What is mcp-atom-of-thoughts CLAUDE.md?

An MCP server that helps an agent break a problem into smaller reasoning steps, track confidence, verify conclusions, and optionally display the reasoning as a graph. MCP is a standard way for an AI agent to use external tools.

Use it for decomposing complex problems, checking hypotheses, tracking reasoning sessions, exporting reasoning graphs, and viewing them as D3 visualizations.

It provides a structured record of how a conclusion was reached instead of leaving reasoning as an unorganized response.

How dioptx/mcp-atom-of-thoughts configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dioptx/mcp-atom-of-thoughts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dioptx/mcp-atom-of-thoughts/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dioptx/mcp-atom-of-thoughts

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dioptx/mcp-atom-of-thoughts/claude-md/github.svg)](https://agentmods.dev/instructions/dioptx/mcp-atom-of-thoughts/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dioptx/mcp-atom-of-thoughts/claude-md"><img src="https://agentmods.dev/badge/instructions/dioptx/mcp-atom-of-thoughts/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dioptx/mcp-atom-of-thoughts/claude-md"><img src="https://agentmods.dev/badge/instructions/dioptx/mcp-atom-of-thoughts/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 997 This file is loaded in full into every session.

When invoked 997 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00997	$0.00997
Opus 5.5	$0.00399	$0.00399
Sonnet 5.5	$0.00199	$0.00199
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash f291fe9b2f13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-atom-of-thoughts CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-atom-of-thoughts (v3)

MCP server for structured reasoning via Atom of Thoughts. Decomposes problems into atomic units (premise → reasoning → hypothesis → verification → conclusion) with confidence tracking, session scoping, and on-demand D3 visualization.

Architecture

index.ts          — MCP server entry, tool dispatch, viz attachment, approval server
atom-server.ts    — Full AoT (depth 5, decomposition-contraction) with session-scoped state
atom-light-server.ts — AoT-fast (depth 3) — extends atom-server, lighter response shape
tools.ts          — MCP tool definitions (3 tools)
types.ts          — AtomData, Session, GraphNode, GraphLink, ApprovalResult
config.ts         — CLI arg parsing (--mode, --viz, --max-depth, --output-dir, --downloads-dir)
visualization.ts  — D3.js interactive graph renderer (callback URL embedded)
graph-export.ts   — JSON export of atom graph
approval.ts       — File-based approval polling (fallback path)
approval-server.ts — Local 127.0.0.1 HTTP listener for browser → server callbacks
d3-bundle.ts      — D3 asset bundler

MCP Tools (3)

Tool	Purpose
`AoT-fast`	Default reasoning. Depth 3, auto-suggests conclusions. Set `viz:true` during planning
`AoT-full`	Deep reasoning with decomposition-contraction. Depth 5. Same shape as AoT-fast, plus decomposition controls
`atomcommands`	Lifecycle/meta: `decompose`, `complete_decomposition`, `termination_status`, `best_conclusion`, `set_max_depth`, `export`, `check_approval`, `new_session`, `switch_session`, `list_sessions`, `reset_session`

Atom Types

premise (P) → reasoning (R) → hypothesis (H) → verification (V) → conclusion (C)

Each atom: atomId, content, atomType (required), dependencies (default []), confidence (default 0.7), optional viz (default false), optional sessionId (default active session).

Sessions

All atom state scoped to a sessionId (default "default").
Auto-archive on shouldTerminate; auto-spawn fresh default-N on next zero-dep atom.
Two reasoning problems in the same MCP process do not collide.
Every response includes sessionId.

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 79 lines · 997 tokens per session scan A f291fe9b2f13

Subscribe to this mod's changes

mcp-atom-of-thoughts CLAUDE.md is an instructions file published in the GitHub repository dioptx/mcp-atom-of-thoughts (95 stars, last pushed 29d ago), licensed MIT. It adds 997 tokens to every session, about $0.0040 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Planning agent-infra ai-reasoning claude d3 developer-tools mcp-server

mcp-atom-of-thoughts CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-atom-of-thoughts CLAUDE.mddioptx/mcp-atom-of-thoughts	Instructions file	95	29d ago	MIT	A	997	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-atom-of-thoughts: Instructions file for Claude Code