Atom of ThoughtsCAUTION
MCP server for structured AI reasoning — decompose problems into atomic thoughts with dependency graphs, confidence tracking, and interactive D3.js visualization
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Structured reasoning for LLMs. Decompose, track confidence, visualize, approve.
[](https://www.npmjs.com/package/@dioptx/mcp-atom-of-thoughts) [](LICENSE) [](package.json) [](#development) [](tsconfig.json)
Quickstart
1. Add to your MCP config:
{
"mcpServers": {
"atom-of-thoughts": {
"command": "npx",
"args": ["-y", "@dioptx/mcp-atom-of-thoughts"]
}
}
}2. Restart your client.
3. Ask the model to reason something through:
"Use AoT-fast to think through whether we should use JWT or session-based auth for the API."
The model breaks the problem into five kinds of atoms (premise, reasoning, hypothesis, verification, conclusion), each tagged with a confidence score. You get a structured chain you can audit, not a black-box answer.
[!TIP] Works with Claude Code, Cursor, Windsurf, or any MCP-aware client.
Install
npx (recommended; zero install, always latest)
{ "command": "npx", "args": ["-y", "@dioptx/mcp-atom-of-thoughts"] }npm global
npm install -g @dioptx/mcp-atom-of-thoughts
{ "command": "mcp-atom-of-thoughts" }Smithery
npx -y @smithery/cli install @dioptx/mcp-atom-of-thoughts --client claude
Docker
docker build -t aot .
{ "command": "docker", "args": ["run", "-i", "--rm", "aot"] }How it works
graph LR P["P · Premise"]:::premise --> R["R · Reasoning"]:::rea
2c142d17bf33OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-atom-of-thoughts -- npx -y @dioptx/[email protected]
{
"mcpServers": {
"mcp-atom-of-thoughts": {
"command": "npx",
"args": [
"-y",
"@dioptx/[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
AoT-fast | read | Default structured reasoning. Decomposes problems into atomic thoughts with dependency tracking. Depth 3. Use for: think-through, analyze, reason about tradeoffs, debug root causes, evaluate alternatives, make decisions. Most reasoning tasks belong here. Trigger phrases: |
AoT-full | read | Deep structured reasoning with decomposition-contraction. Depth 5. Use for: implementation plans, architecture decisions, multi-step verification, problems that decompose into sub-problems. Trigger phrases: |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
resolve({ port: addr.port, url: `http://127.0.0.1:${addr.port}/approval` });return this.boundPort ? `http://127.0.0.1:${this.boundPort}/approval` : null;? `approval=http://127.0.0.1:${callbackInfo.port}`payload-shape.test.ts
- The HTML embeds a callback URL (`http://127.0.0.1:<port>/approval`) that the approve/reject UI POSTs to.
- `visualization.ts`: when generating HTML, embed the callback URL (`http://127.0.0.1:<port>/approval`) and `sessionId` so the browser POSTs back automatically on approve/reject.
@modelcontextprotocol/sdk, chalk, zod, @types/node, typescript, vitest
assets/demo-customize.cast
assets/demo.png
Gates applied: no_behavioural_pass.
2c142d17bf33full audit observations/trust-audit/mcp-server/dioptx__atom-of-thoughts-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 2c142d17bf33 | CAUTION | B | 89 | first audit |
Questions
What is the Atom of Thoughts MCP server?
MCP server for structured AI reasoning — decompose problems into atomic thoughts with dependency graphs, confidence tracking, and interactive D3.js visualization
What tools does Atom of Thoughts expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Atom of Thoughts safe to connect to an agent?
With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Atom of Thoughts need?
No credential environment variables were found in its source, so it appears to need none.
How does Atom of Thoughts run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @dioptx/mcp-atom-of-thoughts at 3.0.0.
How current is this page?
The grade is for one exact copy of the source (2c142d17bf33), read on 2026-10-07. The repository is watched and re-audited when it changes.