Back to Home
Infatoshi icon

thinkingcap

Verified Safe

by Infatoshi

Overview

A multi-agent research MCP server that runs multiple LLM providers in parallel and synthesizes their responses to a given query.

Installation

Run Command
npx -y thinkingcap openrouter:moonshotai/kimi-k2-thinking groq:moonshotai/kimi-k2-instruct-0905 cerebras:zai-glm-4.6 xai:grok-4-fast

Environment Variables

  • OPENAI_API_KEY
  • OPENROUTER_API_KEY
  • GROQ_API_KEY
  • CEREBRAS_API_KEY
  • XAI_API_KEY
  • ANTHROPIC_API_KEY
  • GOOGLE_API_KEY

Security Notes

API keys are correctly managed via environment variables and are not hardcoded. The system uses LLMs to generate structured data (questions) that are then JSON parsed; while this introduces a potential risk if an LLM deviates maliciously from the expected format, the prompts explicitly guide the LLM to return only a JSON array of strings, mitigating the risk. Web search is performed against DuckDuckGo, a legitimate search engine, via direct HTTP requests. There are no detected uses of `eval` or similar dangerous functions on untrusted inputs.

Similar Servers

Stats

Interest Score53
Security Score8
Cost ClassHigh
Avg Tokens8000
Stars4
Forks0
Last Update2025-11-25

Tags

multi-agentLLMresearchMCPAI