Start free

Qdrant connector · Vector database reports

Read & reportRead-only source

Spot unhealthy Qdrant collections and indexing backlogs early.

Bring Qdrant collections and cluster status into your reports and AI assistants: each collection’s status, optimizer status, points and indexed vectors, vector settings and quantization, and the cluster’s Raft health.

  • Catch collections that aren’t green or have optimizer errors
  • Compare indexed vectors with points to see a backlog
  • Ask ChatGPT or Claude whether a new collection matches production
QdrantSheetsData StudioChatGPTClaude

Start free Explore the data

Updated November 2026

Qdrant reportSample data
Collection nameStatusPoints count
invoicesgreen1,284,310
vendorsyellow96,412
contractsgreen18,920
Refreshes on your schedule in Google Sheets

What Datapipe reads from a Qdrant cluster

A Qdrant cluster, in Qdrant Cloud or self-hosted, is the data source, with all collections or the one you pick. Reports show the cluster as it is when they run.

Collections

Read each collection’s status, optimizer status, points, indexed vectors, segments, shards and replication factor.

Vector settings

See vector names, dimension, distance, sparse vectors, payload indexes and quantization.

Cluster

Check Qdrant version, peers, Raft role, leader, term, pending operations and peers with send failures.

Pick a collection

Choose one collection from the list, or all of them, when you add Qdrant.

Report datasets and details

Reports you can build

2 reporting datasets, each with its own fields. Pick one in the app, then choose your columns.

  • Vector collections
  • Cluster status
What each dataset reports
  • Vector collections

    Each Qdrant collection with its health, point and indexed vector counts, segments, vector settings, shards and payload indexes.

  • Cluster status

    Qdrant server version, whether clustering is on, peers, this peer's Raft role, term, commit index and pending operations.

Metrics and dimensions

27 report fields across 2 datasets.

Search the available fields. Hover or tap a field to see what it means.

Send Qdrant data anywhere

Google SheetsGoogle SheetsA sheet that refreshes every morning.
Data StudioData StudioCharts that read the same numbers.
BigQueryBigQueryA warehouse table for the same columns.
ClickHouseClickHousePush rows into ClickHouse over HTTPS with an API key.
AWS S3AWS S3Write report files to your S3 bucket with IAM access keys.
Amazon RedshiftAmazon RedshiftLoad rows into Redshift via the Data API with IAM keys.
FireboltFireboltPush rows into Firebolt over HTTPS with a Service Account.
PostgreSQLPostgreSQLWrite report rows into PostgreSQL with database credentials.
MySQLMySQLWrite report rows into MySQL with database credentials.
SnowflakeSnowflakePush rows into Snowflake over HTTPS with a PAT token.
Databricks SQLDatabricks SQLLoad rows into Databricks SQL with a Personal Access Token.
Cloudflare R2Cloudflare R2Write report files to your R2 bucket with access keys.
Excel / CSVExcel / CSVA Drive file you can open in Excel.
ClaudeClaudeAdd Datapipe's MCP connector, then ask Claude in a sentence.
ChatGPTChatGPTAdd Datapipe's MCP connector, then ask ChatGPT in a sentence.
APIAPIRead the same rows from your own tool.
Don't see yours? Use CSV or APIDownload the rows, or read them from your own tool.

Connect Qdrant to ChatGPT or Claude for vector database questions

Using MCP, Claude can find Qdrant collections whose indexed vectors trail their points, and check whether the cluster leader changed.

Example

Which collections are not green, and how far behind is their indexing?

List collections whose status isn’t green with optimizer status, and subtract indexed vectors from points to show each backlog.

Set up the Qdrant MCP connector

Datapipe is a hosted MCP server. Add it once as a custom connector in Claude, ChatGPT or Grok, and your assistant can work with Qdrant alongside the other data sources in your project.

  1. Add QdrantAdd it as a data source in Datapipe.
  2. Add the connectorPaste https://trydatapipe.com/mcp as a custom connector in your assistant.
  3. Sign inSign in to Datapipe and choose the project your assistant can use.

Qdrant collections with status, optimizer status, points, indexed vectors, vector settings and quantization, plus cluster version, peers and Raft state. Qdrant is read-only in Datapipe.

Start with Qdrant

What you need

Your Qdrant cluster URL and a read-only database key from the cluster’s API Keys page. Self-hosted servers need a public https address.

What to know

Read-only. Qdrant Cloud keys expire after 90 days by default, and a key limited to some collections can’t read cluster status. Up to 20,000 rows per report.

How it works

  1. Create a read-only database key on your Qdrant cluster, then add Qdrant under Data sources.

  2. Enter your cluster URL and key, then pick a collection or all of them.

  3. Send collection status to a sheet each hour, or ask ChatGPT which collections are behind on indexing.

Works well with Qdrant

Add both to the same project. Each keeps its own report, so you can check them side by side or ask ChatGPT or Claude a question that needs both.

Questions

Collections with status, counts and vector settings, and cluster status with Raft details.

Yes, when the server has a public https address. Qdrant Cloud works too.

A read-only database key. Keys limited to some collections can’t read cluster status.

No. It reads counts, settings and status, never point vectors or payloads.

Yes. Datapipe is a hosted MCP server that covers Qdrant and the other data sources in your project. Add https://trydatapipe.com/mcp as a custom connector in Claude, ChatGPT or Grok, then sign in to Datapipe. Qdrant collections with status, optimizer status, points, indexed vectors, vector settings and quantization, plus cluster version, peers and Raft state. Qdrant is read-only in Datapipe.

Free to start. Paid plans add more data sources and refresh faster.

Free and Starter refresh once a day. Pro refreshes every hour. Agency refreshes every 15 minutes on the first 50 data sources.

One for each Qdrant account you add to a project. Adding the same account to another project counts again. Reports and destinations do not use extra data sources.

Keep vector search healthy.

Catch a yellow collection or a stuck optimizer before search results start missing.

Start free See setup requirements