MCP App Store
by KeenEthics
Prophecy DataGPT icon

Prophecy DataGPT MCP Server for Claude and ChatGPT

By Prophecy

Overview

Your business context. Prophecy's governed data work. Answers you can check and rerun, in Claude. You know which accounts matter, what "on track" means and where the numbers break. What slows you down is the data work behind the answer: pulling, cleaning and joining messy data across systems. Prophecy DataGPT does that work end to end, from raw data to finished analysis and reports, without leaving the conversation. Ask "Which regions are behind on pipeline this quarter?" DataGPT pulls CRM exports and warehouse tables, cleans and matches records, applies your rules, and returns the answer with the visual workflow behind it. Inspect any step, open the code, or say what to change in plain language. For business teams: Go from raw data to a trusted report in plain language, using your team's definitions Turn messy, multi-tab Excel workbooks into clean tables on your data platform Check any number: every answer comes with the workflow and code behind it Rerun approved workflows on new data the same way every time, or schedule them For data teams and IT: Review and approve AI-built workflows instead of rebuilding them, backed by open code in Git Run everything on the Snowflake, Databricks or BigQuery you already own, with no separate engine Keep business-built work governed: traceable to source, separated by team, access by invite or domain Grow a knowledge graph from your catalogs that learns from every approved workflow About Prophecy: since 2017, Prophecy has built governed, code-backed data workflows for the world's largest enterprises. DataGPT brings that engine into the AI tools your teams already use. Try asking: "Reconcile this month's invoice export against payments in Snowflake and flag mismatches." "Count anything within $1 as a match, rerun, and share the unmatched list with my AP manager." Get started free: sign up for a Prophecy account when you connect. If your company manages connectors, your admin can add it for everyone.

How to connect

  1. Claude: Open the Prophecy DataGPT listing in the Claude connectors directory and choose Connect. Claude listing Prophecy DataGPT exposes 54 tools here.
  2. ChatGPT: Open the Prophecy DataGPT listing in the ChatGPT app directory and choose Connect. ChatGPT listing Prophecy DataGPT exposes 60 tools here.

Tools

prophecy_add_connection

ChatGPT
Open the Add-Connection widget so the user can test and save a new warehouse or file connection on fabricId (from prophecy_fabrics); kind preselects a connector. The widget saves it itself — no further tool call, and secrets never travel as tool arguments.

prophecy_ai

ChatGPT
Analyze data and answer questions about it with Prophecy AI, the agent that builds pipelines and analyses (charts, dashboards) and answers questions about an uploaded data file or a project. It knows the project's pipelines, gems, columns and lineage. Use it to: • BUILD / EDIT a pipeline, gem or analysis ('chart revenue', 'add a filter', 'undo that'); create a new one first with prophecy_create_pipeline / prophecy_create_analysis and pass it as pipeline / app. • QUESTIONS / CHARTS about a data file in the Databox (csv, json, parquet, txt), whether uploaded now or already there: pass the ask plus every Databox file_path it is about, both in message and in files; Totals, rankings and charts about that file come from here, computed on their fabric. ❌ WRONG: a total, count or description of that file's contents answered without calling this tool. A workbook (.xlsx/.xlsm) goes to prophecy_analyze_excel instead — Prophecy AI cannot analyze one. • Diagnostic Q&A ('why is column Y null?', 'trace lineage of Z'). Skip it for RUN-only (prophecy_run_pipeline), INSPECT-only (prophecy_pipeline_canvas, prophecy_run_table), chart audits (prophecy_audit_chart), cloud-file reads (SharePoint, OneDrive, S3, GCS, SFTP, Smartsheet, Databricks Volumes → prophecy_create_pipeline, then prophecy_analyze_excel), deletes (prophecy_delete_pipeline / prophecy_delete_analysis), and SCHEDULE intents (prophecy_pipeline_schedules / prophecy_schedule_pipeline, then prophecy_publish_project to make them run). Then: pipeline create / edit → prophecy_pipeline_canvas; if the ask includes a run → prophecy_run_pipeline INSTEAD (it draws the canvas; Prophecy AI's own run does not stream); analysis create / edit → prophecy_analysis. No project yet: create one with prophecy_create_project, then prophecy_create_pipeline in it, and tell the user which project you created. One running turn per project. Returns {conversationId, turnId, status:'running'} at once; call prophecy_ai_wait with those ids until status:done.

