qmcp - QDrant MCP Server for OpenCode

Semantic search server for code and documentation using Qdrant vector database.

Language: English | Русский

Features

• Semantic Search: Find code and documentation using natural language queries
• Multi-language Support: Python, Go, JavaScript, TypeScript, Java, C#, Markdown
• Live Updates: File watcher for automatic reindexing
• Incremental Indexing: Only index changed files
• Gitignore Support: Respects .gitignore - excludes node_modules, __pycache__, .venv, build artifacts, etc.
• Cleanup: Remove stale vectors for deleted/changed files
• Diagnostics: Introspection tools to understand what's indexed
• OpenCode Skill: Natural language interface for Qdrant management

Installation

Via PyPI (Recommended)

pip install qmcp-qdrant

Via uv

uv tool install qmcp-qdrant

From Source

git clone https://github.com/BigKAA/qmcp.git
cd qmcp
make install

Updating

Via uv (Recommended)

uv tool upgrade qmcp-qdrant

Via pip

pip install --upgrade qmcp-qdrant

Quick Start

1. Ensure Qdrant is running

For Kubernetes deployment, see Qdrant on Kubernetes.

2. Add MCP Server to OpenCode

opencode mcp add qmcp-qdrant qmcp-qdrant

⚠️ Note: Environment variables must be set in ~/.config/opencode/opencode.json config file (see below).

💡 Global MCP, multiple projects: qmcp now uses a two-level auto-indexing strategy. The server automatically starts a watcher for configured WATCH_PATHS, and OpenCode/agents should ensure the current workspace is watched with qdrant_watch_ensure(paths=[workspace_root]).

💡 WATCH_PATHS format: WATCH_PATHS accepts a single absolute path, a comma-separated list of paths, or a JSON array string. For example: /home/user/project, /home/user/project,/home/user/docs, or ["/home/user/project", "/home/user/docs"].

3. That's It!

OpenCode will automatically discover and use the semantic search tools.

Manual Configuration (Alternative)

If opencode mcp add doesn't work, edit ~/.config/opencode/opencode.json directly:

{
  "mcp": {
    "qmcp-qdrant": {
      "type": "local",
      "command": ["qmcp-qdrant"],
      "environment": {
        "QDRANT_URL": "http://192.168.218.190:6333",
        "WATCH_PATHS": "/home/user/shared-docs,/home/user/shared-snippets"
      }
    }
  }
}

For Python module:

{
  "mcp": {
    "qmcp-qdrant": {
      "type": "local",
      "command": ["python", "-m", "qmcp.server"],
      "environment": {
        "QDRANT_URL": "http://192.168.218.190:6333",
        "WATCH_PATHS": "/home/user/shared-docs,/home/user/shared-snippets"
      }
    }
  }
}

Indexing Notes

⚠️ Important: Full indexing and reindexing of large projects can take a significant amount of time (minutes to hours depending on project size).

For large codebases, prefer:

• Incremental reindex (mode="incremental") - only updates changed files based on content hashes
• File watcher - enables automatic live updates when files change

Automatic Indexing Strategy

qmcp supports automatic indexing on two levels:

1. Server startup level — on MCP startup, the server automatically tries to start a watcher for WATCH_PATHS.
2. Workspace session level — because one global MCP server can be shared across multiple repositories, agents should check the watcher state for the current workspace and call qdrant_watch_ensure(paths=[workspace_root]) when the workspace path is missing.

Recommended OpenCode flow for every new workspace:

status = qdrant_get_status()

# If watcher is not active or the current repo is not covered,
# safely extend the watcher without dropping other projects.
qdrant_watch_ensure(paths=["/absolute/path/to/current/workspace"])

qdrant_watch_ensure merges the current workspace with already watched paths and WATCH_PATHS, making it safe for a single global MCP shared by multiple projects.

The indexer automatically respects .gitignore files, significantly reducing index size by excluding:

• Dependencies: node_modules/, vendor/, .venv/, .pip cache/
• Build artifacts: dist/, build/, *.class, *.o, *.so
• Generated files: __pycache__/, *.pyc, *.pyo, .pytest_cache/
• IDE settings: .idea/, .vscode/, *.swp, *.swo
• Environment files: .env, .env.local, *.log

Configuration

Environment Variable	Default	Description
QDRANT_URL	http://localhost:6333	Qdrant server URL
QDRANT_API_KEY	(none)	Qdrant API key (optional)
EMBEDDING_MODEL	BAAI/bge-small-en-v1.5	Embedding model
EMBEDDING_CACHE_DIR	(system temp)	Custom directory for model cache
WATCH_PATHS	/data/repo	Baseline paths to watch automatically on server startup
BATCH_SIZE	50	Batch size for indexing
DEBOUNCE_SECONDS	5	Debounce delay
LOG_LEVEL	INFO	Logging level
LOG_FORMAT	text	Log format (text or json)

💡 Model Cache: Set EMBEDDING_CACHE_DIR to persist models across restarts. First launch downloads the model (~13MB), subsequent launches use cached version.

