qdrant-find
Look up memories in Qdrant. Use this tool when you need to:
- Find memories by their content
- Access memories for further analysis
- Get some personal information about the user
LABSCO SUMMARY
An agent gets somewhere to put things and a way to find them again.
Two calls over one collection: text goes in with whatever metadata you attach and comes back on a described query rather than an exact match. The tool descriptions being configurable is what makes it more than a note store — rewrite them and the same pair becomes the snippet library, the decision log, or whatever else you want the agent to reach for.
What it is
Qdrant's own two-call MCP server. One call writes a piece of text, with optional metadata, into a named collection; the other searches that collection in natural language. Embeddings are produced locally by FastEmbed, so no embedding key is involved.
What you get
- An entry stored in the collection you name, with whatever metadata you attach to it
- A natural-language search over one collection, returning the stored entries that match
- A default collection through COLLECTION_NAME, which drops the collection argument from both calls
- Both tool descriptions rewritable through TOOL_STORE_DESCRIPTION and TOOL_FIND_DESCRIPTION, which is how the same two calls become a code-snippet store rather than a note store
- The result count capped by QDRANT_SEARCH_LIMIT, 10 by default
- A read-only mode: QDRANT_READ_ONLY removes qdrant-store and leaves the search
- Stdio by default, with --transport for SSE or streamable HTTP when the client connects over the network
Requirements
uv, to run uvx mcp-server-qdrant, and somewhere to put the vectors: QDRANT_URL for a running Qdrant, with QDRANT_API_KEY for a managed one, or QDRANT_LOCAL_PATH for an on-disk database. Set one or the other — both together is rejected. EMBEDDING_MODEL defaults to sentence-transformers/all-MiniLM-L6-v2 and only FastEmbed models are supported, so a collection made elsewhere has to match that model's vectors.
Setup effort
One command — uvx mcp-server-qdrant
USE CASES
01
Keeping notes an agent can find later
Write the note when it appears, retrieve it later by describing what it was about rather than remembering how it was worded.
02
Looking something up when you only remember what it was about
The query is a description, not a keyword, so an entry filed under different wording still comes back.
03
Turning the pair into a code-snippet library
Rewrite the two tool descriptions so the text field carries what the code does and the metadata carries the code itself.
04
Letting an agent read a collection it must not change
Start with QDRANT_READ_ONLY set — the store tool is gone from the list, search remains.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
qdrant-store
Keep the memory for later use, when you are asked to remember something.
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected. Setting QDRANT_READ_ONLY disables qdrant-store, leaving only qdrant-find. Both names use hyphens, not underscores.
Requires
uvx on PATH
Optional
QDRANT_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-server-qdrantMCP Clients
Claude Desktop — uvx
CLAUDE DESKTOP — UVX · JSON
{
"mcpServers": {
"qdrant": {
"command": "uvx",
"args": [
"mcp-server-qdrant"
],
"env": {
"QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
"QDRANT_API_KEY": "<YOUR_QDRANT_API_KEY>",
"COLLECTION_NAME": "<YOUR_COLLECTION_NAME>",
"EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
}
}
}
}Claude Code
CLAUDE CODE · TERMINAL
claude mcp add code-search -e QDRANT_URL="http://localhost:6333" -e COLLECTION_NAME="code-repository" -e EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" -- uvx mcp-server-qdrantVS Code
VS CODE · JSON
{
"inputs": [
{
"type": "promptString",
"id": "qdrantUrl",
"description": "Qdrant URL"
},
{
"type": "promptString",
"id": "qdrantApiKey",
"description": "Qdrant API Key",
"password": true
},
{
"type": "promptString",
"id": "collectionName",
"description": "Collection Name"
}
],
"servers": {
"qdrant": {
"command": "uvx",
"args": [
"mcp-server-qdrant"
],
"env": {
"QDRANT_URL": "${input:qdrantUrl}",
"QDRANT_API_KEY": "${input:qdrantApiKey}",
"COLLECTION_NAME": "${input:collectionName}"
}
}
}
}
