Collections and entities of Milvus and Zilliz Cloud: filtered pages, vector and full-text search. Upserts and deletes wait for approval.
The screenshots show GateRook 2.0.0: the Milvus 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 Milvus, choose its card and select Continue to configure.
Obtain the Milvus endpoint, database name and authentication details. A self-managed server commonly exposes its API on port 19530.
Use an identity with read privileges on the intended collections. The connector also accepts a managed Zilliz Cloud endpoint and token, covered in its own guide.
Enter a Name, for example milvus-demo. Your AI app uses this name to choose the connection.
Enter Server URL and Database, commonly default. Restrict Collections to the collection names or patterns the AI may use.
Select Username and password when Milvus authorization is enabled, then fill those fields. Select API key or token (Zilliz Cloud) for a managed token, or No authentication only for an intentionally unauthenticated development server.
For a private CA, add CA certificate (PEM) under Advanced.
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.
Check the database name and the user’s collection privileges if the server responds but no collections are visible. A search also needs a collection that is loaded and a query vector matching its vector field.
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 Milvus on the endpoint and passing its connection test, ask your AI app to use milvus-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 collections in milvus-demo.”
- “Describe the fields and indexes of products on milvus-demo.”
- “Using milvus-demo, fetch the record whose primary key is 123 from products.”
| 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.