What is mcp-server-qdrant CLAUDE.md?

A repository guide for coding agents working on a Rust server that connects the Model Context Protocol (MCP) to Qdrant, a database for searching data by meaning. It documents the project’s commands, structure, and options for creating text embeddings.

Use it when an agent needs to understand this repository, run its checks, switch between ONNX and Candle embedding backends, or navigate its configuration and modules.

It gives the agent the project-specific instructions needed to build, test, format, and run the code correctly. It also explains which embedding backend and build options the project supports.

How vaporif/mcp-server-qdrant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vaporif/mcp-server-qdrant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vaporif/mcp-server-qdrant/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vaporif/mcp-server-qdrant

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vaporif/mcp-server-qdrant/claude-md/github.svg)](https://agentmods.dev/instructions/vaporif/mcp-server-qdrant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vaporif/mcp-server-qdrant/claude-md"><img src="https://agentmods.dev/badge/instructions/vaporif/mcp-server-qdrant/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vaporif/mcp-server-qdrant/claude-md"><img src="https://agentmods.dev/badge/instructions/vaporif/mcp-server-qdrant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 794 This file is loaded in full into every session.

When invoked 794 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00794	$0.00794
Opus 5	$0.00397	$0.00397
Sonnet 5	$0.00159	$0.00159
Haiku 4.5	$0.00079	$0.00079

Measured 8d ago against content hash 13215ffa3b53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-server-qdrant CLAUDE.md 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 8d 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Rust MCP (Model Context Protocol) server for Qdrant vector database with local embedding support. Dual candle/ONNX embedding backends (feature-flagged).

Commands

All commands use just (task runner). Run just to see available tasks.

Build: just build (debug), just build-release (release)
Test: just test — uses cargo nextest
Test single: just test -E 'test(my_test_name)' (nextest filter expression)
Lint: just lint — runs cargo fmt --check + cargo clippy -D warnings
Format: just fmt
Run: just run
Watch: just watch (uses bacon)

Feature flags

onnx-fetch (default) — ONNX Runtime with auto-download of runtime binaries
onnx — ONNX Runtime with user-provided ORT_DYLIB_PATH
candle — Pure Rust candle-based BERT embedding backend (no native deps)

Build with candle instead of ONNX:

cargo build --no-default-features --features candle

Architecture

Single crate at repo root

Modules

config — CLI parsing (clap) with env var fallbacks, config structs
errors — Error types (thiserror)
filters — Filterable field types for Qdrant queries
embeddings — EmbeddingProvider trait + feature-gated backends
- embeddings/candle_backend — candle BERT embedder (default)
- embeddings/onnx_backend — ONNX Runtime embedder
qdrant — Qdrant client connector (placeholder)
server — MCP server implementation (placeholder)

Code Conventions

Rust edition 2024
Clippy: all + pedantic + nursery + cargo warnings enabled
Allowed lints: implicit_return, missing_errors_doc, missing_panics_doc, missing_safety_doc, module_name_repetitions, must_use_candidate, similar_names, too_many_lines, cognitive_complexity, multiple_crate_versions, significant_drop_tightening
Modern module syntax: foo.rs + foo/bar.rs (not foo/mod.rs)
Nix dev environment via flake.nix + direnv
.envrc auto-loads the dev shell

Read the full file on GitHub · 69 lines

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.

8d ago First seen · 69 lines · 794 tokens per session scan A 13215ffa3b53

Subscribe to this mod's changes

mcp-server-qdrant CLAUDE.md is an instructions file published in the GitHub repository vaporif/mcp-server-qdrant (0 stars, last pushed 3mo ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 per session on Opus 5. 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.

embeddings mcp model-context-protocol qdrant

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-server-qdrant: Instructions file for Claude Code