Zilliz Cloud uses GateRook’s Milvus connector. Zilliz Cloud's managed Milvus: the cluster's public endpoint and an API key.
The screenshots show GateRook 2.0.0: the Zilliz Cloud form, the endpoint selector, and this connector’s actual tool preview. The form and preview have not been saved. Select a screenshot to open it at full size.
1. Create a connection and enter the settings
In GateRook, open Connections, select Add connection, search for Zilliz Cloud, choose its card and select Continue to configure.
Copy the public data endpoint of the Zilliz Cloud cluster and create an API key authorized to read the required database and collections.
Use the cluster data endpoint shown in its connection details. The Zilliz Cloud management API is a separate service and does not serve Milvus collection queries.
Enter a Name, for example zilliz-cloud-demo. Your AI app uses this name to choose the connection.
Enter the HTTPS cluster endpoint in Server URL and set Database to the intended database, using default only when that is where your collections live.
Set Authentication to API key or token (Zilliz Cloud) and paste the cluster-authorized key into API key or token.
Restrict Collections to the required collection names. Keep CA certificate (PEM) empty for a normally trusted public Zilliz endpoint.
Choose Development, Staging or Production to match the service. Review the connector’s limit and access settings before continuing.
2. Test the connection and add it to an endpoint
Select Continue to test. GateRook checks the settings from your computer. Review the result and resolve any connection, certificate or permission error before continuing.
If the endpoint is valid but a collection is missing, check Database, the key's permissions and collection availability. A management API URL or a key without data access cannot substitute for the cluster connection details.
After the test passes, select Continue to add to an endpoint. Choose the endpoint your AI app uses, review its tool modes, then select Save connection. GateRook offers default as the starter endpoint.
3. Use the connection from your AI IDE
After saving Zilliz Cloud on the endpoint and passing its connection test, ask your AI app to use zilliz-cloud-demo, or the name you chose. If its tools are missing, confirm the endpoint assignment and refresh the MCP connection or start a new chat.
The preview below shows this connector’s default tools before saving. The table explains what each tool can do; connection settings, credentials and endpoint policies can restrict access further.
Start with a small read request. Replace example resource names with existing resources your connection may access. Open Activity after the call to inspect its connection, tool, arguments, policy decision and result metadata.
Ask your AI, for example
- “List the permitted Zilliz collections and their schemas.”
- “Describe the vector dimension and scalar fields of one selected collection.”
- “Read at most 10 entities using a scalar filter, excluding vector values from the output.”
| Tool | What it does | Starts as |
|---|---|---|
vector_list_collections | List the permitted Milvus collections in the configured database. | Read only |
vector_describe_collection | Show a collection’s primary key, fields, vector indexes, embedding or BM25 functions, load state, partitions and available row count. | Read only |
vector_get | Read records by primary key or a bounded scalar-filter page, optionally within a partition. Include vectors only when requested. | Read only |
vector_query | Search by vector or stored record ID. Text search requires a compatible embedding or BM25 function in the collection; select the vector field when needed. | Read only |
vector_upsert | Writes up to 100 records to one collection; a record with an existing id replaces it. You approve the exact records. Never retried. | Approval |
vector_delete | Deletes records by id, up to 1,000 of one collection. You approve the exact ids; nothing else is deleted. Never retried. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.