Collections and documents of Typesense and Typesense Cloud: typo-tolerant search with filters, facets and sorting. Document writes and deletes wait for approval.
The screenshots show GateRook 2.0.0: the Typesense 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 Typesense, choose its card and select Continue to configure.
Find the Typesense server or cluster endpoint and prepare a scoped API key.
For the read tools, a key can be limited to documents:search, documents:get and collections:get on the intended collections. Keep indexing and deletion permissions out of a search-only key.
Enter a Name, for example typesense-demo. Your AI app uses this name to choose the connection.
Enter Server URL including https:// for a remote deployment and the required port. Supply API key.
Restrict Collections to the exact collection names or deliberate patterns. 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.
For a denied operation, check the key’s action list and collection scope. Searches need field names from the collection schema, so inspect the collection before choosing the fields to search.
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 Typesense on the endpoint and passing its connection test, ask your AI app to use typesense-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 typesense-demo.”
- “Describe the products collection on typesense-demo.”
- “Using typesense-demo, search products for wireless headphones in its title field and return five matches.”
| Tool | What it does | Starts as |
|---|---|---|
search_list_indexes | List the permitted Typesense collections and available document counts. | Read only |
search_describe_index | Show collection fields and their types, facet and sort settings, default sorting field and vector fields. | Read only |
search_query | Search text fields with filters, facets, sorting and pagination, or query a configured vector field. Specify the search or vector field when the collection configuration requires it. | Read only |
search_get_documents | Documents by id, up to 100. | Read only |
search_index_documents | Adds or replaces up to 100 documents of one index, or merges their fields into existing ones. You approve the exact documents. Never retried. | Approval |
search_delete_documents | Deletes documents by id, up to 1,000 of one index. 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.