MCP Thinkgate

Name: MCP Thinkgate
Author: tjp2021

by tjp2021version 0.1.1i★ –iRuns on your computer

Registry nameio.github.tjp2021/mcp-thinkgate

Install

Overview

Description from the maker (original English)

Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Other
You need to fill in: ANTHROPIC_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: ANTHROPIC_API_KEY

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "thinkgate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-thinkgate"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add thinkgate --env ANTHROPIC_API_KEY=your-value -- npx -y mcp-thinkgate

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "thinkgate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-thinkgate"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "thinkgate": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-thinkgate"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

ANTHROPIC_API_KEY secret env
Optional. Enables AI-powered classification via Haiku (more accurate). Falls back to rule-based classification if not provided. Get a key at https://console.anthropic.com

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account tjp2021, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

More stars than 0% of the other 32655 servers in this category
Published to the registry more recently than 2% of the other 32655 servers in this category
Basic checks equal to or better than 100% of the other 32655 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is MCP Thinkgate safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: ANTHROPIC_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.1.1) reached the registry 9 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, SuperCollider

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago

Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated 2 days ago

Install

SuperCollider

by Tok

Make sound with SuperCollider: synths, drums, chords, melodies and soundscapes over OSC.

Runs on your computerUpdated today

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

ThinkGate

Automatic reasoning mode selection for Claude agents.

The problem

You built an AI agent. It handles everything — status checks, quick lookups, complex architecture questions, deep debugging sessions. But under the hood it runs every single message through the same model with the same thinking settings.

That means you're burning extended thinking tokens on "what time is it in Tokyo?" and getting shallow answers on "help me design the entire auth system."

You could manually tag requests — ULTRATHINK: before the hard ones. But you forget. Your users definitely won't do it. And if you're building agents for other people, you can't train every end user to manage thinking modes.

ThinkGate fixes this at the infrastructure layer. It sits between the incoming message and your model call, classifies the complexity in ~200ms, and returns exactly which model and thinking depth to use. Automatically. Every time.

Who this is for

Agent builders running Claude on a mix of simple and complex tasks who are tired of one-size-fits-all model settings
Teams running 24/7 agents (WhatsApp bots, Slack assistants, Telegram agents) where message complexity varies wildly and cost/latency actually matters
Anyone who's ever typed `ULTRATHINK` manually and thought: this should just happen on its own

How it works

Incoming message

↓ Haiku call (~200ms, ~$0.0001) "How complex is this?" ↓ fast → no extended thinking think → medium effort ultrathink → max effort ↓ Claude runs with the right settings

A cheap, fast Haiku call reads your prompt and decides which tier it needs. Then your main Claude call runs with the right effort level. You pay almost nothing for the classification, and save real money (and latency) on the 60%+ of messages that don't need extended reasoning.

The classifier is the IP here — not which model runs it. Three tiers. A system prompt trained on the boundary between "this needs thinking" and "this doesn't." Works out of the box.

Tiers

Tier	Claude effort	When
`fast`	`none`	Factual, conversational, simple edits
`think`	`medium`	Architecture, debugging, multi-step analysis
`ultrathink`	`max` / `high`	System design, proofs, open-ended complexity

Profiles (model mapping)

Set THINKGATE_PROFILE or pass { profile } to classifyPrompt:

Profile	fast	think	ultrathink
`claude` (default)	`claude-haiku-4-5-...`	`claude-sonnet-4-6`	`claude-opus-4-6`
`openrouter-cost`	`google/gemini-2.5-flash`	`anthropic/claude-sonnet-4.5`	`anthropic/claude-opus-4.6`
`openrouter-balanced`	`anthropic/claude-haiku-4.5`	`anthropic/claude-sonnet-4.5`	`anthropic/claude-opus-4.6`

Per-tier overrides: THINKGATE_FAST_MODEL, THINKGATE_THINK_MODEL, THINKGATE_ULTRA_MODEL.

Cost note: the MCP tool is advisory. Hosts must actually switch models. Pi does this via ~/.pi/agent/extensions/thinkgate-router.ts + thinkgate.json.

Rule mode (no API key) is free and preferred for auto-routing. Long checklist pastes no longer auto-upgrade to THINK.

Use as an MCP tool (Claude Desktop / Claude Code)

Add to ~/.claude/settings.json (Claude Code) or ~/Library/Application Support/Claude/claude_desktop_config.json (Claude Desktop):

"mcpServers": { "thinkgate": { "command": "npx", "args": ["-y", "mcp-thinkgate"], "env": { "ANTHROPIC_API_KEY": "your-api-key-here" } } } }

Restart Claude. Now you can ask it to classify before it answers:

"Before responding, classify the complexity of this task: design a rate limiter for a public API"

Tier: think

Effort: medium Suggested model: claude-sonnet-4-6 Confidence: 92% Why: Requires structured design reasoning and trade-off analysis, but has well-defined scope.

Use as a library (agent frameworks)

Install:

npm install mcp-thinkgate

Import and use:

import { classifyPrompt, setLogLevel } from 'mcp-thinkgate';

// Optional: silence logs (default level is 'info', writes to stderr) setLogLevel('error');

const result = await classifyPrompt(userMessage, process.env.ANTHROPIC_API_KEY!);

// result.tier → 'fast' | 'think' | 'ultrathink' // result.effort → 'none' | 'medium' | 'max' // result.confidence → 0.0 - 1.0 // result.reasoning → one sentence explanation

// Works without an API key too (rule-based fallback): const quickResult = await classifyPrompt(userMessage);

Reference implementation: TinyClaw

TinyClaw is an open-source multi-agent framework for Claude. ThinkGate is wired into its invokeAgent() function — every message is automatically classified before the Claude CLI runs, and --effort is set accordingly.

Three lines added. Zero config required. Every agent in every team automatically gets the right thinking depth.

See the integration at src/lib/invoke.ts.

Requirements

Node.js 20+
Anthropic API key (optional — falls back to rule-based classification)

Local development

git clone https://github.com/tjp2021/mcp-thinkgate

cd mcp-thinkgate npm install npm test npm run build

Contributing

See CONTRIBUTING.md for dev setup, commands, and PR process.

Security

See SECURITY.md for vulnerability reporting.

License

MIT — see LICENSE

MCP Thinkgate

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Otheri

Common questions

Alternatives

Spec Driven Development

Remote Desktop Commander

SuperCollider

README from the maker

ThinkGate

The problem

Who this is for

How it works

Tiers

Profiles (model mapping)

Use as an MCP tool (Claude Desktop / Claude Code)

Use as a library (agent frameworks)

Reference implementation: TinyClaw

Requirements

Local development

Contributing

Security

License