Community MCP server for Qdrant open-source vector database. Agents can create and manage collections, upsert points with payloads, perform filtered vector similarity searches, manage collection aliases, and retrieve collection statistics. Open-source and self-hostable. Ideal for privacy-sensitive RAG applications and custom embedding-based search systems.
npx -y @qdrant/mcp-server-qdrant
{
"mcpServers": {
"qdrant": {
"env": {
"QDRANT_URL": "http://localhost:6333",
"QDRANT_API_KEY": "your-api-key"
},
"args": [
"-y",
"@qdrant/mcp-server-qdrant"
],
"command": "npx"
}
}
}Search Qdrant collection
{
"type": "object",
"required": [
"collection",
"vector"
],
"properties": {
"limit": {
"type": "integer"
},
"vector": {
"type": "array"
},
"collection": {
"type": "string"
}
}
}// Input
{
"limit": 5,
"vector": [
0.1,
0.2
],
"collection": "docs"
}// Output
{
"result": [
{
"id": "p1",
"score": 0.92
}
]
}Upsert Qdrant points
{
"type": "object",
"required": [
"collection",
"points"
],
"properties": {
"points": {
"type": "array"
},
"collection": {
"type": "string"
}
}
}// Input
{
"points": [
{
"id": "p1",
"vector": [
0.1,
0.2
]
}
],
"collection": "docs"
}// Output
{
"status": "ok"
}Community MCP server for Qdrant open-source vector database. Agents can create and manage collections, upsert points with payloads, perform filtered vector similarity searches, manage collection aliases, and retrieve collection statistics. Open-source and self-hostable. Ideal for privacy-sensitive RAG applications and custom embedding-based search systems.
Qdrant provides 2 tools including search_points, upsert_points.
Yes, Qdrant is completely free to use with no usage limits on the free tier.
You can install Qdrant using the following command: npx -y @qdrant/mcp-server-qdrant. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
Qdrant is listed under the AI & Machine Learning category in the AgentForge MCP registry.
Qdrant has a current uptime of 99.92% with an average response time of 20ms.
To connect Qdrant, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Qdrant's tools via the Model Context Protocol.