Skip to main content
Glama
ai-integr8tor

mcp-server-qdrant

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
QDRANT_URLNoURL of the Qdrant server (e.g., http://localhost:6333)
QDRANT_API_KEYNoAPI key for the Qdrant server
COLLECTION_NAMENoName of the default collection to use
EMBEDDING_MODELNoName of the embedding model to usesentence-transformers/all-MiniLM-L6-v2
QDRANT_READ_ONLYNoEnable read-only mode (disables qdrant-store tool)false
QDRANT_LOCAL_PATHNoPath to the local Qdrant database (alternative to QDRANT_URL)
EMBEDDING_PROVIDERNoEmbedding provider to use (currently only 'fastembed' is supported)fastembed
QDRANT_SEARCH_LIMITNoMaximum number of results to return from search10

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
qdrant-findA

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

qdrant-storeB

Keep the memory for later use, when you are asked to remember something.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: qdrant-find for retrieval and qdrant-store for storage. There is no ambiguity between them.

Naming Consistency5/5

Both tool names follow a consistent pattern with the 'qdrant-' prefix followed by a clear verb ('find', 'store'), making them predictable and easy to understand.

Tool Count4/5

With only 2 tools, the server is minimal but it covers the core operations of storing and retrieving memories. It could benefit from additional tools like delete, but the count is appropriate for a simple memory store.

Completeness3/5

The server lacks update and delete operations, which are notable gaps for memory management. While store and find cover basic needs, agents may require more functionality for complete lifecycle management.

Maintenance

ActivityInactive
ResponsivenessNo issues