Qdrant MCP server

What the model can do

Qdrant vector database (self-hosted or Qdrant Cloud): collections with their size and payload schema, points' payloads read by id, scrolled, or counted under a filter (vectors never fetched), and snapshots; can upsert, re-label, clear or delete points by id, create and delete collections, take and delete snapshots, and create and delete payload indexes.

Reads

• qdrant_list_collectionsThe collections in Qdrant, by name.
• qdrant_get_collectionOne Qdrant collection: status, how many points and indexed vectors, segments, vector size and distance, and the payload schema…
• qdrant_scroll_pointsPoints in a Qdrant collection with their payloads (no vectors), optionally under a filter on payload keys…
• qdrant_count_pointsHow many points in a Qdrant collection match a payload filter (or all of them).
• qdrant_get_pointOne point in a Qdrant collection by id, with its payload (no vector).
• qdrant_list_snapshotsSnapshots of a Qdrant collection on the node: name, when taken, size in bytes.

Acts, when you ask

These change something in Qdrant. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• qdrant_upsert_pointsWrites points into a Qdrant collection by id, each with its vector (of the collection's size) and an optional payload.
• qdrant_set_payloadSets payload keys on points in a Qdrant collection, by id.
• qdrant_delete_pointsDeletes points from a Qdrant collection by id: their vectors and payloads are gone.
• qdrant_create_collectionCreates an empty Qdrant collection with its vector size and distance (or several named vectors).
• qdrant_delete_collectionDeletes a Qdrant collection with every point, vector and payload in it.
• qdrant_delete_payload_keysRemoves the named payload keys from points in a Qdrant collection, by id.
• qdrant_overwrite_payloadReplaces the WHOLE payload of points in a Qdrant collection, by id: every key not in the new payload is deleted.
• qdrant_clear_payloadRemoves every payload key from points in a Qdrant collection, by id; their vectors stay.
• qdrant_create_snapshotTakes a snapshot of a Qdrant collection on the node (a full copy for backup), using disk space there.
• qdrant_delete_snapshotDeletes one snapshot of a Qdrant collection from the node.
• qdrant_create_field_indexIndexes a payload field of a Qdrant collection so filters and ordering on it are fast.
• qdrant_delete_field_indexRemoves a payload field index from a Qdrant collection.

Connect it

First connect Qdrant on Dashboard → Connections, then add Memtro to your client once. The Qdrant tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Qdrant connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › How many points are in the support-articles collection?
• › Which payload keys are indexed in the products collection?
• › How many points have source set to confluence?
• › What is the payload of point 4812?
• › Take a snapshot of the docs collection, then delete points 101 and 102

Questions

Is this an official Qdrant MCP server?

No. It is Memtro's MCP server with Memtro's Qdrant connector behind it: the connector reads Qdrant through its API with the credentials you connect on Dashboard → Connections, and Qdrant publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Qdrant?

Only when you ask, and only what it has been granted: upsert points by id (replaces any point that already has the id); set payload keys on points by id (overwrites those keys); delete points by id; create a collection; delete a collection and all its points (permanent); remove payload keys from points by id; replace the whole payload of points by id; clear the payload of points by id; take a snapshot of a collection; delete a collection snapshot (permanent); index a payload field; remove a payload field index. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Databases and warehouses

• Postgres MCP server
• MySQL and MariaDB MCP server
• SQL Server MCP server
• BigQuery MCP server
• Snowflake MCP server
• AWS Athena MCP server