14,252 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Run, fit, and route work to local LLMs: one MCP server for Ollama, LM Studio, llama.cpp, Docker Model Runner, MLX, vLLM, and Foundry Local, with hardware-aware model selection. Runs locally from the @tmhs/local-ai-mcp npm package. Needs 17 environment variables to run.
A flexible, multi-provider AI orchestrator for routing requests based on cost, latency, and other strategies. Runs locally from the ai-orchestrator npm package.
★not rated 0 4mo agoA
tokens not measured
originalMIT
Give text-only LLM agents eyes: an MCP server + CLI that describes images through a vision-language model (VLM) API. Runs locally from the agent-eyes-mcp npm package.
★not rated 0 2mo agoA
tokens not measured
originalMIT
MCP Server that gives DeepSeek (and other text-only LLMs) vision capability via third-party OpenAI-compatible vision APIs. Runs locally from the deepseek-vision-mcp Python package.
MCP server "doubao-seed-image-recognition-mcp" as configured in xuhs8832/doubao-seed-image-recognition-mcp. Runs locally from the doubao-seed-image-recognition-mcp npm package.
MCP server for semantic search using local Qdrant and Ollama (default) with support for OpenAI, Cohere, and Voyage AI. Runs locally from the @mhalder/qdrant-mcp-server npm package.
★not rated 0 2mo agoA
tokens not measured
originalMIT
MCP server "opencode-openai-vision-mcp" as configured in WormAlien/OpenCode-vision-OmniRoute. Runs locally from the opencode-openai-vision-mcp npm package.
★not rated 0 4mo agoA
tokens not measured
originalMIT
OpenGPT a framework for producing grounded domain specific LLMs, and NHS-LLM a conversational model for healthcare made using OpenGPT. Runs locally from the opengpt Python package.
MCP server "lightrag-fastmcp-bridge" as configured in leviethung2103/lightrag-mcp-server. Runs locally from the lightrag-fastmcp-bridge Python package.
RAG-lite: local semantic search over your files, as a CLI and an MCP server. No LLM, no API keys, no servers. Runs locally from the @adborroto/semantic-search-mcp npm package.
★not rated 0 2mo agoA
tokens not measured
originalMIT
An MCP server that exposes the Chinese GLM-4V vision model as an AI-assistant tool. It accepts local image paths and Data URLs, which are text representations of image data, over Streamable HTTP.
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Runs locally from the openrag Python package.
Give your AI coding assistant a brain: persistent memory, hybrid code search, AI-authored annotations, and an AST symbol graph — 100% local MCP server, no API keys. Runs locally from the projectmind-mcp Python package.