A lightweight MCP server for linear-static structural analysis of bridges and building frames, providing tools to build 3D beam/truss models, analyze with built-in or CalculiX solvers, and export to FreeCAD.
Provides native MCP tools for quantitative-finance and risk-modeling workflows, enabling computation of option Greeks, simulation of geometric Brownian motion asset-price paths, historical/parametric VaR and CVaR estimates, bond duration/convexity metrics, and Nelson-Siegel yield-curve interpolation using only Python's standard library.
Exposes Beam's local, offline risk-scanning tools to any MCP-compatible host, enabling read-only heuristic detection of risky AI agent patterns without executing, blocking, or approving actions.
Federated, local-first search for AI agents: one query fans across transcripts, files, a knowledge graph, a vector store, the live web, and YouTube, fused by trust-weighted RRF into one ranked answer. Five
modes (grep/lexical/semantic/hybrid/rerank), runs entirely on your machine over MCP.
Provides DuckDuckGo web search through MCP with automatic failover across multiple backends, enabling reliable query results even when individual backends are rate-limited or blocked.
Wraps the local agy CLI into an MCP server to provide a web_search tool that enables Claude Code to perform real internet searches through Gemini/Google.
Enables running web searches across multiple engines like Google, Bing, DuckDuckGo, Yahoo! JAPAN, and Brave via Playwright, with tools to fetch page content and manage browser profiles.
Enables any calling model to search public X content through Grok's native search using an existing local OAuth login, returning summaries, structured posts, source URLs, and search counts while sharing cached and concurrent searches across local terminals.
Enables AI clients to search, compare, and register products by integrating objective specifications, review-derived experiential attributes, and sales conditions such as price, shipping, and stock.
Enables read-only collection and comparison of Google Search Console and Bing Webmaster data, conservative URL protection, content auditing, reviewed-build verification, and private report generation through ten typed tools over stdio.
Semantic, on-demand skill retrieval for Claude Code that saves tokens and improves skill discovery by replacing the native skill listing with vector embedding search.
MCP server for searching files on macOS by name or content using semantic and lexical search, providing file paths and line numbers for agents to read from.
Provides fully local, privacy-preserving semantic search over file names and paths via MCP, using BGE embeddings for fuzzy matching and supporting incremental updates, watch mode, and a loopback-only HTTP server.
Enables local, read-only keyword search across past Claude Code, Codex, Gemini CLI, and ChatGPT conversations plus markdown notes, with exact source citations and context retrieval.
Enables AI agents to run semantic search over local Obsidian or Markdown vaults, returning notes ranked by meaning with paths, headings, scores, and snippets, and to trigger incremental reindexing of changed notes. Everything runs on the user's own machine, so no note content leaves it.
Aggregates security research articles from WeChat, QAX Butian, and Xianzhi community, with optional KimiCode web search. Supports smart deduplication, article fetching, and anti-bot measures.
Enables semantic code search across indexed code folders using vector embeddings, with support for multiple embedding providers and automatic file watching. Provides an admin UI and integrates with MCP clients for natural language code queries.
Enables AI clients to run local semantic search over your own documents and code in Chinese or English, with embeddings computed on an Intel NPU. Also lets clients check index status and trigger reindexing.
Enables AI assistants to run incremental SQLite FTS5 full-text search over explicitly configured local workspace roots, covering Markdown, code, PDF, DOCX, XLSX, CSV and HTML with BM25 ranking, Chinese bigrams, and phrase, prefix, path, type and date filters. Exposes search, safe root-confined reads with line/page/sheet locations, recent-file listing, and reindexing as MCP tools so assistants can locate and quote source content without network or account access.
Full-text search over Claude Code conversation history using SQLite FTS5, exposing indexed transcripts as MCP tools for searching, browsing, and reading turns.
A local-first MCP server that enables semantic search over PDF and DOCX documents using structure-aware parsing and vector storage. It allows users to query their local knowledge base through Claude Code without cloud dependencies or GPU requirements.
