Collections and objects of Weaviate and Weaviate Cloud: filtered pages, vector, BM25 and hybrid search through GraphQL. Upserts and deletes wait for approval.
The screenshots show GateRook 2.0.0: the Weaviate 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 Weaviate, choose its card and select Continue to configure.
Find the REST endpoint of your Weaviate deployment and prepare an API key for an identity allowed to read the required collections.
Use the exact collection names; Weaviate collection names begin with a capital letter. A remote connection needs HTTPS.
Enter a Name, for example weaviate-demo. Your AI app uses this name to choose the connection.
Enter Server URL and limit Collections, for example to Product. Include the port if your deployment requires it.
Select API key under Authentication and enter the key. Use No authentication only for a development deployment intentionally configured without it.
Enter a private CA certificate (PEM) under Advanced only if the deployment uses its own certificate authority.
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 authentication succeeds but collection access fails, check the identity’s authorization role. For vector queries, inspect the collection’s vector configuration first and use the configured vector name and dimensions.
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 Weaviate on the endpoint and passing its connection test, ask your AI app to use weaviate-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 weaviate-demo.”
- “Describe the properties and vector configuration of Product on weaviate-demo.”
- “Using weaviate-demo, fetch the Product object with the UUID I provide.”
| Tool | What it does | Starts as |
|---|---|---|
vector_list_collections | List the permitted Weaviate collections. | Read only |
vector_describe_collection | Show collection properties, vectorizer or named-vector configuration, supported text search, tenants and available object count. | Read only |
vector_get | Read objects by UUID or a bounded metadata-filter page, with a tenant when the collection uses multi-tenancy. Include vectors only when requested. | Read only |
vector_query | Search by vector or stored object UUID, or use text keyword search. Semantic and hybrid text search require a configured vectorizer; choose a target vector 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.