← All integrations

Qdrant MCP server

29 operations0 webhooks

Vector search engine for semantic, hybrid and filtered search over embeddings, self-hosted or on Qdrant Cloud.

Try Qdrant with your agent

Connect Qdrant, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in Qdrant on my account, then run one read-only example and show me the result.

Runs once, when you ask

Qdrant tools and triggers

Tools are what your agent can do in Qdrant through Corsair's MCP server. Triggers are the Qdrant events a routine can start from.

Points

  • Clear PayloadDestructive

    Remove every payload key from points selected by ID list or filter

    points.clearPayload

  • CountRead-only

    Count the points that match a filter, exactly or approximately

    points.count

  • DeleteDestructive

    Delete points selected by ID list or by filter

    points.delete

  • Delete PayloadDestructive

    Remove specific payload keys from points selected by ID list or filter

    points.deletePayload

  • Delete VectorsDestructive

    Remove named vectors from points selected by ID list or filter

    points.deleteVectors

  • GetRead-only

    Retrieve points by ID, optionally with their payloads and vectors

    points.get

  • Overwrite PayloadDestructive

    Replace the whole payload of points selected by ID list or filter

    points.overwritePayload

  • ScrollRead-only

    Page through points matching a filter. Pass next_page_offset back as offset to get the next page

    points.scroll

  • Set PayloadWrite

    Merge payload keys into points selected by ID list or filter, optionally under a nested key

    points.setPayload

  • Update VectorsWrite

    Replace specific named vectors on existing points, keeping the others

    points.updateVectors

  • UpsertWrite

    Insert or replace points with their vectors and payloads, waiting for the write by default

    points.upsert

Collections

  • CreateWrite

    Create a collection with dense, sparse or named vector configs, sharding and index settings

    collections.create

Connect Qdrant to Claude, ChatGPT or Cursor

  1. 1

    Connect Qdrant in Corsair

    Add your Qdrant API key once in Corsair. Corsair stores the credential encrypted and makes the Qdrant API calls for your agent, so it never goes into a prompt or a config file. Connect Qdrant

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Qdrant. On a ChatGPT personal plan, connect Qdrant here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Qdrant's read and write operations run right away and its 8 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/qdrant, add the Qdrant plugin, and connect with an API key. Then call methods like corsair.qdrant.api.aliases.list() from your app. Corsair keeps each tenant isolated.

Yes. Qdrant requires an API key from your Qdrant account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit Qdrant, GitHub, Notion, Stripe, and the rest. Trigger Qdrant from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for vector search engine for semantic, hybrid and filtered search over embeddings, self-hosted or on qdrant cloud. Common builds include sync jobs, admin tooling, and agents that call Qdrant APIs from your backend.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Qdrant API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/qdrant in the open repo. When Qdrant ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your Qdrant data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Qdrant data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put Qdrant on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 8 destructive Qdrant operations. You can change a link's mode at hub.corsair.dev/me.