MCP Server

Async MCP server for ArangoDB: 46 tools for graphs, queries, and multi-tenancy.

Local serverstdioPython

What is the MCP MCP server?

MCP MCP server exists for a simple reason — assistants are far more useful when they can act on MCP directly instead of describing what you should do. Async MCP server for ArangoDB: 46 tools for graphs, queries, and multi-tenancy.

What you get

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.

  • 46 MCP Tools - Complete ArangoDB operations (queries, collections, indexes, graphs)
  • Multi-Tenancy - Work with multiple databases, environment switching, cross-database operations
  • MCP Design Patterns - Progressive discovery, context switching, tool unloading (98.7% token savings)
  • 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

What the assistant can call

Once MCP is connected, these are the calls the assistant has available:

  • arango_set_focused_database — Set focused database for session
  • arango_get_focused_database — Get currently focused database
  • arango_list_available_databases — List all configured databases
  • arango_get_database_resolution — Show database resolution algorithm
  • 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

Setting it up

The server ships on PyPI as mcp-arangodb-async, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need 4 environment variables: ARANGO_URL, ARANGO_DB, ARANGO_USERNAME, ARANGO_PASSWORD. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Docker and Docker Compose installed - Python 3.11+ (for mcp-arangodb-async)

Choosing this one

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — arango_set_focused_database, arango_get_focused_database, arango_list_available_databases and 11 more — is a fair guide to whether it matches your workflow. It is maintained by PCfVW; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
arango_set_focused_databaseSet focused database for session
arango_get_focused_databaseGet currently focused database
arango_list_available_databasesList all configured databases
arango_get_database_resolutionShow database resolution algorithm
arango_queryExecute AQL queries
arango_list_collectionsList all collections
arango_insertInsert documents
arango_updateUpdate documents
arango_removeRemove documents
arango_create_collectionCreate collections
arango_backupBackup collections
arango_list_indexesList indexes
arango_create_indexCreate indexes
arango_delete_indexDelete indexes

How to install the MCP MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Docker and Docker Compose installed - Python 3.11+ (for mcp-arangodb-async)
VariableDescriptionRequired
ARANGO_URLEndpoint or connection string the server talks to.Yes
ARANGO_DBConfiguration value read at startup.Optional
ARANGO_USERNAMEConfiguration value read at startup.Optional
ARANGO_PASSWORDConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP to arango set focused database.
  • Use MCP to arango get focused database.
  • Use MCP to arango list available databases.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (arango_set_focused_database, arango_get_focused_database, arango_list_available_databases, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.