"Using npx to run tools directly without requiring an API" matching MCP servers:

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.

Enables semantic search across Apple Mail, Messages, Calendar, and Contacts on macOS using natural language queries. All processing happens locally with privacy-first vector indexing for fast similarity search.

MCP server that ingests PDF documents into pgvector for semantic search and RAG pipelines. It handles extraction, chunking, local embeddings, and storage, enabling agents to make PDFs searchable via natural language.

A lightweight RAG system that provides an MCP server for searching and interacting with vector-based knowledge bases. It enables users to perform retrieval-augmented generation and search across Qdrant collections through a standardized interface.

Enables natural language search and analysis of uploaded PDF, CSV, and Excel documents using retrieval-augmented generation and MCP tools, providing contextual answers to user queries.

Enables semantic search over OpenAPI endpoint catalogs using FAISS and LangGraph, returning grounded technical recommendations for natural-language API queries.

Enables Claude to interact with core AWS services like S3, EC2, RDS, and CloudWatch, along with a generic SDK wrapper for any AWS operation. It also supports cost monitoring and optional vector store capabilities for document ingestion and search.

Enables stateless similarity search over pre-computed vector corpora using NMI and cosine fusion with entropy-calibrated weighting. Provides tools for ranking, scoring, outlier detection, and alpha calibration for AI agents.

askDB is an MCP server that retrieves relevant database schema (DDL) from a Pinecone index and provides it to LLMs to write SQL, without connecting to the database itself.

MCP server for semantic search in an Obsidian Second Brain vault using self-hosted Qdrant and Google Gemini embeddings.

Provides fast static embedding, similarity, and search capabilities via MCP tools and an OpenAI-compatible HTTP API using a tiny 16M-parameter English embedding model.

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.

Model Context Protocol server for RosalindDB, enabling AI clients to create datasets, ingest vectors, run similarity queries, and check usage on a cost-optimized vector search database.

An MCP server for OpenServerless that exposes action tools for creating, invoking, and managing API endpoints with integrated services like S3, PostgreSQL, Redis, and Milvus.

An MCP server that provides semantic memory on top of Qdrant vector search, with tools to store and retrieve information using embeddings.

A persistent local vector memory server that allows users to store and search project-specific context using LanceDB and local embeddings. It enables MCP-compliant editors to maintain long-term memory across different projects without requiring external API keys.

An MCP server for neuroanatomically-inspired memory consolidation using Neo4j and semantic search, enabling episodic memory encoding, semantic retrieval, and graph operations.

Enables GitHub Copilot to query local ChromaDB instances to retrieve relevant documents and context for AI conversations. It allows users to search vector collections using natural language tools directly within VS Code.

A nested MCP system that demonstrates server composition by using an orchestrator to manage an internal vector store for semantic search. It enables complex, multi-hop retrieval and reasoning over a knowledge base through an agentic reasoning loop.

Provides a private, on-device memory with semantic search for MCP clients, enabling encrypted storage and recall of context facts without external API calls.