# agentic-graph-rag

> agentic-graph-rag — imagines-nummorum-agentic-graph-rag. Use this tool when you need to perform complex graph-based reasoning and analysis, solving problems related to network relationships and entity interactions. It provides a research prototype for agentic reasoning, utilizing GraphRAG-driven approaches and integrating with technologies like ADK, MCP, and Neo4j. Ideal for use cases involving graph data, entity disambiguation, and knowledge graph construction, with inputs including graph structures and outputs comprising insightful relationship analyses.

Canonical page: https://skillsregistry.net/skills/imagines-nummorum-agentic-graph-rag  
JSON: https://api.skillsregistry.net/v1/skills/imagines-nummorum-agentic-graph-rag

## Description

GraphRAG-Driven Agentic Reasoning: A Research Prototype using ADK, MCP, and Neo4j

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/imagines-nummorum/agentic-graph-rag)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "imagines-nummorum-agentic-graph-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/imagines-nummorum-agentic-graph-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/imagines-nummorum-agentic-graph-rag/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt