agentmods.dev

qdrant

A local connector for retrieving relevant context from Qdrant, a database designed to search stored information by meaning.

In plain words
What is it for?
Fetching context from a Qdrant database using its URL, API key, and collection name.
Why use it?
It lets a coding agent look up related information from a Qdrant collection instead of relying only on the current conversation.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

7 4mo ago A scan tokens not measured original MIT
View the source file viknesh20-20/claude-code-tool-kit
Install

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.

agentmods
npx agentmods add mcp/viknesh20-20/claude-code-tool-kit/qdrant
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

qdrant scanned grade A with 0 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 3d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 13 lines

What it actually says

{
  "qdrant": {
    "command": "uvx",
    "args": [
      "mcp-server-qdrant"
    ],
    "env": {
      "QDRANT_URL": "${QDRANT_URL}",
      "QDRANT_API_KEY": "${QDRANT_API_KEY}",
      "COLLECTION_NAME": "${QDRANT_COLLECTION}"
    }
  }
}
Changes

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.

  1. 3d ago First seen · 13 lines scan A a2a886e5d299

Subscribe to this mod's changes

qdrant is an MCP server published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIDatabasesRAG and vectorsagent-orchestrationai-agentsai-coding-assistant-toolsclaude-ai-skillsclaude-codeclaude-code-agents
Related

Other mcp servers, from other repositories

infino

MCP server for Infino — keyword, vector, hybrid, and SQL retrieval over data on object storage, for AI agents. Runs locally from the @infino-ai/mcp-server npm package. Needs 3 environment variables to run.

infino-ai/infino-mcp · not measured

opensolr-mcp

MCP server for Opensolr — managed Apache Solr with hybrid BM25+kNN search, server-side embeddings, and RAG answers as agent tools. Runs locally from the opensolr-mcp Python package. Needs 2 environment variables to run.

phpcip/opensolr-mcp · not measured

local-knowledge-rag

MCP server "local-knowledge-rag" as configured in patakuti/local-knowledge-rag-mcp. Runs /path/to/local-knowledge-rag-mcp/dist/mcp-server.js with node. Needs 3 environment variables to run.

patakuti/local-knowledge-rag-mcp · not measured

better-qdrant-mcp-server

MCP server for enhanced Qdrant vector database functionality. Runs locally from the better-qdrant-mcp-server npm package.

wrediam/better-qdrant-mcp-server · not measured

pgvector

MCP server exposing pgvector similarity search, hybrid search, and index management as tools for LLM agents. Runs locally from the mcp-server-pgvector Python package. Needs 2 environment variables to run.

mittalpk/mcp-server-pgvector · not measured

qdrant-search-mcp

MCP server "qdrant-search-mcp" as configured in webtoolbox/qdrant-search-mcp. Runs locally from the qdrant-search-mcp Python package.

webtoolbox/qdrant-search-mcp · not measured