Qdrant MCP — Cas d'usage, Installer & Démo en direct

Name: Qdrant MCP Server
Author: qdrant

Pourquoi l'utiliser

Fonctionnalités clés

Two-tool minimal surface — store text, find text; no schema gymnastics
Embedding model runs locally via fastembed by default (no extra API key)
Works with Qdrant Cloud or any self-hosted instance via QDRANT_URL
Metadata stored alongside each entry for filterable recall
Ideal building block for agent memory and lightweight RAG

Démo en direct

Aperçu en pratique

qdrant.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "qdrant": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "qdrant",
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

{
  "context_servers": {
    "qdrant": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-server-qdrant"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add qdrant -- uvx mcp-server-qdrant

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : Qdrant

Give a Claude agent persistent memory across sessions

👤 Builders making personal assistants or internal copilots ⏱ ~15 min beginner

Quand l'utiliser : You want Claude to remember user preferences, past decisions, or ongoing projects even after the chat ends.

Prérequis

Running Qdrant (local Docker or cloud) — docker run -p 6333:6333 qdrant/qdrant OR a Qdrant Cloud cluster URL + API key
COLLECTION_NAME env var set — Any string, e.g. claude_memory

Déroulement

Teach it to store important facts

Whenever I tell you something important about a project (deadlines, stakeholders, decisions), store it with qdrant-store, metadata {project, category}.✓ Copié

→ Claude starts echoing 'stored' for durable facts
Verify recall works

What do you remember about project 'atlas'? Use qdrant-find with a query like 'project atlas decisions'.✓ Copié

→ Relevant prior messages returned with scores
Curate and forget

Search for anything about project 'atlas' that's more than 90 days old or marked obsolete, and delete those entries.✓ Copié

→ List of pruned items with confirmation

Résultat : An assistant that actually remembers what you told it last week — scoped per-project, prunable.

Pièges

Storing every message bloats the collection and degrades recall quality — Only store explicit facts/decisions, not chit-chat. Make the 'store or not' decision part of the system prompt.
Collection created with wrong vector size after switching embedding models — Qdrant rejects mismatched vectors — drop and recreate the collection when you change EMBEDDING_MODEL

Combiner avec : filesystem · notion

Build a lightweight RAG over a docs folder

👤 Devs who want RAG without a framework ⏱ ~30 min intermediate

Quand l'utiliser : You have 50–5000 Markdown files and want Claude to answer questions against them, with citations.

Prérequis

Docs on disk as Markdown — Any folder of .md files

Déroulement

Chunk and store the docs

Read every .md under /docs. Split into ~500-token chunks on heading boundaries. For each chunk, call qdrant-store with the text and metadata {source_path, heading}.✓ Copié

→ N chunks stored, one per section
Query with a user question

User asks: 'How do I rotate API keys?' Use qdrant-find to pull the top 5 most relevant chunks. Cite source_path in your answer.✓ Copié

→ Answer with inline [source_path] citations
Measure retrieval quality

For these 10 eval questions [list], which of the expected source paths appear in the top-5 retrieval? Report recall@5.✓ Copié

→ A retrieval-quality score you can improve iteratively

Résultat : A working RAG loop you can tune chunk size and k until quality is acceptable.

Pièges

Too-large chunks dilute the embedding and kill recall — Keep chunks under ~1000 tokens; split by headings first, then by token count as a fallback
Updating a doc doesn't remove old chunks — answers become stale — Use a deterministic point id (hash of source_path+heading) so upserts replace rather than duplicate

Combiner avec : filesystem · firecrawl

Deduplicate a messy list of tickets, leads, or FAQs semantically

👤 Ops teams with a CSV of near-duplicates ⏱ ~25 min intermediate

Quand l'utiliser : Exact-match dedup misses things like 'reset password' vs 'how do I change my password' — you need semantic similarity.

Déroulement

Store each item with its row id as metadata

Read rows.csv. For each row, qdrant-store with information=<text> and metadata={row_id: <id>}.✓ Copié

→ N points stored
Cluster by similarity

For each row, query qdrant-find for its top-5 neighbors with score > 0.85. Output groups of row_ids that are mutually near.✓ Copié

→ Duplicate groups printed
Pick canonical + mark rest as duplicates

For each group, pick the longest/most-informative row as canonical. Output a CSV {row_id, canonical_id}.✓ Copié

→ Dedup map ready for the source system

Résultat : A dedup mapping CSV with confidence scores, reviewable by a human before applying.

