Qdrant MCP server

Connect Qdrant to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Qdrant MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the manage payload index tool in Qdrant
  • Use the manage snapshots tool in Qdrant
  • Use the manage payload tool in Qdrant
  • Use the recommend points tool in Qdrant
  • Use the create collection tool in Qdrant
  • Use the search points tool in Qdrant

Supported Tools

manage_payload_index

Manage Payload Index

Creates or deletes payload field indexes on a collection. Indexes improve filter performance during search. Supported field types: `keyword`, `integer`, `float`, `geo`, `text`, `bool`, `datetime`, `uuid`. Text indexes support tokenizer configuration.

manage_snapshots

Manage Snapshots

Creates, lists, downloads, deletes, or recovers snapshots. Snapshots contain collection data and configuration for backups or recovery. Full storage snapshots require a single-node deployment and are unavailable on Qdrant Cloud.

manage_payload

Manage Payload

Sets, overwrites, deletes, or clears payload data on points. Supports targeting points by IDs or filter conditions. Use **set** to merge new payload fields, **overwrite** to replace the entire payload, **deleteKeys** to remove specific keys, or **clear** to remove all payload data.

recommend_points

Recommend Points

Finds similar points based on positive and negative examples. Positive examples define what you're looking for; negative examples define what to avoid. Examples can be point IDs or raw vectors. Supports two strategies: `average_vector` (averages all examples) and `best_score` (evaluates each candidate against all examples).

create_collection

Create Collection

Creates a new Qdrant collection with specified vector parameters. Supports single unnamed vectors or multiple named vector spaces for multi-modal data (e.g., text + image embeddings). Configure distance metric, dimensionality, and optional HNSW/quantization settings.

search_points

Search Points

Performs vector similarity search using the universal query API. Finds the closest points to a query vector, with optional filtering, score thresholds, and support for named vector spaces. This is the primary search mechanism for semantic/neural search.

list_collections

List Collections

Lists all collections in the Qdrant cluster. Returns the name of each collection. Use this to discover available collections before performing operations on them.

get_points

Get Points

Retrieves specific points by their IDs from a collection. Returns the point payload and optionally the vector data. Use this to look up known points by ID.

delete_collection

Delete Collection

Permanently deletes a Qdrant collection and all its data. This action cannot be undone.

delete_points

Delete Points

Deletes points from a collection by IDs or by a filter condition. Use IDs for targeted deletion or filters for bulk removal based on payload conditions.

count_points

Count Points

Counts the number of points in a collection, optionally filtered by payload conditions. Supports both exact and approximate counting modes.

discover_points

Discover Points

Finds points similar to a target constrained by a context of positive/negative example pairs. Context pairs partition the vector space, guiding the search toward regions where positive examples overlap. Without a target, performs pure context-based exploration. Useful for controlled exploration beyond simple nearest-neighbor search.

upsert_points

Upsert Points

Inserts or updates points (vectors with optional JSON payloads) in a collection. Supports batch operations. Each point requires an ID (integer or UUID string) and a vector. Payloads can include any JSON data for filtering and retrieval.

scroll_points

Scroll Points

Iterates through points in a collection with pagination. Supports filtering by payload conditions. Returns points along with a pagination offset for fetching the next page. Useful for browsing, exporting, or processing all points in a collection.

manage_aliases

Manage Collection Aliases

Creates, deletes, or renames collection aliases. Aliases provide alternative names for collections, useful for versioning or A/B testing. Can also list existing aliases.

get_collection

Get Collection Info

Retrieves detailed information about a specific Qdrant collection, including its status, vector configuration, point count, indexed vectors count, and payload schema. Useful for inspecting collection health and configuration.

manage_clusters

Manage Cloud Clusters

Manages Qdrant Cloud clusters. List, get details, create, delete, restart, suspend, or unsuspend clusters. Requires a Cloud Management API key. Call list_accounts to discover account IDs and list_cloud_options to discover creation options.

update_collection

Update Collection

Updates Qdrant collection indexing, optimization, replication, or vector storage settings. Existing points remain in the collection. Call get_collection to inspect the current configuration.

list_cloud_options

List Cloud Cluster Options

Discovers cloud providers, regions, and resource packages available to a Qdrant Cloud account. Call list_accounts to choose an account, then discover providers, regions, and packages before creating a cluster.

list_accounts

List Cloud Accounts

Lists the Qdrant Cloud accounts accessible to the management key. Use the returned accountId in cloud cluster and configuration tools.

Connect Qdrant to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Qdrant in Metorial. In your Metorial portal, enable the Qdrant MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Qdrant tools.

Run Qdrant through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Qdrant and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Qdrant tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Qdrant

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Google Drive

Upload, download, create, copy, move, rename, trash, and permanently delete files and folders in Google Drive. Search for files using complex queries filtering by name, MIME type, owner, modification date, labels, and other metadata. Share files and folders with specific users, groups, or domains with role-based permissions (owner, writer, commenter, reader). Manage shared drives and their members. Export Google Workspace files (Docs, Sheets, Slides) to standard formats like PDF, DOCX, and XLSX. Track file revision history and restore earlier versions. Create, read, update, and delete threaded comments and replies on files. Read label definitions and search files by label. Browse the Drive apps installed for your account. Store app-specific data in a hidden per-user folder.

Technical notes for Qdrant

Manage vector collections, point data, JSON payloads, and cloud clusters in Qdrant. Run dense, sparse, hybrid, recommendation, and discovery queries. Configure collection indexes and optimization, manage aliases, and create downloadable snapshots or recover collections from backups.

Frequently asked questions

Common questions about connecting Qdrant to AI agents with Metorial.

  1. How many tools does the Qdrant MCP server have?
    The Qdrant MCP server exposes 20 tools, including Manage Payload Index, Manage Snapshots, Manage Payload. Each one is governed and traced through Metorial.
  2. Qdrant exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Qdrant MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Qdrant and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Qdrant MCP server yourself or use the hosted gateway.

Connect Qdrant to production AI agents

See how Metorial gives your team governed access to Qdrant, with tracing and security controls built in.