prophecy_ai_wait

ChatGPT
Collects the answer of a running prophecy_ai turn. Long-polls and returns status:done / status:error with the answer, or a still-running / awaiting-the-user's-answer status (call again).

prophecy_analysis

ChatGPT
Show the charts and dashboard of an analysis on live data: opens a persisted Prophecy analysis (SQL app), runs it on the fabric and renders its charts. For 'run / show analysis X', and after any prophecy_ai turn that creates or edits an analysis (its own run does not stream). Pass appName + its pipeline.

prophecy_analysis_sources

ChatGPT
READ-ONLY DIAGNOSTIC. Lists the tables a pipeline exposes for charting (Visualize / preview gems, with tableIds, labels and columns). To add charts call prophecy_ai instead; call this only when the user asks what a pipeline can chart, or to diagnose why Prophecy AI could not bind a chart (usually no Visualize gem).

prophecy_analyze_excel

ChatGPT
Analyze an Excel spreadsheet (.xlsx/.xlsm; a legacy binary .xls is not readable — have the user re-save it as .xlsx) the user attached, uploaded or points at, with Prophecy's table detector, and render the detected tables (sheet, cell range, confidence) as a real source gem. When the user asks to analyse a workbook in Prophecy, it is this tool's work: Prophecy AI has no table detector, and the detected tables become a gem a pipeline can run on. An attached file: upload it with prophecy_databox_upload_file, then pass the returned file_path with connection: 'ProphecyFileSystem'. A cloud file: its path plus the connection name. An existing gem for this file + connection is reused.

prophecy_answer_thread

ChatGPT
Widget-internal. Fired when the user clicks a clarifying-question or permission button inside the thread widget. Claude should not call this directly.

prophecy_attach_fabric

ChatGPT
Attach a fabric to a Prophecy project, as the SQL IDE does; use it when a tool errors because the project has no fabric. A no-op when that fabric is already attached. fabricId is required: take it from prophecy_fabrics (the active workspace default, unless the user named another), and never guess one — ask the user when it is unclear.

prophecy_audit_chart

ChatGPT
Audit how a chart's numbers were derived — the user asks, or clicks Audit / Inspect on an analysis widget. Runs the audit with Prophecy AI and opens the pipeline canvas in audit mode, contributing gems highlighted. Your reply is Prophecy AI's answer, relayed as written. chart is what the chart IS and datum the point clicked. Route chart audits here, not to prophecy_ai.

prophecy_branches

ChatGPT
List a Prophecy project's branches: the checked-out one, the main one and the rest.

prophecy_create_analysis

ChatGPT
Create a new, empty analysis (SQL App) on an existing pipeline; the name is checked with the IDE’s rules. Then add charts with prophecy_ai, app set to this name, and show it with prophecy_analysis.

prophecy_create_pipeline

ChatGPT
Create a new, empty SQL pipeline in a project; the name is checked with the IDE’s rules. Then build it with prophecy_ai, pipeline set to this name.

prophecy_create_project

ChatGPT
Create a Prophecy SQL project in the user's current workspace and attach a fabric to it. Returns the new project's id and link.

prophecy_create_tables_from_gem

ChatGPT
Write warehouse tables from any gem's output ports, one table per port, by running the gem once. processId is the gem's id or canvas label (from prophecy_analyze_excel or prophecy_pipeline_canvas); omit ports for all of them. Rows come from the gem's capped interim (default 10 MB), so a large output lands as a sample — repeat the reply's row counts and truncation flags. Not how output ports are created: prophecy_analyze_excel and the extract widget persist those. Requires confirm:true.

prophecy_databox

ChatGPT
Open the user's Databox — the file browser over their own files, project files and connected warehouses. Use it whenever the user wants to SEE, browse or pick from THEIR data ('show me my files', 'what data do I have', 'open my Databox'). Returns the listing at path and renders it as a browsable widget; pass no path for the Home landing. Every call mounts another browser card, so call it ONCE per turn, for the one folder the user wants to look at: when you need folder contents to answer in text — naming files back, counting, recursing, checking something exists — use prophecy_databox_list instead, which renders nothing and takes several folders at once. A project's files may sit at ['projects', <projectId>] or, if uploaded earlier, in its attachments child — list both before concluding a file is not there.

