OpenScout
Verified Safeby boxcalfdevelopmentallearning748
Overview
Perplexity-inspired answer engine that provides cited responses to questions using web search, retrieval, and LLM synthesis.
Installation
streamlit run app.pyEnvironment Variables
- TAVILY_API_KEY
- NEO4J_URI
- NEO4J_USERNAME
- NEO4J_PASSWORD
- GROQ_API_KEY
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- GOOGLE_API_KEY
- MCP_URL
- MCP_API_KEY
Security Notes
The code handles API keys securely by loading them from environment variables (.env) or Streamlit session state, with inputs masked. It explicitly states keys are not stored or logged. Network requests are made to trusted external services (Tavily, various LLMs, Neo4j, and an optional MCP server) using standard libraries. No `eval()` calls, code obfuscation, or obvious malicious patterns were detected. The dependency on an external MCP server (if configured) would introduce a trust boundary, but the client-side interaction appears secure.
Similar Servers
rmcp
Serves as an AI assistant backend to perform comprehensive statistical analysis, econometric modeling, machine learning, time series analysis, and data science tasks using R through natural language conversations.
kernel-mcp-server
A Model Context Protocol (MCP) server enabling AI assistants to securely access Kernel platform tools and perform web browser automation, app deployment, and monitoring.
company-docs-mcp
Transforms organizational documentation into an AI-powered knowledge base for semantic search, Q&A via chat interface, Claude Desktop, and Slack integration.
karma
Provides a plug-and-play Knowledge Graph service via the Model Context Protocol (MCP), allowing AI agents to store, retrieve, and manage structured and unstructured knowledge (entities, relations, observations).