13,736 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 for image recognition - OCR and visual analysis via multimodal APIs, enables image understanding for text-only AI coding tools like Claude Code + DeepSeek. Runs locally from the mcp-vision Python package.
Ask a council of local (Ollama, vLLM, TRT-LLM, SGLang) and cloud (OpenAI, Anthropic, X.AI Grok) AI models. Get individual, categorized (agreement / complementary / conflicting), or fully deconflicted answers with a resolution score.
★not rated 1 1mo agoA
tokens not measured
originalApache-2.0
SHADDAI 7-agent council + RAG knowledge bases as a Model Context Protocol server. Key-free: no API keys, no external LLM, no localhost. Wire it into Claude with one npx line and instantly get a knowledge-grounded 7-agent system. Runs locally from the shaddai-mcp npm package.
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings. Runs locally from the @dalecb/obsidian-semantic-mcp npm package. Needs 8 environment variables to run.
★not rated 1▲
+1 1mo agoA
tokens not measured
originalMIT
Local multi-client RAG server over the Model Context Protocol. Runs locally from the cortex-local-rag Python package. Needs 1 environment variable to run.
★not rated 1 3d agoA
tokens not measured
originalApache-2.0
Claude Code skills for the full data engineering lifecycle: sourcing, profiling, modeling, architecture, ETL build, reliability, ML delivery, code quality, and routine reporting.
Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration. Runs locally from the ruflo npm package.
★not rated 1 5mo agoA
tokens not measured
originalApache-2.0
Run an evidence-gated edit loop over a Neurarch model graph through the neurarch-mcp MCP server. Use when an agent needs to inspect, explain, audit, extend, refactor, or debug a neural-network architecture stored as a .neurarch.json graph; summarize a model; locate parameter or compute hotspots; trace dependencies and…
Pinecone vector database integration for Cursor. Create and manage indexes, upsert data, and run semantic searches via the Pinecone MCP server. Build document Q&A assistants with citations, or get started fast with /pinecone-quickstart. Great for semantic search, RAG, and agentic AI apps.
★not rated 1 3d agoA
tokens not measured
originalMIT
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Create, edit, and build Observable Notebooks using Notebook Kit. Use when working with .html notebook files, generating static sites from notebooks, querying databases from notebooks, or using data loaders (Node.js/Python/R) in notebooks. Covers notebook file format, cell types, CLI commands, database connectors, and…
Model Context Protocol server for FHIR R4 with validation, narrative generation, and comprehensive resource management. Runs locally from the fhir-mcp-server npm package.