prophecy_databox_copy

ChatGPT
Copy a file (not a folder) in the user's Databox, from → to, both as prophecy_databox returns an item's path. The reply is text only, naming where the copy landed; call prophecy_databox_list on the folder if you need its contents. Fails if something sits at to unless overwrite is true — ask the user before setting it. A file keeps its extension: samples.json → report.json, never → samples. A connection path cannot be written to; some stores cannot copy and say so.

prophecy_databox_create_folder

ChatGPT
Create a folder in the user's Databox inside the PARENT path (segments as prophecy_databox takes them; [] is Home). A connection path cannot be written to.

prophecy_databox_delete

ChatGPT
Delete a file or folder (recursively) in the user's Databox by path: moves it to the Databox Trash, where the user can restore it. Deleting an entry already in the Trash (a ['trash', …] path) removes it for good. Requires confirm:true (ask the user first). A connection path cannot be deleted.

prophecy_databox_download_file

ChatGPT
Mint a 15-minute URL that streams a file's raw bytes from the user's Databox by path (segments as prophecy_databox returns them); the token in the URL is the credential. Only when the user asks to download or keep the file: give them the link, never fetch it yourself to read, total or chart the data (questions about a file → prophecy_ai). Not for connection paths.

prophecy_databox_list

ChatGPT
List what is inside Databox folders and answer in text alone — nothing is rendered. This is the tool for every listing you need in order to ANSWER: naming the files back to the user, counting them, recursing into subfolders, checking a folder holds something. prophecy_databox is only for when the user wants to SEE the browser, and each of its calls mounts another file-browser card. Pass every folder you need in ONE paths call rather than one call per folder, and never list a folder whose entries an earlier result already gave you.

prophecy_databox_move

ChatGPT
Move or rename a file (not a folder) in the user's Databox, from → to, both as prophecy_databox returns an item's path. Destination folders that don't exist yet are created, so don't create them first. The reply is text only, naming where the file landed; call prophecy_databox_list on the folder if you need its contents. Fails if something sits at to unless overwrite is true — ask the user before setting it. A file keeps its extension: samples.json → report.json, never → samples, so don't offer that. A connection path cannot be written to.

prophecy_databox_preview_file

ChatGPT
Show one file from the user's Databox inline — PDF, Excel, CSV, image, markdown or text (JSON, TXT, code, logs); Word/PowerPoint, audio/video, archives and other binaries get a download card. The widget streams the file itself, so no bytes enter the conversation. A password-protected (encrypted) PDF or Excel file is not rendered: the widget says it is password protected, and there is no password prompt. Databox files only, not files on a connection: a ['connection',…] path is refused. Clicking a file in the `prophecy_databox` widget sends "Preview the file `/<path>` from my Databox" as the user's turn — that message means CALL THIS TOOL with those path segments, nothing else. Pass the fabricId the prophecy_databox result carried; otherwise choose one as the fabricId description says. Bytes or a link to keep → prophecy_databox_download_file; browsing → prophecy_databox.

prophecy_databox_upload_file

ChatGPT
Save a file the user attached or uploaded in this chat — a spreadsheet, csv or other data file to analyze, or one to keep — into their Databox at path. If your host can hand over attachments, pass it as file and this server fetches it and returns the saved file_path; otherwise the reply returns a signed URL — POST the raw file bytes there as it shows and its 2xx response returns the file_path. ['projects', <projectId>] for a project's files; for personal ones, the user's own folder as prophecy_databox reports it for Home — the server names that folder, so a path you assembled from a prophecy_whoami userId may address one that does not exist. A connection is not an upload destination, so tell the user before calling. Several files → ONE call: hand them all over in files, or, POSTing bytes yourself, set count to the number of files and POST each to its own URL from the reply, all at once — never one call per file. Max 4 GB a file. If you hold an attachment neither as file nor as bytes, or its transfer fails, the chat dropped it; attaching it again fails the same way: tell the user the file is too large for the chat to hand over, and call prophecy_databox so they drop it into the Databox there. Then: no work named ('save this', a bare attachment) → prophecy_databox on its folder, so they see it. Any question, total, ranking, analysis or chart is work — 'add these to my files AND analyse …' is a work ask. With no project yet, create one with prophecy_create_project first and upload into ['projects', <projectId>]. A spreadsheet (.xlsx/.xlsm) → prophecy_analyze_excel with the returned file_path and connection: 'ProphecyFileSystem'. Any other format (csv, json, parquet, txt) → prophecy_ai with the ask verbatim plus the file_path, that same path also in files, then prophecy_analysis for the charts. The resulting total, aggregate or chart lands on the user's fabric, where their pipelines can reuse it.

