Single-use token from this exact preview. Send it with confirm: true after the user approves. It expires after ten minutes. |