~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
docs(readme): drop stale "New:" prefix + link the MCP and CLI guides (#3998)
LearningCircuit0568f82046ca
diff --git a/README.md b/README.mdindex d236501623..18209fa939 100644--- a/README.md+++ b/README.md@@ -105,7 +105,7 @@ You ask a complex question. LDR:Choose from 20+ research strategies for quick facts, deep analysis, or academic research.-**New: LangGraph Agent Strategy** — An autonomous agentic research mode where the LLM decides what to search, which specialized engines to use (arXiv, PubMed, Semantic Scholar, etc.), and when to synthesize. Early results are promising — it adaptively switches between search engines based on what it finds and collects significantly more sources than pipeline-based strategies. Select `langgraph-agent` in Settings to try it.+**LangGraph Agent Strategy** — An autonomous agentic research mode where the LLM decides what to search, which specialized engines to use (arXiv, PubMed, Semantic Scholar, etc.), and when to synthesize. It adaptively switches between search engines based on what it finds and collects significantly more sources than pipeline-based strategies — this is the strategy behind the ~95% SimpleQA result above. Select `langgraph-agent` in Settings.### Build Your Knowledge Base@@ -309,6 +309,8 @@ python -m local_deep_research.web_search_engines.rate_limiting statuspython -m local_deep_research.web_search_engines.rate_limiting reset```+See the [Command Line Tools guide](docs/cli-tools.md) for the full reference.+## 🔗 Enterprise IntegrationConnect LDR to your existing knowledge base:@@ -330,7 +332,7 @@ Works with: FAISS, Chroma, Pinecone, Weaviate, Elasticsearch, and any LangChain-## 🔌 MCP Server (Claude Integration)-LDR provides an MCP (Model Context Protocol) server that allows AI assistants like Claude Desktop and Claude Code to perform deep research.+LDR provides an MCP (Model Context Protocol) server that allows AI assistants like Claude Desktop and Claude Code to perform deep research. Full setup details in the [MCP Server guide](docs/mcp-server.md).> ⚠️ **Security Note**: This MCP server is designed for **local use only** via STDIO transport (e.g., Claude Desktop). It has no built-in authentication or rate limiting. Do not expose over a network without implementing proper security controls. See the [MCP Security Guide](https://modelcontextprotocol.io/docs/concepts/security) for network deployment requirements.