prophecy_delete_analysis

ChatGPT
Delete an analysis (SQL App) from a project, leaving its pipeline; cannot be undone from here. Show the user which analysis and call once they agree (confirm:true).

prophecy_delete_pipeline

ChatGPT
Delete a SQL pipeline from a project; cannot be undone from here. Refuses, naming them, while analyses read from it unless force. Show the user which pipeline and call once they agree (confirm:true).

prophecy_delete_project

ChatGPT
Delete a Prophecy project permanently, as the Prophecy UI does; cannot be undone from here. Show the user exactly which project and call once they explicitly agree (confirm:true).

prophecy_describe_table

ChatGPT
Return every column and type of a warehouse table as text, from information_schema on the fabric.

prophecy_describe_warehouse_columns

ChatGPT
List a warehouse table's columns and types through its connection — cheaper than prophecy_describe_table.

prophecy_excel_preview_sheet

ChatGPT
WIDGET-INTERNAL. Loads one sheet's cell grid of an xlsx source that prophecy_analyze_excel already added, when the user clicks a sheet tab in the extract widget.

prophecy_fabrics

ChatGPT
List every fabric on the connected Prophecy account with its provider, workspace (team) and connections, plus the workspace the user is in and its default fabric. Call this to choose a `fabricId` — no tool picks one for you: in a project use that project's fabric (prophecy_project_detail), otherwise the active workspace's default, and ask the user when neither settles it. Answers 'which fabric / which connection' in one call. A fabric whose connections can't be listed has connections: null; a per-fabric failure is an error on its row.

prophecy_fast_run_gem

ChatGPT
Preview a gem's output rows, like the gem dialog's Run button; a cold cache materializes inputs first, and a source gem gets a plain gem run. Orchestration / ProphecyManaged fabrics only (a SQL warehouse fabric → prophecy_run_gem).

prophecy_get_thread

ChatGPT
Widget-internal. The ai-thread widget polls this to refresh itself. Claude should not call it; use prophecy_ai_wait for the answer.

prophecy_inspect_lineage

ChatGPT
Show Prophecy's Explore Lineage view of a chart audit, contributing gems highlighted. Call it when the user clicks 'Explore Lineage View' on an audit reply (the prompt names the ids), or for 'show me that lineage again' (no ids: the newest audit turn). A new audit is prophecy_audit_chart.

prophecy_list_connections

ChatGPT
List the connections on ONE fabric (warehouses and filesystems: Snowflake, Databricks, SharePoint, S3, ADLS, GCS, volumes, …) as {id, name, provider, isDefault}; feed name into prophecy_list_databases. For every fabric's connections at once use prophecy_fabrics.

prophecy_list_databases

ChatGPT
List the databases (catalogs / BigQuery projects) a warehouse connection exposes. Next is prophecy_list_schemas — a database name is not a schema for prophecy_list_schema_tables.

prophecy_list_schema_tables

ChatGPT
List the tables inside a warehouse schema; their columns come from prophecy_describe_warehouse_columns.

prophecy_list_schemas

ChatGPT
List the schemas inside a warehouse database (after prophecy_list_databases).

prophecy_notify_run

ChatGPT
Widget-internal — Claude should not call this directly. The pipeline widget reports a run the user started from its Run button, so Claude knows it happened.

prophecy_on_the_fly_analysis

ChatGPT
Chart a warehouse table on the fly: one chart per read-only SELECT (with LIMIT), rendered inline, nothing persisted; keep it with prophecy_save_analysis. Chart types: metric (one row, column 'value'), bar/line (x + series [{key,label}]), donut (label + value). Tables as catalog.schema."Table". GROUP BY the raw expression, never an alias or ordinal; double-quote names with spaces; take exact column names from prophecy_run_table first.

