MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
MIT ★ 5 -
multimodal_search_mcp_architecturegithub.com/estelacode/multimodal_search_mcp_architectureupdated this year
Low-Latency Multimodal Search Web App with MCP Architecture 🔌🛠️🧠 #StrandsAgentSDK #FasterWhisper #Multilingual #MultimodalSearch #ChromaDB # DockerCompose
★ 1 -
Local stdio MCP bridge between LM Studio Bionic and a Find Images.app MCP server. Provides next-level image search and information retrieval based on multimodal embeddings
MIT -
多模态内容理解与工具编排 Agent:Chinese-CLIP 图文共享向量空间 + BM25/RRF 混合检索 + cross-encoder 重排(真实文本查询 hit@10 0.668→0.918)+ Schema 约束工具调用 + 可溯源生成,含 MCP、多轮会话记忆、ReAct 编排与分层离线评测。 | Multimodal agent: Chinese-CLIP retrieval, BM25+RRF hybrid search, cross-encoder reranking, schema-constrained tool calling, MCP server.
MIT -
Calypso Multimodal RAGno update data
Multimodal RAG for source-backed AI answers. Launch a hosted Gemini File Search RAG layer that answers from your PDFs, docs, screenshots, charts, diagrams, help center, FAQs, and images with citations people can verify. Calypso gives your website, AI agents, workflows, and product UI one reusable knowledge layer for grounded answers across text and visual content.
smithery -
Digital Collections Explorer: The multimodal viewer for searching digital collections.
NOASSERTION ★ 16 -
Multimodal local search over documents and media — pdf, office files, notes, images, audio and subtitles — from any MCP-capable agent.
pypi MIT -
@captain-sdk/captain-mcpgithub.com/runcaptain/captain-mcpupdated this year
MCP server for Captain — multimodal RAG search and live project search. Usable from Claude Code, Cursor, and any MCP-aware client.
npm MIT -
Open-source Rust multimodal vector database & RAG platform: one unified space for text, image, audio, video & docs - hybrid search, reranking, built-in MCP server.
AGPL-3.0 -
On-device multimodal search for macOS: photos, video moments, audio, PDFs and docs, by meaning. MLX + EmbeddingGemma 2, with an MCP server for agents.
MIT ★ 1 -
Production multimodal enterprise search & Corrective RAG (CRAG) platform. 5-agent LangGraph orchestration, dynamic query rewriting, Docling layout parsing, Groq Whisper-v3, Qdrant hybrid search, and NeMo guardrails. 298 tests.
MIT -
minimax-unified-mcpgithub.com/exomind-team/minimax-unified-mcpupdated this year
Unified MiniMax MCP server for multimodal generation, Token Plan search, and image understanding.
MIT ★ 1 -
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
dsh-qwen-mmgithub.com/RRRosmontis/dsh-qwen-mmupdated this year
Qwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。
MIT ★ 1 -
MOSAIC (Multimodal Orchestration for Synthesis, Analysis & Intelligent Comprehension) - AI-powered video analysis platform featuring FastAPI backend, React frontend, and MCP server. Process videos, extract clips, ask questions about content, and perform multimodal search using vision models and transcription, Even creates clips from a video!
-
mcp-neo4j-graphraggithub.com/guerinjeanmarc/mcp-neo4j-graphragupdated this year
A unified Neo4j MCP server for GraphRAG: vector search, fulltext search, search-augmented Cypher queries, write operations, and multimodal image retrieval
pypi MIT -
Modular, observable RAG framework exposing tools via MCP (Model Context Protocol) — hybrid search, multimodal ingestion, evaluation, dashboard
MIT -
MCP server for Cencori — first-party web search, docs, gateway, Embedded Agents, memory, sessions, governance, and multimodal inference.
npm MIT -
Pluggable, observable modular RAG service exposed over the Model Context Protocol (MCP): hybrid search, reranking, multimodal ingestion, tracing dashboard and evaluation.
MIT -
grow-book-mcpgithub.com/dephekt/grow-book-mcpupdated this year
MCP server for semantic search over scanned / image-heavy PDFs: embeds page text AND page renders (Voyage context-4 + multimodal-3.5), fused with BM25.
MIT -
Local multimodal knowledge base for textbooks, slides and technical documents on macOS. Swift 6, hybrid search, Apple Vision figures, cited AI synthesis, CLI & MCP.
MIT -
vectorize-mcp-workergithub.com/dannwaneri/vectorize-mcp-workerupdated this year
Hybrid RAG Worker on Cloudflare Edge — Vector + BM25 search, metadata filtering, multimodal vision, MCP server, and intelligent query routing. ~400ms p99.
