"A semantic search router for dynamically discovering and routing MCP tool definitions" matching MCP servers:

Enables agents to send only the handful of tool definitions relevant to each question, ranking a large catalog by keywords and optional embeddings to cut context cost and wrong-tool picks. It can also run in front of any mcpServers config as a proxy that exposes just search_tools and call_tool instead of the whole catalog.

Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.

Enables fully local semantic search over a Roam Research graph via MCP, providing tools for hybrid retrieval, index refresh, and stats while keeping all content on-machine.

Routes external MCP tools behind a small on-demand discovery interface for Codex agents, using Jev to select relevant tools and providing fallback to the full inventory when confidence is low.

Local semantic recall MCP server for citation-integrity workflows. Enables semantic search over a text corpus, returning file paths and page numbers for verification, with 100% local processing using ONNX embeddings and LanceDB.

Local offline semantic search over documents (txt, md, pdf, docx, pptx, csv). Indexes folders into a LanceDB vector database with multilingual embeddings and supports hybrid vector + keyword search via Reciprocal Rank Fusion. No API keys, no cloud, no Docker required.

Provides semantic code search over codebases using local embeddings with natural language queries. Supports hybrid search, file watching, and respects .gitignore.

Indexes codebases using semantic embeddings for natural language search, enabling developers to find code with queries like 'how does authentication work'.

Provides AI assistants with instant access to TypeScript type definitions from your project dependencies. Enables generation of complete, type-safe mocks and test data by automatically discovering and exposing interface structures from node_modules.

Enables AI agents to perform semantic search over codebases by converting natural language queries into efficient search patterns like grep and ripgrep. It utilizes LLMs to verify relevance and find code snippets that traditional keyword-based searches might miss.

Enables AI coding agents to perform semantic code search locally, finding code by meaning rather than exact keywords.

A tiny RAG-lite retrieval engine that indexes files on disk and provides semantic search via MCP, returning relevant text chunks (file, line, score) without generating answers.

A lightweight MCP server for querying arXiv with semantic and keyword search, supporting natural language queries and structured filters.

Enables cost-aware LLM routing over MCP with verification-based cascading, offering tools for routing queries, resuming escalated approvals, estimating costs, comparing policies, and explaining routing decisions, plus read-only resources and a policy-selection prompt.

Enables semantic code search over local repositories, providing tools like semantic_search and list_indexed_repos to Claude Code, so users can find relevant code sections via natural language instead of grep.

Enables semantic search over documentation stored in a Vectorize database using the Cloudflare Agents SDK, allowing users to query indexed content via natural language.

Enables natural language search of local photo archives using AI-powered semantic understanding, with integration into Claude Desktop via the Model Context Protocol.

An MCP proxy that embeds tool definitions and returns only the top-k semantically relevant tools per query, reducing context usage and routing calls to upstream MCP servers.

A Model Context Protocol server that provides real-time web search capabilities to AI assistants through pluggable search providers, currently integrated with the Brave Search API.

An MCP routing proxy that prevents LLMs from executing unintended tools. It securely curates, filters, and routes tools from multiple backend MCP servers. (LLMが意図しないツールを実行するのを防ぐMCPルーティングプロキシ。複数のバックエンドMCPサーバーからのツールを安全にキュレーション、フィルタリング、ルーティングします。)

Pools multiple configured search provider API keys behind a single endpoint and exposes MCP tools for web search and document reading, enabling agents to keep searching when individual quotas are exhausted and fetch HTML/PDF content as Markdown.

Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids, grades sides blind with one judge per vendor, and tracks per-kind standings and lane pacing.

An MCP server that enables file system search and inspection, including directory listing, regex-based file name and content searches, and reading text, PDF, and DOCX files.

Enables Claude to store and retrieve information with semantic search using Qdrant vector database, providing persistent memory for conversations, code, and documentation.

Enables dynamic tool discovery and loading for Claude using BM25, regex, and semantic search algorithms. It supports managing a catalog of over 10,000 tools with minimal context overhead and provides a REST API for tool management.

A Python MCP server that enables semantic search through Search Labs blog posts indexed in Elasticsearch, allowing Claude to intelligently retrieve relevant information from the blog content.

Enables semantic search over local notes and documents using natural language queries. Supports multiple file types (Markdown, Python, HTML, JSON, CSV, text) with fast local embeddings and persistent ChromaDB vector storage.

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

Enables semantic search over local markdown specs, RFCs, and docs using Ollama and LanceDB, allowing AI agents to find relevant information by meaning rather than exact keywords.

A semantic search system for Claude Code transcript history, exposed as an MCP server so Claude Code can query its own past sessions.