A production-ready Model Context Protocol (MCP) server exposing advanced ArangoDB operations to AI assistants like Claude Desktop and Augment Code. Features async-first Python architecture, comprehensive graph management, flexible content conversion (JSON, Markdown, YAML, Table), backup/restore functionality, and analytics capabilities.

📚 Documentation: https://github.com/PCfVW/mcp-arango-async/tree/master/docs

🚀 Quick Start: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/getting-started/quickstart-stdio.md

🔧 Installation: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/getting-started/installation.md

📖 Tools Reference: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/user-guide/tools-reference.md

🐛 Issues: https://github.com/PCfVW/mcp-arango-async/issues

✅ 34 MCP Tools - Complete ArangoDB operations (queries, collections, indexes, graphs)
✅ Graph Management - Create, traverse, backup/restore named graphs
✅ Content Conversion - JSON, Markdown, YAML, and Table formats
✅ Backup/Restore - Collection and graph-level backup with validation
✅ Analytics - Query profiling, explain plans, graph statistics
✅ Dual Transport - stdio (desktop clients) and HTTP (web/containerized)
✅ Production-Ready - Retry logic, graceful degradation, comprehensive error handling
✅ Type-Safe - Pydantic validation for all tool arguments

┌────────────────────┐      ┌─────────────────────┐      ┌──────────────────┐
│   MCP Client       │      │  ArangoDB MCP       │      │   ArangoDB       │
│ (Claude, Augment)  │─────▶│  Server (Python)    │─────▶│  (Docker)        │
│                    │      │  • 34 Tools         │      │  • Multi-Model   │
│                    │      │  • Graph Mgmt       │      │  • Graph Engine  │
│                    │      │  • Analytics        │      │  • AQL Engine    │
└────────────────────┘      └─────────────────────┘      └──────────────────┘

• Python 3.11+
• Docker Desktop (for ArangoDB)

# Install from PyPI
pip install mcp-arangodb-async

# Start ArangoDB
docker run -d \
  --name arangodb \
  -p 8529:8529 \
  -e ARANGO_ROOT_PASSWORD=changeme \
  arangodb:3.11

# Verify installation
python -m mcp_arangodb_async --health

Expected output:

{"status": "healthy", "database_connected": true, "database_info": {"version": "3.11.x", "name": "mcp_arangodb_test"}}

📖 Detailed installation guide: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/getting-started/installation.md

1. Configure Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/.config/Claude/claude_desktop_config.json (macOS/Linux):

{
  "mcpServers": {
    "arangodb": {
      "command": "python",
      "args": ["-m", "mcp_arangodb_async", "server"],
      "env": {
        "ARANGO_URL": "http://localhost:8529",
        "ARANGO_DB": "mcp_arangodb_test",
        "ARANGO_USERNAME": "mcp_arangodb_user",
        "ARANGO_PASSWORD": "mcp_arangodb_password"
      }
    }
  }
}

2. Restart Claude Desktop

3. Test the connection:

Ask Claude: "List all collections in the ArangoDB database"

📖 Full stdio quickstart: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/getting-started/quickstart-stdio.md

1. Start HTTP server:

python -m mcp_arangodb_async --transport http --host 0.0.0.0 --port 8000

2. Test health endpoint:

curl http://localhost:8000/health

3. Connect from web client:

import { MCPClient } from '@modelcontextprotocol/sdk';

const client = new MCPClient({
  transport: 'http',
  url: 'http://localhost:8000/mcp'
});

await client.connect();
const tools = await client.listTools();

📖 HTTP transport guide: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/developer-guide/http-transport.md

Required:

ARANGO_URL=http://localhost:8529
ARANGO_DB=mcp_arangodb_test
ARANGO_USERNAME=root
ARANGO_PASSWORD=changeme

Optional:

# Transport configuration
MCP_TRANSPORT=stdio                    # stdio or http
MCP_HTTP_HOST=0.0.0.0                  # HTTP bind address
MCP_HTTP_PORT=8000                     # HTTP port
MCP_HTTP_STATELESS=false               # Stateless mode

# Connection tuning
ARANGO_TIMEOUT_SEC=30.0                # Request timeout
ARANGO_CONNECT_RETRIES=3               # Connection retries
ARANGO_CONNECT_DELAY_SEC=1.0           # Retry delay

# Logging
LOG_LEVEL=INFO                         # DEBUG, INFO, WARNING, ERROR

📖 Complete configuration reference: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/configuration/environment-variables.md

The server exposes 34 MCP tools organized into 9 categories:

