Log inSubmit server
MCP Thinkgate logo

MCP Thinkgate

Classifies prompts into fast, think, or ultrathink tiers and recommends Claude model and effort settings.

InstallRepository
Full README Compare alternatives Embed widget Claim this listing

Install MCP Thinkgate

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-thinkgate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-thinkgate"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y mcp-thinkgate

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 6d ago.

Overview

mcp-thinkgate MCP server classifies prompt complexity and recommends a Claude model plus thinking effort before an agent responds. It uses a no-key rule-based fallback or an optional Anthropic Haiku classification call, returning fast, think, or ultrathink with confidence and reasoning. Reach for it when one agent handles both routine requests and tasks needing architecture, debugging, or deeper analysis. The result is advisory, so the host must apply any model or effort changes.

Use cases

  • Route simple status questions to low-effort Claude calls
  • Classify architecture and debugging prompts before execution
  • Reduce extended-thinking use for routine agent messages
  • Add automatic effort selection to a Claude agent framework

Key features

  • Three-tier prompt complexity classification
  • Claude model and effort recommendations
  • Rule-based fallback without an API key
  • Anthropic Haiku classification option
  • Configurable profiles and per-tier model overrides

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

5/5 checks healthy over the last 50d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · mcp-thinkgate (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads132Package downloads in the last 30 days.
Last commit3mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How MCP Thinkgate works

What mcp-thinkgate MCP server does

mcp-thinkgate MCP server evaluates an incoming prompt and assigns one of three complexity tiers: fast, think, or ultrathink. Each tier maps to an effort level: none, medium, or maximum/high. The result also includes a confidence value and a one-sentence explanation of the classification.

The intended use is automatic routing for Claude-based agents that receive a mixed workload. Short factual questions and simple edits can use the fast tier, while architecture work, debugging, multi-step analysis, system design, proofs, and other open-ended tasks can receive more reasoning effort. The server does not perform the requested task itself; it advises the surrounding agent about how to run it.

How it works

With an Anthropic API key, the classifier sends the prompt through a relatively inexpensive Haiku call, then returns a routing recommendation. Without a key, mcp-thinkgate MCP server uses a rule-based fallback, which is free and preferred for automatic routing when an API call is not wanted.

Profiles determine the model mapping for each tier. The default claude profile maps the tiers to Haiku, Sonnet, and Opus model variants. openrouter-cost and openrouter-balanced provide alternative mappings. A caller can select a profile through THINKGATE_PROFILE or by passing a profile to classifyPrompt; individual tier models can also be overridden.

The MCP result is only a recommendation. The host or agent integration must actually select the model and apply the effort setting. The reference TinyClaw integration does this before invoking the Claude CLI.

Setup and configuration

The server requires Node.js 20 or newer. For an MCP client, configure it as an npx -y mcp-thinkgate stdio server, then restart the client. The supplied example targets Claude Desktop and Claude Code. An ANTHROPIC_API_KEY may be provided to enable API-backed classification, but it is optional because rule-based classification works without one.

For application code, install the npm package and import classifyPrompt. Pass the user message and optionally an Anthropic key; calling it without the key uses the fallback. setLogLevel can lower logging from the default info level to error, with logs written to stderr.

Tools and capabilities

  • Classifies prompts into fast, think, and ultrathink tiers.
  • Reports recommended effort, confidence, and reasoning.
  • Supports Claude and two OpenRouter model-mapping profiles.
  • Allows profile selection and per-tier model overrides.
  • Runs through MCP or as the classifyPrompt npm library function.
  • Provides a no-key rule-based fallback.

Limitations and notes

mcp-thinkgate MCP server does not automatically change the host model or Claude effort setting. Integrations must consume its output and perform that switch. API-backed classification requires an Anthropic key, while the fallback does not. The package is designed for Node.js 20 or later.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about MCP Thinkgate

mcp-thinkgate is an MCP server that classifies prompts for Claude agents and recommends a model and thinking effort. Its main tools are the MCP classification capability and the classifyPrompt library function, which return fast, think, or ultrathink tiers with confidence and reasoning. It can use Anthropic or rule-based classification.

Install it for an MCP client by configuring the command npx with arguments -y and mcp-thinkgate, then restart the client. For library use, run npm install mcp-thinkgate in a Node.js 20-or-newer project.

No, mcp-thinkgate does not require an Anthropic API key. Without one, it uses a rule-based fallback for classification. Providing ANTHROPIC_API_KEY enables the optional Anthropic Haiku classification path.

mcp-thinkgate does not change the model by itself. It returns a recommended tier, effort, and model based on the prompt, so the host integration must apply those settings. The README identifies TinyClaw as a reference integration that sets Claude CLI effort before invocation.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Thinkgate AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-thinkgate?style=directory)](https://allmcps.com/mcp/mcp-thinkgate)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-thinkgate"><img src="https://allmcps.com/api/badge/mcp-thinkgate?style=directory" alt="MCP Thinkgate on AllMCPs" /></a>