# Qdrant MCP (pypi · mcp-qdrant)

MCP server that wraps the Qdrant vector database API as tools.

- Trust score: 58/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- pypi · `mcp-qdrant`: 58/100 (this document), [markdown](https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant.md), [page](https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant)

## Channel facts

- Registry: `pypi`
- Package: `mcp-qdrant`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 44/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs a script at install time (build_backend) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.
  - 1 of 40 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (MIT License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 20 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1576 tokens (~121/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Qdrant MCP server?

Qdrant MCP runs locally as a PyPI package, launched with uvx mcp-qdrant. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add avaazquezz-mcp-qdrant -- uvx mcp-qdrant
```

### Cursor

```json
{
  "mcpServers": {
    "avaazquezz-mcp-qdrant": {
      "command": "uvx",
      "args": [
        "mcp-qdrant"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "avaazquezz-mcp-qdrant": {
      "command": "uvx",
      "args": [
        "mcp-qdrant"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add avaazquezz-mcp-qdrant -- uvx mcp-qdrant
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "avaazquezz-mcp-qdrant": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-qdrant"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add avaazquezz-mcp-qdrant --command uvx --arg mcp-qdrant
```

### Hermes

```yaml
mcp_servers:
  avaazquezz-mcp-qdrant:
    command: "uvx"
    args: ["mcp-qdrant"]
```

### Netclaw

```json
{
  "McpServers": {
    "avaazquezz-mcp-qdrant": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-qdrant"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add avaazquezz-mcp-qdrant -t stdio -c uvx -a mcp-qdrant
```

### Other

```json
{
  "mcpServers": {
    "avaazquezz-mcp-qdrant": {
      "command": "uvx",
      "args": [
        "mcp-qdrant"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 57, −14)

- [security regression] Malware scan: pass → unverified

### 2026-09-15 (score 71, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 55, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-13 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 54, −14)

- [security regression] Malware scan: pass → unverified

### 2026-09-09 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `qdrant_health_check` (~79 tokens)

Confirm the configured Qdrant instance is reachable and responding.

Never raises to the caller: a health check that raises on the exact
condition it exists to detect defeats its own purpose. Connection
failures are logged and reported in the result's ok/error fields
instead, so a client renders them without a tool-call error round-trip.

Output parameters:

- `collection_count`
- `error`
- `ok` (boolean)

### `qdrant_collection_create` (~260 tokens)

Create a collection: either a single unnamed vector (`vector_size`
\+ `distance`), or one or more named vectors (`vectors`, each a full
\`VectorParams` — size, distance, and optionally its own
\`multivector_config` for ColBERT-style multi-vectors or
\`quantization_config`) — exactly one of the two. `sparse_vectors`
defines sparse (keyword-style) vectors at creation time.
\`quantization_config` (scalar/product/binary) and
\`strict_mode_config` apply to the whole collection.

Fails with a clear error if a collection with this name already exists.

Example (simple): {"collection_name": "docs", "vector_size": 4, "distance": "Cosine"}
Example (hybrid): {"collection_name": "docs", "vectors": {
    "dense": {"size": 4, "distance": "Cosine"}
}, "sparse_vectors": {"sparse": {}}}

Input parameters:

- `collection_name` (string, required)
- `distance` (string)
- `metadata`
- `quantization_config`
- `sparse_vectors`
- `strict_mode_config`
- `vector_size`
- `vectors`

Output parameters:

- `config`: Current statistics and configuration of the collection
- `indexed_vectors_count`: Approximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index.
- `optimizer_status`: Current statistics and configuration of the collection
- `payload_schema` (object): Types of stored payload
- `points_count`: Approximate number of points (vectors + payloads) in collection. Each point could be accessed by unique id.
- `segments_count` (integer): Number of segments in collection. Each segment has independent vector as payload indexes
- `status`: Current statistics and configuration of the collection
- `update_queue`: Update queue info
- `warnings`: Warnings related to the collection

### `qdrant_collection_list` (~26 tokens)

List every collection name in the configured Qdrant instance.

Example: {}

Output parameters:

- `collections` (array)

### `qdrant_collection_info` (~48 tokens)

Return full config and status of one collection.

