# hubmesh

> hubmesh — demigoddsk-hubmesh. Use this tool when you need to efficiently retrieve relevant graph data from a vector database, leveraging centrality-aware planning to optimize query performance. It solves problems related to graph data retrieval, indexing, and querying, particularly in applications where low-latency and high-precision are crucial. The hubmesh tool accepts graph queries as input and returns relevant graph data as output, making it suitable for use cases such as knowledge graph querying and graph-based recommendation systems.

Canonical page: https://skillsregistry.net/skills/demigoddsk-hubmesh  
JSON: https://api.skillsregistry.net/v1/skills/demigoddsk-hubmesh

## Description

Centrality-aware GraphRAG retrieval planner — drop-in layer over any vector DB. Zero LLM in the query path; MCP server included.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/DemigodDSK/hubmesh)

## 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": "demigoddsk-hubmesh"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/demigoddsk-hubmesh` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/demigoddsk-hubmesh/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