1. Conduid
  2. RAG
  3. QdrantSkillsMCP
MCP server · RAG

QdrantSkillsMCP

by · github.com/jamesburton/QdrantSkillsMCP

MCP server for semantic skill search and retrieval using Qdrant. Provides vector-based skill storage, semantic search, and multi-agent setup via CLI and MCP tools.

Unclaimed rag
InstallView source
34Low

Scored 6 months ago · breakdown

About QdrantSkillsMCP

QdrantSkillsMCP is an MCP server published by jamesburton in the RAG category: mCP server for semantic skill search and retrieval using Qdrant. Provides vector-based skill storage, semantic search, and multi-agent setup via CLI and MCP tools.

The repository has 1 stars and 0 forks, with the last commit 3 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/jamesburton/QdrantSkillsMCP

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (9)

add-skillPersist a skill with YAML frontmatter to Qdrant

Parameters not published.

archive-skillSoft-hide a skill without deletion

Parameters not published.

delete-skillPermanently remove a skill

Parameters not published.

get-skill-guideReturns the bundled guide teaching agents how to use QdrantSkillsMCP

Parameters not published.

list-skillsList all skills (supports `--names` and `--summaries` modes)

Parameters not published.

load-skillFetch specific skill(s) by name

Parameters not published.

reset-sessionClear session tracking for loaded skills

Parameters not published.

search-skillsSemantic vector search with configurable temperature and max results

Parameters not published.

update-skillUpdate existing skill content and re-embed

Parameters not published.

Ask AI

✦

Ask AI about QdrantSkillsMCP

Powered by Claude · Grounded in docs

I know everything about QdrantSkillsMCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

QdrantSkillsMCP

A .NET 10 MCP server for vector-based skill storage and retrieval using Qdrant. Enables AI agents (Claude Code, Copilot, Codex, etc.) to semantically search, load, and manage skills via MCP tools.

Prerequisites

Get Started

No install needed — dnx runs the tool directly from NuGet, always using the latest version:

# Initialize config (creates ~/.qdrant-skills/config.json with local defaults)
dnx QdrantSkillsMCP -- --config init

# Auto-configure your AI agent (Claude, Copilot, Codex, etc.)
dnx QdrantSkillsMCP -- --setup

# Verify your Qdrant connection
dnx QdrantSkillsMCP -- --config validate

What is dnx? It's .NET 10's equivalent of npx — runs NuGet tools without installing them. Always gets the latest version automatically.

Alternative: Global Install

If you prefer a permanent installation (no dnx prefix needed):

dotnet tool install -g QdrantSkillsMCP
qdrant-skills-mcp --config init
qdrant-skills-mcp --setup

Update later with: dotnet tool update -g QdrantSkillsMCP

Configuration

# Show all config with source annotations ([default], [user], [project], [env])
dnx QdrantSkillsMCP -- --config show

# Connect to a remote Qdrant instance
dnx QdrantSkillsMCP -- --config set QdrantHost=my-qdrant.example.com
dnx QdrantSkillsMCP -- --config set QdrantGrpcPort=6334
dnx QdrantSkillsMCP -- --config set UseTls=true
dnx QdrantSkillsMCP -- --config set QdrantApiKey=your-api-key

# Named profiles for switching between environments
dnx QdrantSkillsMCP -- --config use cloud

# Validate connection works
dnx QdrantSkillsMCP -- --config validate

# Generate env var template for your shell (auto-detects bash/PowerShell/cmd)
dnx QdrantSkillsMCP -- --config env

# Interactive config wizard
dnx QdrantSkillsMCP -- --config

Config files:

  • User-level: ~/.qdrant-skills/config.json (API keys, personal settings)
  • Project-level: ./qdrant-skills.json (shared team settings)
  • Precedence: Environment variables > Project > User > Defaults

CLI Usage

# Search skills by meaning
dnx QdrantSkillsMCP -- --console search "authentication patterns"

# List all skills
dnx QdrantSkillsMCP -- --console list

# JSON output for scripting
dnx QdrantSkillsMCP -- --console --json search "error handling"

# Interactive REPL with tab completion and history
dnx QdrantSkillsMCP -- --console

# Show help
dnx QdrantSkillsMCP -- --console help

MCP Server Mode

By default (no flags), QdrantSkillsMCP runs as an MCP server over stdio. This is how AI agents connect to it. The --setup wizard configures this automatically for your agent.

Available MCP Tools

Tool Description
search-skills Semantic vector search with configurable temperature and max results
load-skill Fetch specific skill(s) by name
add-skill Persist a skill with YAML frontmatter to Qdrant
update-skill Update existing skill content and re-embed
delete-skill Permanently remove a skill
archive-skill Soft-hide a skill without deletion
list-skills List all skills (supports --names and --summaries modes)
reset-session Clear session tracking for loaded skills
get-skill-guide Returns the bundled guide teaching agents how to use QdrantSkillsMCP

ONNX Model Packages

For local embedding without API keys, three pre-built model packages are available:

Package Model Size Quality Dims
QdrantSkillsMCP.Models.MiniLM all-MiniLM-L6-v2 ~23 MB Fastest 384
QdrantSkillsMCP.Models.BgeSmall BGE-small-en-v1.5 ~34 MB Best value 384
QdrantSkillsMCP.Models.BgeBase BGE-base-en-v1.5 ~105 MB Highest quality 768

Without a companion package, the tool auto-downloads all-MiniLM-L6-v2 from HuggingFace on first use (~23 MB, requires internet). This works with no setup.

To pre-install a model, add it to your NuGet global cache (works without a project):

# Create a temp project, restore, then discard — populates the NuGet cache
dotnet new console -o /tmp/model-install --no-restore
dotnet add /tmp/model-install package QdrantSkillsMCP.Models.BgeSmall
dotnet restore /tmp/model-install

The tool auto-detects the model in ~/.nuget/packages/qdrantskillsmcp.models.bgesmall/ on startup.

Then select it:

dnx QdrantSkillsMCP -- --config set OnnxModelName=bge-small-en-v1.5

Embedding Providers

Configure via dnx QdrantSkillsMCP -- --config set EmbeddingProvider=<provider>:

Provider Model Notes
LocalONNX (default) all-MiniLM-L6-v2 Runs locally, no API key needed, 384 dimensions
OpenAI text-embedding-3-small/large Requires OpenAiApiKey or OPENAI_API_KEY env var
Ollama Any Ollama embedding model Set EmbeddingUrl (default: http://localhost:11434)
AzureOpenAI Azure-hosted embeddings Requires endpoint, key, and deployment name

Development

Requires .NET 10 SDK and Docker (for Qdrant via Aspire).

# Run with Aspire (starts Qdrant automatically)
dotnet run --project src/QdrantSkillsMCP.AppHost

# Run unit tests
dotnet test tests/QdrantSkillsMCP.UnitTests

# Run all tests (requires Qdrant running)
dotnet test

License

MIT

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About QdrantSkillsMCP

How do I install QdrantSkillsMCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is QdrantSkillsMCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is QdrantSkillsMCP still maintained?

Yes — the last commit was 3 months ago. The repository has 1 stars and 0 forks.