Fails with a clear error if the collection doesn't exist.

Example: {"collection_name": "docs"}

Input parameters:

- `collection_name` (string, required)

Output parameters:

- `config`: Current statistics and configuration of the collection
- `indexed_vectors_count`: Approximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index.
- `optimizer_status`: Current statistics and configuration of the collection
- `payload_schema` (object): Types of stored payload
- `points_count`: Approximate number of points (vectors + payloads) in collection. Each point could be accessed by unique id.
- `segments_count` (integer): Number of segments in collection. Each segment has independent vector as payload indexes
- `status`: Current statistics and configuration of the collection
- `update_queue`: Update queue info
- `warnings`: Warnings related to the collection

### `qdrant_collection_update` (~215 tokens)

Update optimizer/HNSW/collection/vector params on an existing
collection.

Only the fields you pass are changed; omitted ones keep their current
value. `quantization_config="disabled"` turns quantization off.
\`vectors_config`/`sparse_vectors_config` only **adjust** named
vectors that already exist (HNSW/quantization/index tuning) — they
cannot add a new one; use `qdrant_collection_vector_create` for
that, or this fails with Qdrant's own "Not existing vector name"
error. Fails with a clear error if the collection doesn't exist.

Example: {"collection_name": "docs", "optimizers_config": {"indexing_threshold": 10000}}

Input parameters:

- `collection_name` (string, required)
- `collection_params`
- `hnsw_config`
- `optimizers_config`
- `quantization_config`
- `sparse_vectors_config`
- `strict_mode_config`
- `vectors_config`

Output parameters:

- `config`: Current statistics and configuration of the collection
- `indexed_vectors_count`: Approximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index.
- `optimizer_status`: Current statistics and configuration of the collection
- `payload_schema` (object): Types of stored payload
- `points_count`: Approximate number of points (vectors + payloads) in collection. Each point could be accessed by unique id.
- `segments_count` (integer): Number of segments in collection. Each segment has independent vector as payload indexes
- `status`: Current statistics and configuration of the collection
- `update_queue`: Update queue info
- `warnings`: Warnings related to the collection

### `qdrant_collection_delete` (~44 tokens)

Delete a collection and all its points; a no-op if it doesn't exist.

Example: {"collection_name": "docs"}

Input parameters:

- `collection_name` (string, required)

Output parameters:

- `deleted` (boolean)

### `qdrant_collection_exists` (~40 tokens)

Check whether a collection exists, without raising if it doesn't.

Example: {"collection_name": "docs"}

Input parameters:

- `collection_name` (string, required)

Output parameters:

- `exists` (boolean)

### `qdrant_points_upsert` (~108 tokens)

Insert or replace points (id + vector + payload) in a collection.

Fails with a clear error if the collection doesn't exist.

Example: {"collection_name": "docs", "points": [
    {"id": 1, "vector": [0.1, 0.2, 0.3, 0.4], "payload": {"city": "ny"}}
]}

Input parameters:

- `collection_name` (string, required)
- `points` (array, required)

Output parameters:

- `operation_id`: Sequential number of the operation
- `status`

### `qdrant_points_get` (~85 tokens)

Retrieve points by id; unknown ids are simply omitted, not an error.

Fails only if the collection itself doesn't exist.

Example: {"collection_name": "docs", "ids": [1, 2]}

Input parameters:

- `collection_name` (string, required)
- `ids` (array, required)
- `with_payload` (boolean)
- `with_vectors` (boolean)

Output parameters:

- `points` (array)

### `qdrant_points_delete` (~147 tokens)

Delete points by id list or by payload filter — exactly one of the two.

Deleting an id that doesn't exist is not an error (Qdrant treats it as
a no-op); this only fails if the collection itself is missing, or if
you provide zero or both selectors.

Example (by id): {"collection_name": "docs", "ids": [1, 2]}
Example (by filter): {"collection_name": "docs", "points_filter": {
    "must": [{"key": "city", "match": {"value": "ny"}}]
}}

Input parameters:

- `collection_name` (string, required)
- `ids`
- `points_filter`

Output parameters:

- `operation_id`: Sequential number of the operation
- `status`

### `qdrant_points_scroll` (~108 tokens)

Page through all points in a collection, optionally filtered.

