AgentArmorHQ
Sign in

mcp-server-qdrant

MCP server · GitHub · ★ 1.6k · graded 2026-10-22Source linked

An official Qdrant Model Context Protocol (MCP) server implementation

No outside reports on file

This tool gives AI direct control over a vector database, so only connect it to a Qdrant instance containing data you trust the AI to access and modify.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for MCP Server Qdrant helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (qdrant/mcp-server-qdrant)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/qdrant/mcp-server-qdrant ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 9 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.

Showing all 9Showing 9 community threads of 9

  1. CommunityDoes mcp-server-qdrant have a qdrant-delete tool, and is it hidden in read_only mode?AgentArmorHQ community · 2026-10-26
  2. CommunityHow do I connect mcp-server-qdrant to a local Qdrant database by folder path?AgentArmorHQ community · 2026-10-26
  3. CommunityHow to fix timeout when storing Japanese text with mcp-server-qdrant on Windows?AgentArmorHQ community · 2026-10-26
  4. CommunityHow to use custom or local embedding models (Ollama, vLLM) with mcp-server-qdrant?AgentArmorHQ community · 2026-10-26
  5. CommunityHow to use mcp-server-qdrant with existing Qdrant collections when vector name doesn't match?AgentArmorHQ community · 2026-10-26
  6. CommunityIs there a way to edit or delete a record in mcp-server-qdrant?AgentArmorHQ community · 2026-10-26
  7. Communitymcp-server-qdrant 400: "Vector with name fast-bge-small-en-v1.5 is not configured in this collection"AgentArmorHQ community · 2026-10-26
  8. Communitymcp-server-qdrant ignores FASTMCP_HOST/FASTMCP_PORT — correct env vars?AgentArmorHQ community · 2026-10-26
  9. Communityqdrant-find fails with 'document': what payload structure does the MCP server expect?AgentArmorHQ community · 2026-10-26

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About MCP Server Qdrant

This tool connects Claude and other AI models to Qdrant, a vector database (a system that stores and searches data based on similarity). It lets AI systems store, search, and manage embeddings—numerical representations of text or images—for tasks like semantic search and recommendation systems.

Who it’s for

Developers building AI applications that need to store or search through large amounts of text or image data using vector similarity. Teams using Qdrant for vector storage who want to integrate it with Claude or other MCP-compatible AI tools.

Alternatives

  • Pinecone MCP server: Another vector database with MCP support; may offer managed infrastructure.
  • Weaviate integrations: Alternative vector database with AI integration options.
  • Custom MCP tools: Build your own MCP server with fine-grained access controls instead of using official connectors.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the setup steps in the project’s official README: https://github.com/qdrant/mcp-server-qdrant (opens external site)

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100
GitHub stars
1.6k
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Database access: This connector can read, write, and delete data stored in your Qdrant instance. If Qdrant holds sensitive information, the AI gains direct access to it.
  • No built-in filtering: The tool may not limit which collections or data the AI can reach. An attacker controlling the AI could browse or modify all stored embeddings.
  • Prompt injection: Malicious text fed into the AI could trick it into running unintended vector searches or database commands.
  • Network exposure: If Qdrant is exposed to the internet, this connector makes it reachable by any process running the AI system.
  • Data leakage: Sensitive embeddings or metadata stored in Qdrant could be extracted through the AI and leaked in responses.

How to lower the risk

Least-privilege permissions

  • Create a Qdrant user account with read-only or minimal write access if possible.
  • Limit the connector to specific collections instead of full database access.

Network isolation

  • Run Qdrant behind a firewall or private network, never exposed to the internet.
  • Use local connections (localhost) if the AI system runs on the same machine.

Monitoring

  • Log all vector search and database modification queries the AI makes.
  • Review logs regularly for unexpected data access patterns.

Red flags to watch for

  • Unusual database queries or access to unexpected collections.
  • Unexpected increases in data retrieval or modification volume.
  • Errors or crashes that suggest the AI is probing database boundaries.

Questions

How do I install MCP Server Qdrant?

MCP Server Qdrant does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/qdrant/mcp-server-qdrant.

Are there security reports about MCP Server Qdrant?

No reports found for this package in our research (last checked 2026-10-30). MCP Server Qdrant currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include database access, no built-in filtering, prompt injection.

Is MCP Server Qdrant actively maintained?

MCP Server Qdrant has 1.6k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/qdrant/mcp-server-qdrant before pinning it in production.

What are alternatives to MCP Server Qdrant?

Notable alternatives to MCP Server Qdrant include Pinecone MCP server (Another vector database with MCP support), Weaviate integrations (Alternative vector database with AI integration options), Custom MCP tools (Build your own MCP server with fine-grained access controls instead of using official connectors). You can also compare MCP Server Qdrant side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use MCP Server Qdrant? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for MCP Server Qdrant

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for MCP Server Qdrant](https://agentarmorhq.com/api/badge/qdrant-mcp-server-qdrant)](https://agentarmorhq.com/skills/qdrant-mcp-server-qdrant)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/qdrant-mcp-server-qdrant"><img src="https://agentarmorhq.com/api/badge/qdrant-mcp-server-qdrant" alt="AgentArmorHQ Risk Grade for MCP Server Qdrant" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "qdrant-mcp-server-qdrant"

Share with your security lead

Need sign-off to use mcp-server-qdrant? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: mcp-server-qdrant
- **Listing URL:** https://agentarmorhq.com/skills/qdrant-mcp-server-qdrant
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.6k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (qdrant/mcp-server-qdrant)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/qdrant/mcp-server-qdrant
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
qdrant
Source code
github.com/qdrant/mcp-server-qdrant
Est. context load
~1.4k tokens / turn (~8 tool schemas, 0.68% of 200k context)
Popularity
1.6k GitHub stars
Last updated
2026-10-29
Last graded
2026-10-22

Community

Discussions for MCP Server Qdrant

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for MCP Server Qdrant helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude