DA

debatetalk-ai/mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

1 stars 0 forks 质量 77 趋势 5MIT

Official MCP server and CLI for DebateTalk: run structured multi-model AI debates from Claude, Cursor, or your terminal.

概览

Official MCP server and CLI for DebateTalk — run structured multi-model AI debates from your AI assistant or terminal. DebateTalk makes multiple AI models argue a question independently, challenge each other's reasoning, and converge on a structured synthesis: - — connect Claude Desktop, Cursor, or any MCP-compatible client to DebateTalk - — run debates and check model status from the terminal - — real-time round-by-round updates via MCP logging notifications - — every debate shows cost and a shareable URL - run_debate, get_model_status, recommend_models, estimate_cost, get_history — dt models works instantly, no signup needed. See which models are online and their live latency. For debates, recommendations, and history you need an API key — free accounts include one at console.debatetalk.ai/api-keys. This gives you the dt CLI and the MCP server. Get a key at console.debatetalk.ai/api-keys. Free accounts include 1 API key — sign up at console.debatetalk.ai.

README

以下为原文 README 节选,完整内容请查看原文。

DebateTalk MCP

Official MCP server and CLI for DebateTalk — run structured multi-model AI debates from your AI assistant or terminal.

DebateTalk makes multiple AI models argue a question independently, challenge each other’s reasoning, and converge on a structured synthesis: Strong Ground, Fault Lines, Blind Spots, and Your Call.


Demo


Features

  • MCP server — connect Claude Desktop, Cursor, or any MCP-compatible client to DebateTalk
  • CLI — run debates and check model status from the terminal
  • Streaming progress — real-time round-by-round updates via MCP logging notifications
  • Cost & share links — every debate shows cost and a shareable URL
  • 5 tools: run_debate, get_model_status, recommend_models, estimate_cost, get_history

Try without an API key — dt models works instantly, no signup needed. See which models are online and their live latency. For debates, recommendations, and history you need an API key — free accounts include one at console.debatetalk.ai/api-keys.


Install

npm install -g @debatetalk/mcp

This gives you the dt CLI and the MCP server.

Set your API key:

export DEBATETALK_API_KEY=dt_your_key_here

Get a key at console.debatetalk.ai/api-keys. Free accounts include 1 API key — sign up at console.debatetalk.ai.


CLI

Run a debate:

dt debate "Should we adopt microservices?"

Example output:

- Starting debate…
✔ Debate complete

"Should we adopt microservices?"
Cost: $0.0842

━━━ STRONG GROUND ━━━
1. Microservices suit orgs with 50+ engineers and distinct team boundaries
2. Monoliths are simpler to operate at small scale
3. Migration costs are consistently underestimated

━━━ FAULT LINES ━━━
1. If teams need independent deploy cycles, then microservices — otherwise monolith
2. If operational maturity is low, then monolith — otherwise microservices are viable
3. If data consistency is critical, then monolith avoids distributed transaction pain

━━━ BLIND SPOTS ━━━
1. Cost of distributed tracing and observability tooling
2. Team cognitive load increases with service count
3. Shared database patterns can bridge the gap

━━━ YOUR CALL ━━━
1. Do you have dedicated platform engineering?
在 GitHub 查看完整 README

安装

npx -y @debatetalk/mcp
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "dt": { "command": "npx", "args": ["-y", "@debatetalk/mcp"], "env": { "DEBATETALK_API_KEY": "dt_your_key_here" } } } }