kongen-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@kongen-mcp Score this prompt: What is gravity?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
kongen-mcp
MCP (Model Context Protocol) server for the Kongen Labs Pattern Intelligence API.
Connects Claude Code, Cursor, Windsurf, and any MCP-compatible client to Kongen's cross-domain pattern intelligence — reasoning regime detection, structural transfer scoring, and intelligent model routing.
Tools
Tool | Description | Cost |
| Detect reasoning regime and optimal token budget for a prompt | 1 KT |
| Score a structural signature against cross-domain reference patterns | 50 KT |
| Check your token balance and usage | 0 KT |
| Recommend Haiku/Sonnet/Opus based on prompt complexity | 1 KT |
Related MCP server: claude-patent-creator
Installation
pip install kongenlabs-mcpOr install from source:
git clone https://github.com/kongen-labs/kongen-mcp.git
cd kongen-mcp
pip install .Configuration
Get your API key at kongenlabs.life.
Claude Code
Add with the CLI:
claude mcp add kongen -- kongen-mcpThen set your API key when prompted, or add it manually to .claude/mcp.json:
{
"mcpServers": {
"kongen": {
"command": "kongen-mcp",
"env": {
"KONGEN_API_KEY": "kl_live_..."
}
}
}
}Cursor
Open Settings > MCP > Add Server
Name:
kongenCommand:
kongen-mcpEnvironment variables:
KONGEN_API_KEY: your API key
Windsurf
Add to your MCP configuration:
{
"mcpServers": {
"kongen": {
"command": "kongen-mcp",
"env": {
"KONGEN_API_KEY": "kl_live_..."
}
}
}
}Custom base URL
To point the server at a different API endpoint (for example a local proxy), set KONGEN_API_BASE_URL:
{
"mcpServers": {
"kongen": {
"command": "kongen-mcp",
"env": {
"KONGEN_API_KEY": "kl_test_...",
"KONGEN_API_BASE_URL": "http://localhost:8000"
}
}
}
}Usage examples
Once configured, the tools are available to your AI assistant. Examples of what you can ask:
Prompt scoring:
"Score this prompt for complexity: Prove that the square root of 2 is irrational using proof by contradiction."
Model routing:
"Which Claude model should I use for this task: Summarize this 3-line email."
Transfer scoring:
"Score this structural signature against cross-domain patterns."
Usage check:
"How many Kongen tokens do I have left?"
Environment variables
Variable | Required | Default | Description |
| Yes | — | Your Kongen API key ( |
| No |
| API base URL override |
License
MIT
Available Tools
4 toolscheck_usageA
Check your Kongen Token balance, usage in the current billing cycle, and active plan. No token cost.
Inputs: no named parameters.
route_modelA
Recommend which Claude model (Haiku/Sonnet/Opus) to use for a given prompt based on its reasoning complexity. Internally scores the prompt with Logic, then maps the detected regime to a model recommendation with estimated cost savings. Costs 1 Kongen Token.
Inputs: text (required).
score_promptB
Score a text prompt for reasoning complexity using Kongen's Logic engine. Returns the detected reasoning regime (trivial/fast/moderate/deep/exhaustive), a confidence adjustment factor, and recommended token budget. Costs 1 Kongen Token.
Inputs: text (required), model_hint.
transfer_scoreA
Score a 7-dimensional signal vector against reference patterns. Returns pattern classification, confidence, confidence adjustment, and supporting evidence. Costs 50 Kongen Tokens.
Inputs: complexity (required), constraint (required), boundary (required), coherence (required), +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: checking usage, recommending models, scoring prompts, and scoring transfer vectors. No overlapping functionality.
All tool names follow a consistent verb_noun pattern in snake_case (check_usage, route_model, score_prompt, transfer_score), making them predictable.
With 4 tools, the set is well-scoped for the server's purpose, covering core operations without being too thin or bloated.
The tools cover primary use cases (check usage, route/score prompts, transfer scoring). Minor gaps like account management or token budget adjustments are missing but not critical for the core workflow.
Maintenance
Related MCP Connectors
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Connect AI clients to your Dactic work context through a hosted MCP service.
21-framework people intelligence and compatibility scoring for any MCP client.
Hosted MCP server for pre-action AI governance verdicts, model routing, and evidence verification.
41
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceConnects MindReader knowledge graph to MCP clients, enabling AI assistants with persistent memory and entity/relationship management.-
- FlicenseNot gradedqualityAmaintenanceExposes 20+ MCP tools that let clients query MPEP/USC/CFR rules through hybrid vector and lexical search, run prior-art searches across 100M+ patents via Google BigQuery, flag compliance problems in draft claims and applications, and generate patent-style diagrams. It works programmatically from any MCP-compatible client to support drafting and analysis workflows.-
- FlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to search MPEP/USC/CFR regulations, query 100M+ patents for prior art, run automated 35 USC 112 compliance checks, and generate patent-style diagrams.-
- FlicenseNot gradedqualityAmaintenanceEnables MCP-compatible clients to search patent rules and prior art across MPEP/USC/CFR and 100M+ patents, run automated 35 USC 112 compliance checks, and generate patent-style diagrams.-