# thought-graph-mcp

> Use this tool when you need to visualize and refine complex reasoning processes, breaking down thoughts into editable steps to improve transparency and accuracy. It solves problems of opaque decision-making and rigid thinking by allowing revision of individual steps, and accepts natural language inputs to produce graphical outputs. Ideal for use in applications requiring explainable and adjustable reasoning, such as knowledge graph construction or cognitive modeling.

Canonical page: https://skillsregistry.net/skills/jeff-ong-thought-graph-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jeff-ong-thought-graph-mcp

## Description

Enables LLMs to break down reasoning into an explicit, editable graph of thinking steps, with visualizations and the ability to revise individual steps.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/fpvabx3mdc)
- **Repository:** <https://github.com/jeff-ong/thought-graph-mcp>

## 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": "jeff-ong-thought-graph-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jeff-ong-thought-graph-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jeff-ong-thought-graph-mcp/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