# Engraphy

> Engraphy — devon-clarkk-engraphy. Use this tool when you need to efficiently manage and retrieve complex knowledge graphs, solving problems of data duplication and isolation in AI systems. Engraphy enables AI agents to maintain a self-hosted typed knowledge graph with features like deduplicating writes and hybrid retrieval. It is ideal for use cases requiring robust data management and secure isolation, with inputs including knowledge graph data and outputs including queried results and updated graphs.

Canonical page: https://skillsregistry.net/skills/devon-clarkk-engraphy  
JSON: https://api.skillsregistry.net/v1/skills/devon-clarkk-engraphy

## Description

Enables AI agents to maintain a self-hosted typed knowledge graph on Postgres and pgvector over MCP, with deduplicating writes, hybrid retrieval, and database-enforced isolation.

## Trust

- **Trust score (0–1):** 0.24
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vox4wdpaq2)
- **Repository:** <https://github.com/devon-clarkk/engraphy>

## 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": "devon-clarkk-engraphy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/devon-clarkk-engraphy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/devon-clarkk-engraphy/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