prophecy_pipeline_canvas

ChatGPT
Show a Prophecy pipeline's gem canvas, read-only — after an edit, or when the user asks to see one. Not a preflight, not for an unchanged one, and never in a turn that runs it: prophecy_run_pipeline draws this same canvas.

prophecy_pipeline_schedules

ChatGPT
List a SQL pipeline's schedules as saved in the project (name, on/off, quartz cron + time zone, parameter set, version pin). This is the saved definition, not what is deployed: a schedule runs only after prophecy_publish_project.

prophecy_pipelines

ChatGPT
List the SQL pipelines in a Prophecy project (live), as raw uids for a granular tool. For a user question like 'what pipelines are in project X' call prophecy_ai instead; use this only after Prophecy AI failed.

prophecy_project_create_file

ChatGPT
Create a NEW text file of PROJECT SOURCE (SQL models, YAML, .md, config) in a project's git tree; an existing file fails (use prophecy_project_update_file). A file described in prose ('write me a model that …') → prophecy_ai. A file the user attached, pasted or pointed at is DATA in EVERY format (csv / json / txt too) → prophecy_databox_upload_file, unless the user explicitly asked for the project source or git ('commit this', 'put it in the repo'); never infer that. Show the path and content and call once they agree (confirm:true).

prophecy_project_delete_file

ChatGPT
Delete a file from a Prophecy project's working tree; cannot be undone from here. Show the user which file and call once they agree (confirm:true).

prophecy_project_detail

ChatGPT
Read one Prophecy project: prophecy_projects' fields plus each entity's description, created, createdBy, modified and path, and the fabric attached on the working branch, always fresh. In a project, its fabric is the `fabricId` to pass to tools outside it (Databox, warehouse tables), not the workspace default.

prophecy_project_read_file

ChatGPT
Read a text file from a Prophecy project's working tree — 'show me file X', 'what's the SQL in Y', and after prophecy_ai writes a file so the user sees what landed. Binary files come back empty; user files in the Databox are read with prophecy_databox_download_file.

prophecy_project_update_file

ChatGPT
Replace the text of an EXISTING project source file (a missing one fails — use prophecy_project_create_file). Text only: a binary file is corrupted, and a user-supplied file of any format belongs in the Databox. For an edit described in prose route to prophecy_ai. Show the user the path and new content and call once they agree (confirm:true).

prophecy_projects

ChatGPT
List the projects in the connected Prophecy account, each with its description, creator, team, age and the names of its pipelines, datasets, models, analyses (sqlBusinessApps, each with its pipeline), seeds, sources and macros — enough for 'which project has X'. The 20 newest by default. Per-entity detail → prophecy_project_detail; fabrics → prophecy_fabrics.

prophecy_publish_project

ChatGPT
Publish a project version and deploy it to orchestration fabrics, which is what makes its saved schedules run (and stops deleted ones). Publishes the WHOLE project, every pipeline. Two calls: first without confirm to get the list of schedules each fabric will add, change or remove (nothing is written); show that to the user; then call again with confirm:true and the impactKey the preview returned. The confirm call saves uncommitted changes first, and returns a new list instead of publishing if the changes moved. Simple version control projects only.

prophecy_refresh_auth

ChatGPT
WIDGET-INTERNAL. Refreshes the widget-side bearer when /api/widget/* returns auth_expired. Ships the current bearer on _meta.authorization and no content. Do NOT call from the assistant.

prophecy_run_gem

ChatGPT
Run ONE gem of a Prophecy pipeline (the gem dialog's full Run) and show its output-port rows. Always the full run path, on the user's warehouse — call only when the user asks.

prophecy_run_pipeline

ChatGPT
Run a Prophecy pipeline on its fabric and render the pipeline widget with live interim row counts. RUN-only asks ('run pipeline X', 'show me dataset X') → call this directly, not prophecy_ai. EDIT + RUN → prophecy_ai, then this (Prophecy AI's own run does not stream). Whole pipelines only; a single gem is prophecy_run_gem.

