skills.rest
cardox6
cardox6COMMUNITY
Explore all skills by this author →
GitHub

neo4j-aura-agent-skill

Create, configure, and invoke Neo4j Aura Agents via the v2beta1 REST API.

Updated Aug 25, 2026
Search Tags:#agent#vector search#aura#rest api#neo4j#cypher#graphrag
One-click install
npx skills add https://github.com/cardox6/steuer-graph --skill neo4j-aura-agent-skill-cardox6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neo4j-aura-agent-skill
Source: https://github.com/cardox6/steuer-graph/tree/main/.agents/skills/neo4j-aura-agent-skill
Command: npx skills add https://github.com/cardox6/steuer-graph --skill neo4j-aura-agent-skill-cardox6

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires neo4j, neo4j-graphrag, python-dotenv, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve? Setting up a GraphRAG agent on Neo4j AuraDB requires coordinating OAuth2 authentication, organization/project scoping, schema inspection, tool configuration, and REST API calls — a multi-step process that is error-prone when done manually. ## Core Features & Use Cases - Agent Lifecycle Management: Create, list, get, update (PATCH), delete, and invoke Aura Agents through the v2beta1 REST API using ready-made Python scripts. - Schema-Aware Tool Design: Fetch the AuraDB graph schema with typed properties, low-cardinality value lists, and vector index metadata to correctly configure CypherTemplate, SimilaritySearch, and Text2Cypher tools. - Deployment & Invocation: Set system prompts, control visibility (private/public), expose agents as REST or MCP endpoints, and test them with natural language queries. - Use Case: You have an AuraDB instance loaded with contract data and want a natural-language Q&A agent. The skill fetches the schema, guides tool selection with the user, creates the agent, and verifies it with a test invocation. ## Quick Start Ask the assistant to create an Aura Agent on your AuraDB instance, starting by verifying your Aura API credentials and fetching the graph schema with the provided scripts.

Frequently Asked Questions about neo4j-aura-agent-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Neo4j Aura Agent with the REST API?▼

Obtain an OAuth2 token with your Aura client credentials, then POST a config with name, description, dbid, is_private, and at least one tool to the v2beta1 agents endpoint. The manage_agent.py script wraps this with a create command reading a JSON config file.

What tool types can an Aura Agent use?▼

Aura Agents support three tool types: CypherTemplate for parameterized lookups, SimilaritySearch for vector-based semantic search over a VECTOR index, and Text2Cypher for open-ended aggregation and discovery queries.

Does SimilaritySearch require a vector index in AuraDB?▼

Yes, SimilaritySearch requires an existing VECTOR index in ONLINE state. The fetch_schema.py script detects vector indexes and their dimensions; if none exist, you must create one first with a vector index skill before adding the tool.

Why does agent creation return a 401 or 403 error?▼

A 401 means the OAuth2 token expired (TTL is 3600 seconds), so re-authenticate with your client credentials. A 403 on create means your account lacks project admin access in the Aura console.

Can an Aura Agent be exposed as an MCP server?▼

Yes, set is_mcp_enabled to true in the agent config to get an MCP endpoint link alongside the REST invoke endpoint. Both endpoints use the same OAuth2 bearer token from Aura API credentials.

When should I use Cypher instead of an Aura Agent?▼

Use direct Cypher when you need full query control, low-latency lookups, or write operations. Aura Agents are intended for natural language question answering over the graph, not deterministic data manipulation.

Related Skills

Explore More Software Engineering Skills→
neo4j-contribneo4j-contrib
101

neo4j-aura-agent-skill

Manages the full lifecycle of Neo4j Aura Agents with AuraDB schema and CypherTemplate, SimilaritySearch, Text2Cypher tools.

Official
Advanced
ldclabsldclabs
71

anda-brain

Encode conversations into a persistent knowledge graph with REST and MCP interfaces.

Official
Advanced
neo4j-contribneo4j-contrib
101

neo4j-vector-index-skill

Create Neo4j vector indexes and query nearest neighbors via SEARCH clause.

Official
Advanced
neo4j-contribneo4j-contrib
101

neo4j-migration-skill

Migrate Neo4j driver code and Cypher queries to Cypher 25 syntax.

Official
Advanced