llmstudio-mcp
1465MCP server Claude CodeCodexCursor +2
MCP server "llmstudio-mcp" as configured in dam2452/llmstudio-mcp. Runs locally from the llmstudio-mcp Python package.
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.
MCP server Claude CodeCodexCursor +2
MCP server "llmstudio-mcp" as configured in dam2452/llmstudio-mcp. Runs locally from the llmstudio-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for OpenVecta — call OpenVecta inference models (OpenAI-compatible, USDC per call) as tools from any MCP client. Runs locally from the @openvecta/mcp npm package.
sakshamjain2301/videocontext-mcp
MCP server Claude CodeCodexCursor +2
MCP server "video-understanding-mcp" as configured in sakshamjain2301/videocontext-mcp. Runs locally from the video-understanding-mcp Python package.
MCP server Claude CodeCodexCursor +2
Semantic search MCP server for an Acumatica KB, single multilingual index, no Obsidian/Smart Connections required. Runs locally from the grp-kb Python package.
MCP server Claude CodeCodexCursor +2
MCP server "hybrid-rag-mcp-server" as configured in n-irei/hybrid-rag-mcp-server. Runs locally from the hybrid-rag-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP API server for h2oGPTe. Runs locally from the h2ogpte-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-prompt-server" as configured in marcmodin/mcp-prompt-server. Runs locally from the mcp-prompt-server Python package.
LiChenStuttgart/data-science-mcp
MCP server Claude CodeCodexCursor +2
Data Science MCP Server — Model training, evaluation, and evolution tools for agentic ML workflows. Integrates with agent-utilities IModelEvolver (CONCEPT:AHE-3.15). Runs locally from the data-science-mcp Python package.
Skill Claude CodeCodex
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.
MCP server Claude CodeCodexCursor +2
MCP server "gemini-understanding" as configured in sandlong/gemini-understanding. Runs locally from the @sandlong/gemini-understanding npm package.
MCP server Claude CodeCodexCursor +2
A local MCP server for visual understanding from the GLM Coding Plan. Visual understanding means examining images and interpreting what they contain.
MCP server Claude CodeCodexCursor +2
A locally run MCP server that uses the GLM-4V multimodal AI model to analyse images and other visual input. Multimodal means it can work with visual content as well as text.
MCP server Claude CodeCodexCursor +2
MCP server for visual understanding via Xiaomi MIMO multimodal API. Runs locally from the mimo-vision-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "llm-eval-mcp" as configured in cdywolf/llm-eval-mcp. Runs locally from the llm-eval-mcp Python package.
JayceVane/visual-understanding
Skill Claude Code
Multi-provider visual understanding tool for images, videos, and documents. Supports captioning, OCR, visual Q&A, document analysis, and object grounding (bounding-box localisation) through configurable providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint). Use when the user wants…
MCP server Claude CodeCodexCursor +2
MCP server "table-rag-mcp" as configured in BitDG/TableRAG. Runs locally from the table-rag-mcp Python package.
MCP server Claude CodeCodexCursor +2
Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required. Runs locally from the llm-sidecar Python package.
MCP server Claude CodeCodexCursor +2
Semantic search for Obsidian vaults via MCP. Runs locally from the obsidian-rag-mcp Python package.
AyushShanu/CodeBase-MCP-Server
MCP server Claude CodeCodexCursor +2
MCP server "codebase-rag-mcp" as configured in AyushShanu/CodeBase-MCP-Server. Runs locally from the codebase-rag-mcp Python package.
MCP server Claude CodeCodexCursor +2
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.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 73 tokens together
Add Qwen 3.8 Max vision to text-only Claude Code model gateways through MCP and a transparent local proxy.
MCP server Claude CodeCodexCursor +2
Open-source prompt optimizer plugin for terminal AI agents: cuts token waste via a behavior protocol, local prompt compression, ask-or-assume clarifying questions, and cheapest-capable model routing. Runs locally from the promptopt npm package.
MCP server Claude CodeCodexCursor +2
MCP server providing multimodal vision capabilities via OpenAI-compatible APIs. Runs locally from the vision-mcp npm package.
luffy666code/PaddleOCR-json-MCP
MCP server Claude CodeCodexCursor +2
MCP server "paddleocr-json-mcp" as configured in luffy666code/PaddleOCR-json-MCP. Runs locally from the paddleocr-json-mcp Python package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: