What is debug-thinking?

A local MCP server for structured debugging with problem trees and repeated cycles of forming hypotheses, testing them, and learning from the results.

Breaking down a problem, listing possible solutions, designing checks for competing explanations, and recording what each experiment shows.

It gives debugging work a recorded reasoning structure, helping separate possible causes from experiments and findings.

debug-thinking — MCP server by tosssssy

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/tosssssy/mcp-server-debug-thinking/debug-thinking

Clone the repo

git clone --depth 1 https://github.com/tosssssy/mcp-server-debug-thinking

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

debug-thinking 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

udacity-commit — 86% identical, 8 lines differ

.mcp.json · 8 lines

What it actually says

{
  "debug-thinking": {
    "command": "npx",
    "args": [
      "mcp-server-debug-thinking@latest"
    ]
  }
}

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.

yesterday First seen · 8 lines scan A 612ff0d1f362

Subscribe to this mod's changes

debug-thinking is an MCP server published in the GitHub repository tosssssy/mcp-server-debug-thinking (4 stars, last pushed 7mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.

Debugging Testing

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

reference-langchain

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured

supabase

Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.

supabase/supabase · not measured

playwright-test

A high-level API to automate web browsers. Runs locally from the playwright npm package.

microsoft/playwright · not measured

mcp-search

MCP server "mcp-search" as configured in thedotmack/claude-mem. Runs const f=require('fs'),p=require('path'),o=require('os'),c=require('child_process');const h=o.homedir();const C=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude');const E=process.env.CLAUDE_PLUGIN_ROOT||process.env.PLUGIN_ROOT||'';const…

thedotmack/claude-mem · not measured

browser-use

Make websites accessible for AI agents. Runs locally from the browser-use Python package.

browser-use/browser-use · not measured