Pass the returned `next_page_offset` as `offset` to fetch the next
page; `null` means there are no more pages.

Example: {"collection_name": "docs", "limit": 50}

Input parameters:

- `collection_name` (string, required)
- `limit` (integer)
- `offset`
- `scroll_filter`
- `with_payload` (boolean)
- `with_vectors` (boolean)

Output parameters:

- `next_page_offset`
- `points` (array)

### `qdrant_points_count` (~52 tokens)

Count points in a collection, optionally matching a filter.

Example: {"collection_name": "docs"}

Input parameters:

- `collection_name` (string, required)
- `count_filter`
- `exact` (boolean)

Output parameters:

- `count` (integer): Number of points which satisfy the conditions

### `qdrant_query` (~364 tokens)

Vector similarity search, with optional hybrid search over
multiple prefetch stages.

Pass `query_vector` (a literal vector, or a point id to reuse an
existing point's vector) for a plain nearest-vector query, or
\`fusion` + 2+ `prefetch` stages to combine multiple retrieval
strategies via Reciprocal Rank Fusion (`fusion="rrf"`) or
Distribution-Based Score Fusion (`fusion="dbsf"`) — exactly one of
\`query_vector`/`fusion` is required. `using` selects a named vector;
\`lookup_from` resolves `query_vector` from a point id in another
collection instead of the current one. Fails with a clear error if
the collection doesn't exist.

Example (plain): {"collection_name": "docs", "query_vector": [0.1, 0.2, 0.3, 0.4],
    "limit": 5}
Example (hybrid): {"collection_name": "docs", "fusion": "rrf", "prefetch": [
    {"query_vector": [0.1, 0.2, 0.3, 0.4], "using": "dense", "limit": 20},
    {"query_vector": [0.5, 0.5], "using": "sparse", "limit": 20}
], "limit": 5}

Input parameters:

- `collection_name` (string, required)
- `fusion`
- `limit` (integer)
- `lookup_from`
- `prefetch`
- `query_filter`
- `query_vector`
- `using`
- `with_payload` (boolean)
- `with_vectors` (boolean)

Output parameters:

- `points` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant#diagnostics

## Score history

- 2026-09-21: 58
- 2026-09-20: 58
- 2026-09-19: 57
- 2026-09-18: 57
- 2026-09-17: 57
- 2026-09-16: 71
- 2026-09-15: 71
- 2026-09-14: 55
- 2026-09-13: 70
- 2026-09-12: 69
- 2026-09-11: 54
- 2026-09-10: 68
- 2026-09-09: 68
- 2026-09-08: 67
- 2026-09-07: 64
- 2026-09-06: 64
- 2026-09-05: 64
- 2026-09-04: 64
- 2026-09-03: 64
- 2026-09-02: 64
- 2026-09-01: 64
- 2026-08-31: 64

## Common questions

### What is the Qdrant MCP server?

Qdrant MCP is listed in the public MCP registry as io.github.avaazquezz/mcp-qdrant. MCP server that wraps the Qdrant vector database API as tools. This page covers its PyPI package (mcp-qdrant).

### Is the Qdrant MCP server safe to use?

Qdrant MCP scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Qdrant MCP server expose?

Qdrant MCP exposes 13 tools: qdrant_health_check, qdrant_collection_create, qdrant_collection_list, qdrant_collection_info, qdrant_collection_update, and 8 more. Their descriptions and schemas cost roughly 1,576 tokens of context every time the server is loaded.

### Is the Qdrant MCP server still maintained?

Qdrant MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/mcp-qdrant/
- Socket report: https://socket.dev/pypi/package/mcp-qdrant
- Repository: https://github.com/avaazquezz/Qdrant-MCP
- Changelog RSS feed: https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant.xml
- Changelog JSON feed: https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant.json
- HTML version of this page: https://verifymcp.io/servers/avaazquezz-mcp-qdrant/mcp-qdrant