Chroma Cloud uses GateRook’s Chroma connector. An API key, your tenant's id and the database's name.
The screenshots show GateRook 2.0.0: the Chroma Cloud 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 Chroma Cloud, choose its card and select Continue to configure.
Open your Chroma Cloud database and copy its API key, tenant ID, database name and regional API endpoint. The tenant and database must identify the actual Cloud resource.
Use the endpoint for the database's region. The default https://api.trychroma.com address is not a substitute for a different regional endpoint shown in Cloud connection details.
Enter a Name, for example chroma-cloud-demo. Your AI app uses this name to choose the connection.
Fill Server URL with the regional API base. Set Tenant to your tenant ID and Database to the actual database name; do not retain local-development defaults unless those are the real values.
Select Token in X-Chroma-Token (Chroma Cloud) under Authentication and fill API key or token with the Cloud key.
Restrict Collections to the required collection names. Leave CA certificate (PEM) empty for a publicly trusted Cloud endpoint.
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 an unknown tenant or database, check all three coordinates: regional endpoint, tenant ID and database name. For an authorization error, verify the key's access to that database rather than switching to a local default tenant.
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 Chroma Cloud on the endpoint and passing its connection test, ask your AI app to use chroma-cloud-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 the selected Chroma Cloud database.”
- “Describe the metadata and configuration of one permitted collection.”
- “Get at most 10 records matching a metadata filter and omit embeddings from the answer.”
| Tool | What it does | Starts as |
|---|---|---|
vector_list_collections | List the permitted Chroma collections in the configured tenant and database. | Read only |
vector_describe_collection | Show a collection’s ID, tenant, database, available dimension and metric, collection metadata, embedding function name and record count. | Read only |
vector_get | Fetch records by text ID or read a bounded metadata-filter page, including stored documents. Include embeddings only when requested. | Read only |
vector_query | Find nearest records using an embedding vector or a stored record ID, with a metadata filter and topK limit. Text query 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.