# graph-tool-call

> graph-tool-call — sonaiengine-graph-tool-call. Use this tool when you need to efficiently retrieve specific tools for tasks, leveraging a graph-based approach to minimize token usage and maximize accuracy. It solves the problem of tool discovery and integration for LLM agents, accepting input queries and returning relevant tool recommendations. Ideal for use cases where dependency-free, high-accuracy tool retrieval is crucial, with support for OpenAPI, MCP, and LangChain interfaces.

Canonical page: https://skillsregistry.net/skills/sonaiengine-graph-tool-call  
JSON: https://api.skillsregistry.net/v1/skills/sonaiengine-graph-tool-call

## Description

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/SonAIengine/graph-tool-call)

## 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": "sonaiengine-graph-tool-call"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sonaiengine-graph-tool-call` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sonaiengine-graph-tool-call/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