Indexes and records of Pinecone: metadata-filtered fetches, nearest-neighbour search by vector, record or text with integrated embedding. Upserts and deletes wait for approval.
The screenshots show GateRook 2.0.0: the Pinecone 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 Pinecone, choose its card and select Continue to configure.
Choose the Pinecone project containing the indexes you want the AI to inspect. Create a project API key with the necessary read permissions.
Index discovery and vector reads need different permissions. A key with ControlPlaneViewer and DataPlaneViewer can discover and read indexes; write access is unnecessary for a search-only setup.
Enter a Name, for example pinecone-demo. Your AI app uses this name to choose the connection.
Enter the project’s API key. GateRook stores it encrypted and discovers the project’s indexes.
Limit Indexes to the intended index names or patterns. An empty list includes every index visible to the key.
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 indexes cannot be listed, check the key’s project and control-plane permissions. If discovery works but vector reads fail, check data-plane permissions and the index or namespace named in the request.
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 Pinecone on the endpoint and passing its connection test, ask your AI app to use pinecone-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 indexes available through pinecone-demo.”
- “Describe the dimensions and metric of the products index on pinecone-demo.”
- “Using pinecone-demo, fetch the vector record with ID product-123 from the products index.”
| Tool | What it does | Starts as |
|---|---|---|
vector_list_collections | List the permitted Pinecone indexes with the metadata available from the control API. | Read only |
vector_describe_collection | Show one index’s dimension, metric, status, integrated embedding configuration when present, record count and namespace counts. | Read only |
vector_get | Fetch records by ID in one namespace. Metadata-filtered fetch and unfiltered listing depend on the index API; unfiltered listing uses the serverless list API. Include vectors only when requested. | Read only |
vector_query | Find nearest records using a vector or stored record ID. Text queries require an index with integrated embedding; metadata filters and topK bound the result. | Read only |
vector_upsert | Upsert up to 100 records with vectors, or up to 96 text records in an index with integrated embedding. Reusing an ID replaces its record. Approval is required; writes are not 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.