Qdrant MemoryBLOCK
MCP server providing a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@delorenj/mcp-qdrant-memory)
This MCP server provides a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database.
Features
- Graph-based knowledge representation with entities and relations
- File-based persistence (memory.json)
- Semantic search using Qdrant vector database
- OpenAI embeddings for semantic similarity
- HTTPS support with reverse proxy compatibility
- Docker support for easy deployment
Environment Variables
The following environment variables are required:
# OpenAI API key for generating embeddings OPENAI_API_KEY=your-openai-api-key # Qdrant server URL (supports both HTTP and HTTPS) QDRANT_URL=https://your-qdrant-server # Qdrant API key (if authentication is enabled) QDRANT_API_KEY=your-qdrant-api-key # Name of the Qdrant collection to use QDRANT_COLLECTION_NAME=your-collection-name
Setup
Local Setup
- Install dependencies:
npm install
- Build the server:
npm run build
Docker Setup
- Build the Docker image:
docker build -t mcp-qdrant-memory .
- Run the Docker container with required environment variables:
docker run -d \ -e OPENAI_API_KEY=your-openai-api-key \ -e QDRANT_URL=http://your-qdrant-server:6333 \ -e QDRANT_COLLECTION_NAME=your-collection-name \ -e QDRANT_API_KEY=your-qdrant-api-key \ --name mcp-qdrant-memory \ mcp-qdrant-memory
Add to MCP settings:
{
"mcpServers": {
"memory": {
"command": "/bin/zsh",
"args": ["-c", "cd /path/to/server && node dist/index.js"],
"env": {
"OPENAI_API_KEY": "your-openai-api-key",
"QDRANT_API_KEY": "your-qdrant-api-key",
"QDRANT_URL": "http://your-qdrant-server:6333",
"QDRANT_COLLECTION_NAME": "your-collection-name"
},
"alwaysAllow": [
fc91f8320358OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-qdrant-memory --env OPENAI_API_KEY=${OPENAI_API_KEY} --env QDRANT_API_KEY=${QDRANT_API_KEY} -- npx -y @delorenj/[email protected]{
"mcpServers": {
"mcp-qdrant-memory": {
"command": "npx",
"args": [
"-y",
"@delorenj/[email protected]"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"QDRANT_API_KEY": "${QDRANT_API_KEY}"
}
}
}
}Exposed tools (8)
2 read · 3 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_observations | write | Add new observations to existing entities |
create_entities | write | Create multiple new entities in the knowledge graph |
create_relations | write | Create multiple new relations between entities |
delete_entities | destructive | Delete multiple entities and their relations |
delete_observations | destructive | Delete specific observations from entities |
delete_relations | destructive | Delete multiple relations |
read_graph | read | Read the entire knowledge graph |
search_similar | read | Search for similar entities and relations using semantic search |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (7)
rejectUnauthorized: false,
rejectUnauthorized: false
rejectUnauthorized: false
apiKey: 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhY2Nlc3MiOiJtIn0.x6NrWBMMtPqcep5dNxOqjXT42sQhATAMdxEqVFDJKew',
delete_entities, delete_observations, delete_relations
@modelcontextprotocol/sdk, @qdrant/js-client-rest, axios, dotenv, openai, @types/dotenv, @types/node, shx
Gates applied: no_behavioural_pass, no_license.
fc91f8320358full audit observations/trust-audit/mcp-server/delorenj__qdrant-memory.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | fc91f8320358 | BLOCK | D | 69 | first audit |
Questions
What is the Qdrant Memory MCP server?
MCP server providing a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database
What tools does Qdrant Memory expose?
8 in total: 2 read-only, 3 that write, and 3 that can delete or overwrite (delete_entities, delete_observations, delete_relations). Every one is listed on this page with its risk.
Is Qdrant Memory safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Qdrant Memory need?
It reads OPENAI_API_KEY and QDRANT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Qdrant Memory run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @delorenj/mcp-qdrant-memory at 0.2.4.
How current is this page?
The grade is for one exact copy of the source (fc91f8320358), read on 2026-10-09. The repository is watched and re-audited when it changes.