💡 WATCH_PATHS examples:

• Single path: WATCH_PATHS=/home/user/project
• Multiple paths: WATCH_PATHS=/home/user/project,/home/user/docs
• JSON array: WATCH_PATHS=["/home/user/project", "/home/user/docs"]

MCP Tools

Search & Indexing

Tool	Description
qdrant_search	Semantic search in code/docs
qdrant_index_directory	Index a directory
qdrant_reindex	Reindex (full or incremental)

💡 Tip: Use qdrant_search with filters for precise results:

• chunk_type — filter by code type (function_def, class_def, etc.)
• symbol_name — find exact symbol by name
• language — filter by programming language

See docs/STRUCTURED_METADATA.md for detailed examples.

Collection Management

Tool	Description
qdrant_list_collections	List all collections
qdrant_get_collection_info	Get collection info
qdrant_delete_collection	Delete collection

Diagnostics & Introspection (NEW)

Tool	Description
qdrant_diagnose_collection	Full collection diagnostics - vectors, files, types, issues
qdrant_list_indexed_files	Paginated list of indexed files with metadata
qdrant_diff_collection	Compare Qdrant state with filesystem (orphans, missing, modified)

Maintenance

Tool	Description
qdrant_cleanup	Clean stale vectors (dry-run supported)
qdrant_watch_start	Start file watcher
qdrant_watch_ensure	Ensure workspace path is watched without dropping other projects
qdrant_watch_stop	Stop file watcher
qdrant_get_status	Server status

Diagnostic Tools Usage Examples

# Diagnose a collection - see what's indexed, file types, issues
qdrant_diagnose_collection(collection="myproject")

# List indexed files with pagination
qdrant_list_indexed_files(collection="myproject", limit=50, offset=0)

# Filter by file type
qdrant_list_indexed_files(collection="myproject", file_type=".py")

# Compare Qdrant state with filesystem
qdrant_diff_collection(collection="myproject", repo_path="/path/to/repo")

OpenCode Skill

The project includes an OpenCode skill for natural language management of Qdrant.

Installation

# Copy skill to OpenCode skills directory
cp -r skills/qmcp-manager ~/.config/opencode/skills/

Usage

Once installed, OpenCode will automatically activate the skill when you ask questions like:

Query	What Happens
what's indexed in my Qdrant?	Diagnoses collection and shows stats
show collection stats	Lists all collections with vector counts
clean up orphans in my index	Finds and previews deletion of orphaned vectors
diagnose my index	Full diagnostics with issues and file list
compare index with /path/to/repo	Shows orphans, missing, and modified files
find missing files	Lists files on disk but not indexed
is my index up to date?	Compares hashes to detect changes

Workflows Provided by Skill

1. Quick Status - Check collection state with qdrant_list_collections
2. Full Diagnostics - Detailed analysis with qdrant_diagnose_collection
3. Diff - Compare Qdrant with filesystem using qdrant_diff_collection
4. Safe Cleanup - Preview with dry-run, then confirm deletion
5. Smart Reindex - Incremental updates based on file hashes

Skill Location

skills/qmcp-manager/SKILL.md

OpenCode Integration

Add MCP Server

opencode mcp add qmcp-qdrant qmcp-qdrant

Or edit ~/.config/opencode/opencode.json directly (required for environment variables):

{
  "mcp": {
    "qmcp-qdrant": {
      "type": "local",
      "command": ["qmcp-qdrant"],
      "environment": {
        "QDRANT_URL": "http://192.168.218.190:6333",
        "WATCH_PATHS": "/home/user/shared-docs,/home/user/shared-snippets"
      }
    }
  }
}

Recommended OpenCode Agent Workflow

For a single global MCP server shared across multiple projects:

1. Call qdrant_get_status() when the agent starts working in a workspace.
2. If watcher_active is false or watched_paths does not include the current workspace root, call:

qdrant_watch_ensure(paths=["/absolute/path/to/current/workspace"])

This preserves configured startup paths and already watched projects instead of replacing them.

Manage MCP Servers

opencode mcp list          # List all MCP servers
opencode mcp debug qmcp-qdrant     # Debug connection issues
opencode mcp logout qmcp-qdrant    # Remove MCP server

Development

make install      # Install dependencies
make test         # Run tests
make lint         # Lint code
make format       # Format code
make mcp-dev      # Run with MCP inspector

Troubleshooting

If you encounter issues, see the Troubleshooting Guide for:

• Embedding Model Issues — indexed_vectors_count: 0 diagnosis and fix
• Connection Problems — Qdrant connection troubleshooting
• Search Returns No Results — Empty search results debugging

License

Apache 2.0