Better Qdrant MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QDRANT_URL | No | The URL of the Qdrant server | http://localhost:6333 |
| OLLAMA_MODEL | No | The Ollama model to use for embeddings | nomic-embed-text |
| OPENAI_API_KEY | No | Your OpenAI API key for using OpenAI embedding models | |
| QDRANT_API_KEY | No | Your Qdrant API key if authentication is needed | |
| OLLAMA_ENDPOINT | No | The Ollama API endpoint for local embedding models | http://localhost:11434 |
| OPENAI_ENDPOINT | No | The OpenAI API endpoint | https://api.openai.com/v1 |
| OPENROUTER_API_KEY | No | Your OpenRouter API key for using OpenRouter embedding models | |
| OPENROUTER_ENDPOINT | No | The OpenRouter API endpoint | https://api.openrouter.com/v1 |
| DEFAULT_EMBEDDING_SERVICE | No | The default embedding service to use (openai, openrouter, ollama, or fastembed) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_collectionsB | List all available Qdrant collections |
| add_documentsC | Add documents to a Qdrant collection with specified embedding service |
| searchC | Search for similar documents in a collection |
| delete_collectionC | Delete a Qdrant collection |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: add_documents handles document insertion, delete_collection removes collections, list_collections enumerates them, and search performs similarity queries. There is no overlap in functionality, making tool selection straightforward.
All tools follow a consistent verb_noun pattern (add_documents, delete_collection, list_collections, search). The naming is uniform and predictable, with no deviations in style or convention.
With only 4 tools, the set feels thin for a vector database server, lacking operations like collection creation, document updates, or deletion. While the tools cover basic CRUD aspects, the scope is limited and may require workarounds for full functionality.
There are significant gaps in the tool surface for a Qdrant server: no create_collection tool, no update or delete document operations, and no management of embeddings or configurations. This incomplete coverage will likely cause agent failures in common workflows.