"Ray" matching MCP servers:

Provides AI agents with direct access to the Ray Group DeFi UX rubric, named patterns, and cognitive-bias glossary for grounded UX assessments of DeFi protocols.

Enables local, provenance-aware literature search and retrieval for X-ray binary research, with tools for querying papers, fetching paper details, and accessing source information.

Drive VMD headlessly from any MCP client to analyze structures and trajectories, and ray-trace publication-quality images with no display.

Local repo-intelligence MCP for coding agents: indexes source, symbols, call graphs, git/GitHub history, and source-bound repo memories into local database.

MCP server for analyzing OpenTelemetry traces with performance and error diagnosis, supporting loading from files, AWS X-Ray, and CloudWatch.

Enables running FDMNES X-ray spectroscopy simulations via natural language, supporting input file creation, job execution, output analysis, and keyword lookup through MCP-aware clients.

MCP server that lets AI clients drive the dfxm-geo dark-field X-ray microscopy forward model, enabling config validation, reflection enumeration, and preview-scale simulations.

Enables AI-powered dental X-ray analysis and treatment planning using YOLOv11 and clinical guideline RAG, integrated with MCP for use with Claude and other AI assistants.

MCP server that wraps xraylarch for X-ray spectroscopy analysis, enabling loading, processing, analyzing, and plotting XAS/XAFS spectra through natural language.

Exposes NVIDIA Sionna RT ray-tracing as 15 structured tools for AI agents, enabling wireless channel simulation (scene loading, antenna array setup, ray tracing, CSI extraction) through MCP.

Prototype of a Model Context Protocol (MCP) server that provides access to X-ray properties of elements via the XrayDB library.

Provides AI assistants with progressive code intelligence to explore repository structure, find symbols, and assess the impact of changes using ast-grep.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Exposes hybrid retrieval (dense embeddings + BM25 + RRF) and document operations (search, fetch, rerank) as MCP tools, using Qdrant and OpenAI embeddings for local or server mode.

Enables AI agents to discover and pay for x402-gated HTTP APIs, handling 402 Payment Required flows with local signing. Supports EVM and Solana with non-custodial wallet management.

MCP server that integrates with LM Studio to provide a search_notes tool, allowing the chat model to retrieve and answer from a local Obsidian vault.

Enables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.

Enables local-first hybrid knowledge retrieval from authorized Markdown and plain-text files, combining full-text and vector search with reranking and traceable source references via a single search tool.

Enables semantic search over codebases using natural language queries, returning relevant code snippets with source locations. Integrates with Claude Code for automatic codebase exploration.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.