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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。