Oscar
Enables users to ask questions about Neo4j, Cypher, GraphRAG, and ontology engineering, providing answers grounded in official Neo4j documentation with citations.
README
Oscar — the Knowledge Graph Expert Agent
By Astra AI · oscar.theastraway.com
Oscar is an AI expert agent for knowledge graphs, Neo4j, GraphRAG, Cypher, and ontology engineering. He is grounded in the complete official Neo4j documentation corpus — Cypher Manual, Operations Manual, Graph Data Science (GDS), APOC, GenAI plugin, Getting Started, Drivers, and Aura — and answers with citations to the official docs. A 24/7 ingestion loop of new ML research papers keeps his knowledge current.
No hallucinated Cypher. No stale answers. Receipts on everything.
Quickstart — MCP (2 minutes, free, no signup)
Claude Code
claude mcp add oscar -- npx -y github:theastraway/oscar
Claude Desktop / Cursor / any MCP client
Add to your MCP config (claude_desktop_config.json, .cursor/mcp.json, etc.):
{
"mcpServers": {
"oscar": {
"command": "npx",
"args": ["-y", "github:theastraway/oscar"]
}
}
}
That's it. Your agent now has an ask_oscar tool. Try:
"Ask Oscar how to create a vector index in Neo4j."
Pro tier
Set your key and the limits disappear:
{
"mcpServers": {
"oscar": {
"command": "npx",
"args": ["-y", "github:theastraway/oscar"],
"env": { "OSCAR_API_KEY": "your-key-here" }
}
}
}
Get a key at oscar.theastraway.com.
Quickstart — REST API
curl -X POST https://oscar.theastraway.com/api/ask \
-H "Content-Type: application/json" \
-d '{"question": "When should I use a vector index vs a full-text index in Neo4j?"}'
Pro (unlimited):
curl -X POST https://oscar.theastraway.com/api/ask \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OSCAR_API_KEY" \
-d '{"question": "Design a GraphRAG retrieval strategy for a legal-documents graph."}'
Response:
{
"answer": "…grounded answer with citations to the official Neo4j docs…",
"mode": "hybrid",
"tier": "free",
"remaining_today": 9
}
What Oscar knows
| Corpus | Coverage |
|---|---|
| Cypher Manual | Full query-language syntax and semantics |
| Operations Manual | Deployment, clustering, backup, security |
| Graph Data Science (GDS) | Algorithms, embeddings, pipelines, projections |
| APOC | The real procedures — no inventions |
| GenAI plugin | Vector indexes, embeddings, similarity functions |
| Getting Started + Drivers | Modeling basics, language drivers |
| Aura | Managed-cloud specifics |
| ML research feed | New papers ingested 24/7 (GraphRAG, agent memory, graph ML) |
Oscar is backed by MIND, Astra AI's persistent memory and knowledge-graph platform.
Pricing
| Tier | Price | Includes |
|---|---|---|
| Free | $0 | 10 cited queries/day via API & MCP — no signup |
| Pro | $20/mo | Unlimited fair-use queries, priority latency |
| Team / API | $99/mo | 5 seats, dedicated API keys, higher rate limits |
Upgrade at oscar.theastraway.com.
Repo layout
index.js— the MCP server (stdio).npx -y github:theastraway/oscarapi/ask.js— the hosted query API (Vercel serverless)public/— oscar.theastraway.comdocs/— MCP setup · REST APIexamples/— curl, Python
Environment variables
| Var | Where | Purpose |
|---|---|---|
OSCAR_API_KEY |
MCP client env | Pro key (optional — free tier needs nothing) |
OSCAR_API_URL |
MCP client env | Override endpoint (testing/self-host) |
License
MIT © Astra AI, Inc.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.