prophecy_run_table

ChatGPT
Show the rows of a warehouse table, or of a SELECT, in the data explorer widget with per-column profiles, straight from the warehouse. Table mode: fabricId + connectionName + database + schema + table. Pass `connectionName` whenever the conversation names it (a Databox path connection/<name>/…, a clicked card), or the read uses the fabric's DEFAULT connection. Off the default connection database and schema are required, and where / orderBy / limit / columns / COUNT() do not apply. Free-form mode*: sql (SELECT-only, explicit LIMIT) for JOINs or aggregations, always on the default connection. A Source gem in a pipeline → prophecy_fast_run_gem; columns only → prophecy_describe_table.

prophecy_save_analysis

ChatGPT
Save an on-the-fly analysis (from prophecy_on_the_fly_analysis) as a real pipeline + SQL App. No side effects: returns structured.nextActions[0] = { tool: "prophecy_ai", args } to fire next with args.message verbatim, then check structured.expectedCharts with prophecy_analysis. No projectId yet → prophecy_create_project first.

prophecy_schedule_pipeline

ChatGPT
Create, change or delete a time-based schedule on a SQL pipeline, keyed by schedule name. On an existing schedule only the fields you pass change (e.g. just enabled:false to pause it). File-arrival schedules are edited in the Prophecy UI. The schedule is saved to the project but does NOT run until prophecy_publish_project publishes and deploys it - say so to the user.

prophecy_show_data_preview

ChatGPT
Render rows another tool returned in this conversation as a data-preview widget; fetches nothing. Never fabricate rows. Live data comes from prophecy_run_table, prophecy_fast_run_gem or prophecy_analysis.

prophecy_update_extract_region

ChatGPT
WIDGET-INTERNAL. Saves a resized cell range for one detected table on an xlsx source gem when the user drags a corner handle in the extract widget, and returns the refreshed payload.

prophecy_update_project

ChatGPT
Rename a Prophecy project and/or change its description. Show the user the change and call once they agree (confirm:true).

prophecy_whoami

ChatGPT
Show the Prophecy identity calls run as: account email, server, resolved SQL fabric and its catalog/schema — to confirm the account before writes.

prophecy_add_connection

Claude

prophecy_ai

Claude

prophecy_ai_wait

Claude

prophecy_analysis

Claude

prophecy_analysis_sources

Claude

prophecy_analyze_excel

Claude

prophecy_attach_fabric

Claude

prophecy_audit_chart

Claude

prophecy_branches

Claude

prophecy_create_analysis

Claude

prophecy_create_pipeline

Claude

prophecy_create_project

Claude

prophecy_create_tables_from_gem

Claude

prophecy_databox

Claude

prophecy_databox_copy

Claude

prophecy_databox_create_folder

Claude

prophecy_databox_delete

Claude

prophecy_databox_download_file

Claude

prophecy_databox_list

Claude

prophecy_databox_move

Claude

prophecy_databox_preview_file

Claude

prophecy_databox_upload_file

Claude

prophecy_delete_analysis

Claude

prophecy_delete_pipeline

Claude

prophecy_delete_project

Claude

prophecy_describe_table

Claude

prophecy_describe_warehouse_columns

Claude

prophecy_fabrics

Claude

prophecy_fast_run_gem

Claude

prophecy_inspect_lineage

Claude

prophecy_list_connections

Claude

prophecy_list_databases

Claude

prophecy_list_schema_tables

Claude

prophecy_list_schemas

Claude

prophecy_on_the_fly_analysis

Claude

prophecy_pipeline_canvas

Claude

prophecy_pipeline_schedules

Claude

prophecy_pipelines

Claude

prophecy_project_create_file

Claude

prophecy_project_delete_file

Claude

prophecy_project_detail

Claude

prophecy_project_read_file

Claude

prophecy_project_update_file

Claude

prophecy_projects

Claude

prophecy_publish_project

Claude

prophecy_run_gem

Claude

prophecy_run_pipeline

Claude

prophecy_run_table

Claude

prophecy_save_analysis

Claude

prophecy_schedule_pipeline

Claude

prophecy_show_data_preview

Claude

prophecy_update_project

Claude

prophecy_whoami

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/prophecy-datagpt"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/prophecy-datagpt)