
Adds consensus measurement tools to Claude using Fleiss' kappa and bootstrap confidence intervals to check if AI models agree with themselves or each other. The eight MCP tools let you run multi-model evaluations across Bedrock, OpenAI, and Gemini, generate statistical reports, compare runs over time, and estimate costs before executing. The self-consistency mode is handy because it uses MCP Sampling to test the host model without external API keys. You'd reach for this when you need statistically rigorous validation that an AI is giving consistent answers, especially for high-stakes applications where agreement matters more than speed. Includes schema validation and AI-powered schema suggestion from your data.
Multi-model rating for AI evaluation: measures agreement among model raters (Fleiss' κ, Kendall's W) to find contested items for expert review.
What agreement tells you: where your raters and your criteria are consistent, and where they are not — which items are contested, and whether disagreement comes from the criteria or the raters.
What it does not tell you: that the raters are right. Agreement is reliability, not validity. Models can agree confidently on a wrong answer. Use ConKurrence to decide where an expert's judgment is needed and to diagnose your evaluation criteria — not to replace expert-labelled ground truth.
Status: maintenance mode. ConKurrence is developed by JE Vectors LLC as the evaluation instrument behind Inqura. It is not accepting purchases and carries no support commitment.
npm install -g conkurrence
Use ConKurrence as an MCP server in Claude Desktop or any MCP-compatible client:
npx conkurrence mcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"conkurrence": {
"command": "npx",
"args": ["-y", "conkurrence", "mcp"]
}
}
}
/plugin marketplace add AlligatorC0der/conkurrence
| Tool | Description |
|---|---|
conkurrence_run | Execute an evaluation across multiple AI raters |
conkurrence_report | Generate a detailed markdown report |
conkurrence_compare | Side-by-side comparison of two runs |
conkurrence_trend | Track agreement over multiple runs |
conkurrence_suggest | AI-powered schema suggestion from your data |
conkurrence_validate_schema | Validate a schema before running |
conkurrence_estimate | Estimate cost and token usage |
BUSL-1.1 — Business Source License 1.1