Pièges

Similarity threshold is domain-specific — 0.85 may be too lenient or too strict — Hand-label 20 pairs first, then pick the threshold that best separates dup from non-dup

Combiner avec : postgres · filesystem

Searchable meeting-notes memory

👤 Managers / ICs drowning in Notion/Obsidian notes ⏱ ~20 min beginner

Quand l'utiliser : You take weekly notes but can never find the one where a specific decision was made.

Prérequis

Folder of meeting notes — Any text or markdown files

Déroulement

Index existing notes

Walk /meetings/**/*.md. For each, qdrant-store the body with metadata {date, attendees, project}.✓ Copié

→ All notes indexed with dates
Recall decisions

Find every note where we discussed 'pricing for enterprise tier'. Show me the date and a 2-line summary of each.✓ Copié

→ Ranked list of matching meetings
Keep it fresh

Add today's note <paste>, then tell me which past notes most likely contradict or update decisions in today's.✓ Copié

→ Contradiction check via semantic neighbors

Résultat : A semantic index over your notes you can keep updating weekly.

Pièges

Mixing personal + work notes in one collection leaks scope — Use separate collections or enforce a scope metadata filter on every find

Combiner avec : filesystem · notion

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

qdrant + filesystem

Index a local docs folder then answer questions with citations

Index every .md under /docs into Qdrant, then answer: 'how does our auth flow work?' with citations to the original file paths.✓ Copié

qdrant + firecrawl

Crawl a site and build a searchable knowledge base

Crawl docs.mycompany.com with Firecrawl, store each page in Qdrant collection company_docs.✓ Copié

qdrant + postgres

Semantic search over unstructured columns in a relational DB

SELECT id, body FROM support_tickets created in the last 30 days, embed each body into Qdrant with metadata {ticket_id}, then let me search them by meaning.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
qdrant-store	information: str, metadata?: object	Persist a fact, chunk, or note for later semantic recall	free (local embedding)
qdrant-find	query: str, limit?: int	Retrieve semantically similar entries to answer a question or deduplicate	free

Coût et limites

Coût d'exécution

Quota d'API: Self-hosted: unlimited. Qdrant Cloud: depends on cluster size.
Tokens par appel: Store: ~100 tokens overhead per call. Find: ~200 tokens + result payload.
Monétaire: Free if self-hosted. Qdrant Cloud free tier: 1GB cluster. Paid from ~$25/mo.
Astuce: Start with local Docker for dev; upgrade to Cloud only when you need persistence and multi-device access.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : QDRANT_URL and optional QDRANT_API_KEY in env vars

Sortie de données : If self-hosted: none. If Qdrant Cloud: all vectors and metadata sent to your cluster region.

Embeddings can be reversed enough to recover approximate text — treat the collection as sensitive as the source data.
Set COLLECTION_NAME per tenant if hosting a multi-user agent.

Dépannage

Erreurs courantes et correctifs

Collection does not exist / Not found

The server creates the collection on first store only if COLLECTION_NAME is set. Verify the env var and restart the MCP.

Vérifier : curl $QDRANT_URL/collections

Vector dimension mismatch

You changed EMBEDDING_MODEL without dropping the old collection. Drop it and start fresh (or use a new COLLECTION_NAME).

Vérifier : curl $QDRANT_URL/collections/<name>

Connection refused on localhost:6333

Qdrant container isn't running. docker run -p 6333:6333 qdrant/qdrant and retry.

Vérifier : curl localhost:6333/healthz

Searches return irrelevant results

Chunks may be too big or the embedding model too weak. Try FastEmbed's bge-small-en-v1.5 and chunks ≤500 tokens.

Alternatives

Qdrant vs autres

Alternative	Quand l'utiliser	Compromis
Chroma MCP	You prefer an embedded vector DB with zero infra	Less production-grade than Qdrant for heavy loads
Pinecone MCP	You're already on Pinecone and want hosted-only	Paid from day one; more opinionated
Memory MCP	You want ultra-simple key-value memory, not semantic	No embeddings — exact recall only

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills