Collections and points of Qdrant and Qdrant Cloud: filtered pages, nearest-neighbour search by vector or point. Upserts and deletes wait for approval.
The screenshots show GateRook 2.0.0: the Qdrant 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 Qdrant, choose its card and select Continue to configure.
Obtain the Qdrant REST URL and a key for the collections you want to expose. This connector uses the REST interface, commonly on port 6333.
Use a read-only API key or a JWT limited to the intended collections for a search-only setup. An unauthenticated server is appropriate only where that access is intentional and the environment permits it.
Enter a Name, for example qdrant-demo. Your AI app uses this name to choose the connection.
Enter Server URL, including https:// for a remote server and the REST port if required. Enter collection names or patterns in Collections.
Choose API key under Authentication and enter API key. Use No authentication only when the actual server checks no key.
If the server uses a private CA, open Advanced and enter CA certificate (PEM).
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.
A connection to the gRPC port will not work as the REST endpoint. Check the URL, TLS certificate and key permissions if testing fails; use the collection’s exact name for subsequent requests.
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 Qdrant on the endpoint and passing its connection test, ask your AI app to use qdrant-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 available through qdrant-demo.”
- “Describe the vector configuration of the products collection on qdrant-demo.”
- “Using qdrant-demo, fetch point 123 from products without changing it.”
| Tool | What it does | Starts as |
|---|---|---|
vector_list_collections | List the permitted Qdrant collections. | Read only |
vector_describe_collection | Show a collection’s status, point count, vector dimensions and metrics, named and sparse vector configuration, and indexed payload fields. | Read only |
vector_get | Fetch points by unsigned integer or UUID ID, or scroll a bounded page using a payload filter. Include vectors only when requested. | Read only |
vector_query | Find nearest points using a vector or an existing point ID, with a payload filter and topK limit. Select a vector name when needed; text input is not supported by this connector. | 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.