Which Zilliz Cloud clusters are busiest, and are our collections loaded?
Zilliz Cloud connects Memtro to your managed Milvus vector database. It reads projects and clusters with plan, size, status and region, and a cluster's metrics over time, from compute and storage use to latency, failure rates and entities. It reads backups, alert rules, control-plane jobs, and a cluster's collections with schema, row count and load state. When asked and granted, it can suspend, resume, resize or drop a cluster, create, delete or restore backups, create or delete alert rules, and load, release or drop a collection. Stored vectors and values are never read, and alert rules need Project Admin.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Zilliz Cloud tool, reads what it needs, and answers with the source cited.
These tools change something in Zilliz Cloud. 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.
Once Zilliz Cloud 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 clusters had the highest p99 latency today?
Is the products collection loaded, and how many rows does it hold?
Which backups expire this week?
What alert rules does the search project have?
Suspend the staging cluster.
Maya Okafor, ML platform engineer at Acme Ltd, asked why search felt slow yesterday afternoon. Memtro read the cluster's metrics for that window, giving p99 latency, request counts, compute use and slow queries by hour. She took them to her lead before deciding on a resize.
Dan Fletcher, engineering manager at BigCo, asked Memtro to suspend the staging cluster over the holidays. With the action granted, Memtro suspended it, taking it offline and stopping compute billing while storage was still billed. When he asked for it back in January, it reached RUNNING after several minutes.
The teams that lean on Zilliz Cloud most, a question each of them asks, and what they connect beside it.
A record in Zilliz Cloud 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.
Grist
NocoDB
Typesense
Weaviate
Tinybird
Hightouch
Census
kintone
Monte Carlo
OpenMetadata
Secoda
Softr
Teable
VectaraIn the Zilliz Cloud console, open API Keys and use your personal key or create a customised one. Project Read-Only reads, Read-Write or Admin covers the actions, and Project Admin covers alert rules.
In Memtro, open Connections → Zilliz Cloud and paste the API key.
An administrator grants the cluster, backup, alert and collection actions by name to the teams that may use them. Only Organization Owners and Project Admins can create customised keys.
Ask which clusters had the highest p99 latency today.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Zilliz Cloud tools are the same everywhere.
Only when you ask, and only what it has been granted: suspend a dedicated cluster (stops compute billing, takes it offline); resume a suspended cluster (compute billing restarts); resize a cluster's compute units or replicas (changes the bill); drop a cluster (recycle bin for 30 days, free clusters excepted); back up a cluster or some of its collections (storage is billed); delete a backup; restore a backup to a new cluster (a new billed cluster); create an alert rule that emails named members or roles; delete an alert rule; load a collection into memory; release a collection from memory; drop a collection and all its data. 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.
API key. In the Zilliz Cloud console, open API Keys and use your personal key or create a customised one. Project Read-Only reads, Read-Write or Admin covers the actions, and Project Admin covers alert rules.
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