• arango_query - Execute AQL queries
• arango_list_collections - List all collections
• arango_insert - Insert documents
• arango_update - Update documents
• arango_remove - Remove documents
• arango_create_collection - Create collections
• arango_backup - Backup collections

• arango_list_indexes - List indexes
• arango_create_index - Create indexes
• arango_delete_index - Delete indexes

• arango_explain_query - Explain query execution plan
• arango_query_builder - Build AQL queries
• arango_query_profile - Profile query performance

• arango_validate_references - Validate document references
• arango_insert_with_validation - Insert with validation
• arango_create_schema - Create JSON schemas
• arango_validate_document - Validate against schema

• arango_bulk_insert - Bulk insert documents
• arango_bulk_update - Bulk update documents

• arango_create_graph - Create named graphs
• arango_list_graphs - List all graphs
• arango_add_vertex_collection - Add vertex collections
• arango_add_edge_definition - Add edge definitions
• arango_add_vertex - Add vertices
• arango_add_edge - Add edges
• arango_graph_traversal - Traverse graphs

• arango_traverse - Graph traversal
• arango_shortest_path - Find shortest paths

• arango_backup_graph - Backup single graph
• arango_restore_graph - Restore single graph
• arango_backup_named_graphs - Backup all named graphs
• arango_validate_graph_integrity - Validate graph integrity

• arango_graph_statistics - Graph statistics
• arango_database_status - Database status

📖 Complete tools reference: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/user-guide/tools-reference.md

Model your codebase as a graph to analyze dependencies, find circular references, and understand architecture:

# 1. Create graph structure
Ask Claude: "Create a graph called 'codebase' with vertex collections 'modules' and 'functions', 
and edge collection 'calls' connecting functions"

# 2. Import codebase data
Ask Claude: "Insert these modules into the 'modules' collection: [...]"

# 3. Analyze dependencies
Ask Claude: "Find all functions that depend on the 'auth' module using graph traversal"

# 4. Detect circular dependencies
Ask Claude: "Check for circular dependencies in the codebase graph"

# 5. Generate architecture diagram
Ask Claude: "Export the codebase graph structure as Markdown for visualization"

📖 More examples: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/examples/codebase-analysis.md

• Installation Guide
• Quick Start (stdio)
• First Interaction

• Transport Configuration
• Environment Variables

• Tools Reference
• Troubleshooting

• Architecture Overview
• Low-Level MCP Rationale
• HTTP Transport
• Changelog

• Codebase Dependency Analysis

📖 Full documentation: https://github.com/PCfVW/mcp-arango-async/tree/master/docs

Database connection fails:

# Check ArangoDB is running
docker ps | grep arangodb

# Test connection
curl http://localhost:8529/_api/version

# Check credentials
python -m mcp_arangodb_async --health

Server won't start in Claude Desktop:

# Verify Python installation
python --version  # Must be 3.11+

# Test module directly
python -m mcp_arangodb_async --health

# Check Claude Desktop logs
# Windows: %APPDATA%\Claude\logs\
# macOS: ~/Library/Logs/Claude/

Tool execution errors:

• Verify ArangoDB is healthy: docker compose ps
• Check environment variables are set correctly
• Review server logs for detailed error messages

📖 Complete troubleshooting guide: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/user-guide/troubleshooting.md

✅ Stability - Isolated environment, no host conflicts
✅ Zero-install - Start/stop with docker compose
✅ Reproducibility - Same image across all environments
✅ Health checks - Built-in readiness validation
✅ Fast reset - Recreate clean instances easily
✅ Portability - Consistent on Windows/macOS/Linux

• This project: Apache License 2.0
• ArangoDB 3.11: Apache License 2.0
• ArangoDB 3.12+: Business Source License 1.1 (BUSL-1.1)

⚠️ Important: This repository does not grant rights to ArangoDB binaries. You must comply with ArangoDB's license for your deployment version.

📖 License details: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/getting-started/installation.md#arangodb-licensing

Contributions are welcome! Please see our documentation for guidelines.

📖 Architecture decisions: https://github.com/PCfVW/mcp-arango-async/blob/master/docs/developer-guide/low-level-mcp-rationale.md

• Issues: https://github.com/PCfVW/mcp-arango-async/issues
• Discussions: https://github.com/PCfVW/mcp-arango-async/discussions
• Documentation: https://github.com/PCfVW/mcp-arango-async/tree/master/docs

Built with:

• Model Context Protocol by Anthropic
• python-arango - Official ArangoDB Python driver
• Pydantic - Data validation
• Starlette - HTTP transport
• ArangoDB - Multi-model database