Tracing a broken dashboard
Priya Sharma, analytics lead at Acme Ltd, asked why the sales dashboard looked wrong. Memtro read its upstream lineage and the test cases on those tables, and showed a failing null check on the orders table.
Which data quality tests are failing, and what feeds the table they cover?
OpenMetadata is your data catalogue, and Memtro reads it so anyone can ask where data comes from. It searches tables, topics, dashboards, pipelines, glossary terms and domains, and reads a table's columns, owners and tags. It reads lineage up and downstream, test cases with their latest results, and data quality incidents. When asked and granted, it can acknowledge, assign, resolve, reopen or open an incident, add glossary terms and rewrite descriptions. OpenMetadata can tell Memtro when a test result arrives, and a job can start on it. Table sample data and incident assignees are never read.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right OpenMetadata tool, reads what it needs, and answers with the source cited.
These tools change something in OpenMetadata. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in OpenMetadata, choosing the same kinds; the tab shows OpenMetadata's own steps. Each event can start a job, with the event as its input. OpenMetadata signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce OpenMetadata is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Which data quality tests are failing right now?
What feeds the orders table, and what reads from it?
Who owns the customer dimension table?
What does the glossary say an active customer is?
Acknowledge the incident on the revenue freshness test.
Priya Sharma, analytics lead at Acme Ltd, asked why the sales dashboard looked wrong. Memtro read its upstream lineage and the test cases on those tables, and showed a failing null check on the orders table.
When OpenMetadata told Memtro a test result had arrived at Northwind, a job started. It read the failing test case and its open incident and, as granted, assigned the incident to the data engineering team, which was notified.
The teams that lean on OpenMetadata most, a question each of them asks, and what they connect beside it.
A record in OpenMetadata is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
In OpenMetadata, an administrator opens Settings, then Bots, gives a bot a role and generates a token. A personal access token also works. Edits need Data Steward rights.
In Memtro, open Connections → OpenMetadata and enter the Host (no https://) and the JWT token.
An administrator grants the incident, glossary and description actions by name to the data stewards who may use them. Events are turned on from the connection's Events tab, then added as a webhook alert in OpenMetadata, one per source.
Ask which data quality tests are failing.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The OpenMetadata tools are the same everywhere.
Only when you ask, and only what it has been granted: acknowledge a data quality incident; assign or reassign an incident to a user or team; resolve an incident with a reason and a comment; reopen a resolved incident; open a new incident on a test case; add a glossary term to a glossary; rewrite the description of a table or glossary term. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Host and JWT token. In OpenMetadata, an administrator opens Settings, then Bots, gives a bot a role and generates a token. A personal access token also works. Edits need Data Steward rights.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in OpenMetadata, choosing the same kinds; the tab shows OpenMetadata's own steps. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time