MIT ★ 28 -
Multi-tenant Brand DNA & Creative Intelligence Platform — governed brand knowledge, multimodal asset analysis, hybrid search, AI-ready creative briefs, REST API and MCP server.
MIT -
Official Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
npm Apache-2.0 ★ 372 -
noodle-perplexity-mcpgithub.com/fahd-noodleseed/perplexity-mcp-serverupdated this year
A Perplexity API Model Context Protocol (MCP) server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, transparent reasoning, and multimodal support with file attachments (P
npm Apache-2.0 -
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
pypi MIT ★ 660 -
Agent skill, plugin and MCP server for building multimodal AI apps with Pixeltable in Claude Code, Cursor, Codex and Gemini CLI. Tables, computed columns, embedding search, UDFs and 30+ AI providers.
Apache-2.0 ★ 6 -
ai-ops-agentgithub.com/mirasolutions06/ai-ops-agentupdated this year
Plug-and-play AI chief-of-staff / ops agent: FastMCP tool server (24 tools) over a markdown vault, tasks, calendar, semantic search, multimodal tools, a mission-control dashboard, and scheduled workflows. OpenAI by default, provider-swappable. MIT.
MIT -
Find files by what's in them: photos, PDFs, docs, voice memos and video, on your own computer. EmbeddingGemma 2 + llama.cpp; CLI, app and MCP server for agents.
MIT ★ 9 -
Free, open-source video search. Find B-roll and exact shots in your own footage, search transcripts, and export to your editor. Local desktop app, MCP server and API.
Apache-2.0 ★ 4 -
claude-gemini-multimodal-bridgegithub.com/goodaymmm/claude-gemini-multimodal-bridgeupdated this year
MCP bridge connecting Claude Code, Antigravity CLI and Google AI Studio, routing each request to the layer that can answer it: web search, complex reasoning, or image/audio/document processing
npm MIT -
lookback-aiupdated this year
Local-first multimodal semantic memory for your machine — searchable text + screenshots, MCP-native, runs on CPU.
pypi MIT -
visionsearch-mcpgithub.com/tiagohgms/visionsearch-mcpupdated this year
Multimodal Web Intelligence MCP — local-first image, PDF, and document research via LM Studio
npm MIT -
A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.
MIT ★ 4 -
mcp-servergithub.com/mixpeek/mcp-serverupdated this year
A lightweight, production-friendly Model Context Protocol (MCP) server for Mixpeek
npm MIT ★ 1 -
Privacy-first Multimodal Data Refinery, Repo Context Firewall (Prompt Injection & Trojan Source Defense), Offline Vietnamese OCR, Multilingual E5 ONNX + SQLite FTS5 RAG & 9-Tool MCP Server.
MIT ★ 7 -
A web search agent that enables you to search, visualize, and listen to information.
MIT ★ 5 -
AI-powered monitoring that detects hidden streaming ad failures, finds their root cause, and calculates the revenue lost.
MIT ★ 1 -
Open-source, local-first video indexing and timestamped search with a REST API and MCP server.
Apache-2.0 -
Search your files by meaning and fact-check the web, fully offline.
AGPL-3.0 -
Search video like it's text — moment-level retrieval over a folder of footage with published evals (Recall@5, MRR, latency) and MCP tools for agents.
MIT ★ 1 -
Give AI agents (Claude Code, Cursor, MCP) eyes and ears over your video library with zero cloud dependencies.
MIT ★ 1 -
VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.
pypi MIT ★ 59 -
Model Context Protocol server exposing railroute-ts rail-route tools (rail_route, rail_route_alternatives, rail_station_search) for Europe and India to AI agents.
npm MIT -
Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud. Desktop app + 26 MCP tools for Claude Code, plus a multi-engine web researcher that quotes sources verbatim. 本地离线多模态语义检索
AGPL-3.0 ★ 4 -
GLOBAL-email-RAG-MCPgithub.com/eqramul01/GLOBAL-email-RAG-MCPupdated this year
v2: Hybrid (BM25+vector) RAG over a six-figure legal email archive — full-text message search, recipient-graph filtering, in-chat .eml reading. Gemini Embedding 2, LanceDB, Cloud Run, MCP, queryable from Claude.ai with cited source links.
MIT -
Local-first semantic knowledge operating system & agent context engine with multimodal ingestion, MCP routing, and memory dreaming
-
Local-first multimodal RAG assistant (FastAPI + React) — hybrid retrieval, HyDE, cross-encoder reranking, and an MCP server for querying your documents from Claude Desktop.