better-qdrant-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host for HTTP-based transports | 0.0.0.0 |
| MCP_PATH | No | Path for HTTP transports | /mcp |
| MCP_PORT | No | Port for HTTP-based transports | 8000 |
| QDRANT_URL | No | Qdrant server URL | http://localhost:6333 |
| MCP_TRANSPORT | No | MCP transport: stdio, sse, or streamable-http | stdio |
| OPENAI_API_KEY | No | OpenAI API key | |
| QDRANT_API_KEY | No | Optional Qdrant API key | |
| COLLECTION_NAME | No | Optional default collection name | |
| OPENAI_BASE_URL | No | Optional custom OpenAI base URL | |
| OPENAPI_API_KEY | No | Alternative environment variable for OpenAI API key (typo variant) | |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-small |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| store-knowledgeA | Store useful information or knowledge into the long-term knowledge base (Qdrant). This allows the agent to persist data that can be retrieved later or by other agents. Automatically embeds the text and returns the stored ID. |
| store-knowledge-bulkA | Store multiple pieces of information or knowledge into the long-term knowledge base (Qdrant) at once. This is more efficient than calling store-knowledge multiple times. Each item is automatically embedded and stored with a unique ID. |
| search-knowledgeA | Search for relevant information in the long-term knowledge base using semantic search. Use this to retrieve context, facts, or past interactions stored in Qdrant. |
| inspect-knowledge-baseA | Inspect the knowledge base configuration and view sample data. Useful for debugging collection settings or verifying stored content. |
| get-knowledge-by-idA | Retrieve specific knowledge items by their point IDs with full payload details. Use this to inspect complete information about stored items. Use the 'id' field returned from search-knowledge results. |
| delete-knowledgeA | Delete specific information from the knowledge base using point IDs. Use the 'id' field returned from search-knowledge results. |
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 6 tools
Each tool has a distinct purpose: individual store, batch store, semantic search, get by ID, delete, and inspect. No overlap or ambiguity between them.
Most tools follow a verb_knowledge pattern (store-knowledge, search-knowledge, delete-knowledge). store-knowledge-bulk is a minor deviation but still clear, and get-knowledge-by-id and inspect-knowledge-base are consistent with the verb_noun style.
Six tools is well-scoped for a knowledge base server, covering the essential operations without bloat. Each tool earns its place.
Covers create (single and bulk), read (search, get by ID), delete, and inspect. No explicit update operation, but knowledge entries can be re-created; this is a minor gap.