🚀 A powerful Model Context Protocol (MCP) server powered by Gemini Embedding 2. Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents! 🔎✨

Fast static text embeddings via OpenAI-compatible API & MCP server. English, 16M params, Matryoshka 512→32D.

An MCP server for generating Qwen3 embedding vectors

Build a Local Multi-Modal AI Agent Memory Server Using Gemini Embeddings 2026

Digital Samba Embedded API MCP Server - Model Context Protocol server for Digital Samba's Embedded API

MCP server + CLI + Codex/Claude skill for embedded debugging via probe-rs or OpenOCD — ARM Cortex-M, RISC-V, and Xtensa (ESP32), with AI crash diagnosis

MCP Server using local embeddings to search user-provided ETABS documentation.

Digital Samba Embedded API MCP Server

An embedded Model Context Protocol (MCP) server implementation on FreeRTOS/lwIP

Offline Polish↔English translation & terminology MCP server for LLM agents: Argos Translate MT, SQLite FTS5 dictionary lookup, bge-m3 + sqlite-vec translation memory. Air-gapped after install; every result carries source and license.

Debug embedded systems with AI. Find bugs in seconds, not hours.

EEG embeddings API client, CLI and MCP server for EPI-300K, an EEG foundation model

MCP server for agent memory over HexxlaDB—ring retrieval, embeddings + lexical search, seams, facets, YAML persistence policy, localhost HTTP transport.

Deterministic evidence about embedding spaces and vector indexes for agents: hubness, anisotropy, collapse, distance concentration, ANN recall, HNSW/IVF sweeps. CLI and MCP server.

Deterministic evidence about embedding spaces and vector indexes for agents: hubness, anisotropy, collapse, distance concentration, ANN recall, HNSW/IVF sweeps. CLI + MCP server.

Embedded NoSQL Database for TypeScript & AI Agents. Zero-native document database with ACID transactions & in-memory cache — verified on Node.js & Bun.

Shared long-term memory for MCP agents — one brain, many agents. Standalone embedded runtime: SQLite + FTS5 + exact vector hybrid search, local Harrier q4 ONNX embeddings, self-expiring diary model. No server, container, or daemon required.

Self-hosted Qwen3 retrieval server with Embedding, Reranker, MCP, and Web console.

MCP server for intelligent news article categorization using embeddings and clustering

The MCP tool can then be used inside VS Code / MCP-enabled clients to search local internal documentation using natural language. Uses persistent embedding using minilm-l6-v2, supports multi format embedding and semantic retrieval .

A TypeScript MCP server for document management and semantic search with embeddings

Mnemo core — persistent semantic memory engine (ONNX embeddings + HNSW + sql.js)

An sqlite MCP server with built-in semantic search and local embedding-vector generation

MCP server for IBM watsonx.ai: Granite chat, generation, embeddings, tokenization and forecasting.

MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia)

Miru (見る) — hybrid code search for agents. Bun, TypeScript, Takara embeddings.

Build-aware code intelligence MCP server for embedded C/C++ firmware

Long-term memory your AI coding agents actually share. One brain, many agents — standalone embedded MCP server: SQLite + FTS5 + vector hybrid search, local ONNX embeddings, self-expiring diary. No server, container, or daemon.

Semantic memory server for AI agent teams. MCP server, ChromaDB or Qdrant, local ONNX embeddings.

MCP server for GigaChat — AI chat, embeddings, image generation (Russia)

Deep code indexing for AI agents. SQLite FTS5 + tree-sitter + embeddings + MCP.

Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank

Signal generator control for the embedded bench — CLI + MCP server for AI agents (Siglent SDG series)

MCP memory server for Claude Code — knowledge graph in SQLite, local ONNX embeddings, token-budgeted retrieval

Nautobot Model Context Protocol (MCP) Server - Contains STDIO and HTTP Deployments with Embedding Search and RAG.

Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.

Local-first memory for coding agents: MCP server, single SQLite file, local embeddings

KINDX - On-device hybrid search engine for markdown documents with BM25, vector embeddings, and LLM reranking

MCP server for Alibaba Cloud DashScope: Qwen chat, embeddings and model discovery with your own API key.

USB power control for the embedded bench — CLI + MCP server for AI agents (Yepkit YKUSH hubs)

Local-first cognitive map retrieval engine. SQLite + FTS5 + pluggable embeddings, with audited mutations and an offline consolidator.

RAG over docs with verified citations, hybrid BM25 + embedding retrieval, an eval harness, and an MCP server. Python, FastAPI, Gemini/Groq.

MCP server for Claude Code session history management with text-embedding-3-large semantic search and Prisma ORM

Embedded knowledge base with 114 MCP tools, hybrid BM25+vector search and RAG. One Go binary.

Persistent, local-first memory for AI agents. No cloud, no Docker, no external services – just CozoDB embedded in Node.js.

Universal Qdrant MCP server with automatic dimension detection and search integrity. Supports any OpenAI-compatible embedding API (OpenAI, Qwen, Gemini, Ollama).

MCP server for SEGGER J-Link debug probes — LLM-driven embedded debugging with RTT, GDB server, and Trice/Pigweed support

Serial and SSH terminal for embedded developers that Claude Code and Codex can use (MCP). Windows and Linux.

Sistema de Memoria Dual MCP con Búsqueda Híbrida (SSC/BIRE) — PostgreSQL + pgvector + pg_trgm + embeddings locales (Ollama)

Embedded single-file store for facts that change: exact vector search, full revision history, no server. numpy-only.

MCP server that decodes, validates and explains devicetrees (.dtb/.dts) - memory maps through ranges, interrupt routing, phandles - for embedded Linux, Zephyr and hobby OS work.

MCP server + CLI for AI-native SEO audits: broken links, internal link suggestions, crawl diffs, optional local embeddings.

An MCP server exposing local embedding tools - semantic search, comparison, clustering and zero-shot classification - so an agent can call them in a loop without an API round trip. Caching the embeddings took a search from 1040ms to 1.2ms. PyTorch, sentence-transformers, MCP Python SDK v2.

Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.

Serial port MCP server for Claude Code, Codex, Opencode and AI agents. Reliable UART/USB-serial access for embedded development.

Bench power supply control for the embedded bench — CLI + MCP server for AI agents (B&K Precision 168xB / Manson HCS)

Tool-agnostic long-term memory for LLM agents (HTTP API, MCP, CLI, embedded WebUI)

Local-first agent memory — topic index, FTS, hybrid vector search (BM25 + embeddings + RRF), temporal decay, importance/ttl/persona scoping, bundled MCP server

Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp

Ask questions about any GitHub repo in natural language. Local embedding + ChromaDB + LLM with cited code paths (Anthropic + OpenAI-compatible)