Qdrant

Give the agent a small, explicit memory: text stored with its embedding in a Qdrant collection you choose, found again by meaning. Local Qdrant, local data.

What it can do

Examples of the tools the agent gets from this connector. Each call shows up in the activity feed with its input and result.

1. qdrantstore a note
2. qdrantfind by meaning
3. qdrantlist what is stored

How it connects

Sign-in

API key you provide. You paste an API key from Qdrant into the connector's settings. It is encrypted with the key in your OS keychain and never leaves your machine.

Runs as

MCP server run locally on your machine. An MCP server that runs as a local process on the Node or Python you already have. Gantry checks the runtime is present before installing.

Permissions

Reads run in every mode. Writes outside your folders, messages and anything destructive follow the chat's permission mode: they ask in Manual and Auto-edit, and are judged by the guard model in Auto. How permissions work

Install in Gantry

1. 1

   Open Connectors in the sidebar. The catalog ships with the app; nothing is downloaded until you ask.

2. 2

   Find Qdrant and choose Install. Paste your API key when asked.

3. 3

   Attach it to a chat, or leave it available to every chat in a project. The agent sees its tools from then on.