mcp-server-qdrant is a Model Context Protocol server that lets language-model applications store and retrieve semantic memories in Qdrant, a vector search engine. It is used in AI-powered editors, chats, and workflows that need searchable external context. The catalogue entry provides an agent add-on for using Qdrant as a memory layer.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add qdrant/mcp-server-qdrant --skill setupgit clone --depth 1 https://github.com/qdrant/mcp-server-qdrantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qdrant/mcp-server-qdrant/setup)<a href="https://agentmods.dev/skills/qdrant/mcp-server-qdrant/setup"><img src="https://agentmods.dev/badge/skills/qdrant/mcp-server-qdrant/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qdrant/mcp-server-qdrant/setup"><img src="https://agentmods.dev/badge/skills/qdrant/mcp-server-qdrant/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 38 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium MCP Rug Pull · line 19 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Excessive Agency · line 67 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Supply Chain · line 38 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01464 |
| Opus 5.5 | $0.00018 | $0.00586 |
| Sonnet 5.5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade C, and why
setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure the Qdrant Power
After the Power is installed, guide the user through these steps.
Kiro IDE needs three separate things to be true before the server starts:
uvxis reachable from the process that launched Kiro.- The four variables exist in that process environment.
- The four variable names appear in Kiro's approved list.
A failure in any one of them shows up as the same Failed to connect log line,
so work through the steps in order instead of guessing.
1. Make sure that uvx is available
Run this command:
uvx --version
If the command succeeds, note the full path:
command -v uvx
If the command fails, tell the user that the Power requires uv.
Before you run the installation command, ask the user for approval.
curl -LsSf https://astral.sh/uv/install.sh | sh
After the installation, run uvx --version again.
If uvx is still unavailable, tell the user to restart the terminal and Kiro.
CAUTION: uv installs uvx into ~/.local/bin. A Kiro IDE started from the
macOS Dock or Finder receives a minimal PATH of /usr/bin:/bin:/usr/sbin:/sbin
and cannot resolve the bare uvx command. Step 5 covers this.
2. Collect the configuration
Ask the user for these values:
QDRANT_URL: The URL of the Qdrant server.COLLECTION_NAME: The collection for semantic memories.EMBEDDING_MODEL: The FastEmbed model name.
Use http://localhost:6333 as the usual local URL.
Use the Qdrant Cloud URL for a cloud connection.
If the user does not select an embedding model, use sentence-transformers/all-MiniLM-L6-v2.
If the user uses Qdrant Cloud, tell the user to set QDRANT_API_KEY locally.
If the user uses local Qdrant without authentication, use an empty QDRANT_API_KEY value.
Do not ask the user to send an API key in the conversation.
Tell the user that the server creates the collection automatically.
CAUTION: Do not change the embedding model for an existing collection. A different vector size can cause store or search errors.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 181 lines · 45 tokens per session scan C 3f95c6ffc024
setup is a skill published in the GitHub repository qdrant/mcp-server-qdrant (1,548 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,464 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
RAG Workflow Planner
Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.
pn-rag-evaluation
Evaluate retrieval-augmented generation pipelines — golden sets, automated metrics (incl. RAGAS-style), human rubrics, regression gates in CI. Use when building or changing RAG (chunks, embeddings, rerankers, prompts) and need quality proof, not vibes.
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.