Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ask-llm
MCP serversUnified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
@ask-llm/mcp@1.4.0 -
blenderwright
MCP serversMCP server for Blender. Hundreds of tools for modeling, materials, rendering and more, driven by Claude, Cursor, Codex, Ollama, llama.cpp, or any MCP client.
git clone https://github.com/HoldMyBeer-gg/blenderwright.git -
MCPBridge
MCP serversUnified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.
@iamjrmh/mcpbridge@1.0.0 -
localmodels
MCP serversTalk to a local Ollama server: list, pull, inspect, generate, chat and embed.
@reneturcios/localmodels@0.1.0 -
ragnarok
MCP serversLocal RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.
ragnarok-mcp@2.3.0 -
Connapse
MCP serversSelf-hosted knowledge base and memory for AI agents. MCP server and REST API with hybrid search, reranking and per-user permissions over your files, S3, Azure Blob, GitHub, Confluence and Jira. RAG on .NET 10 and pgvector.
git clone https://github.com/Destrayon/Connapse.git -
massive-context-mcp
MCP serversHandles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.
massive-context-mcp@3.0.1 -
Obsidian Semantic Search
MCP serversRead-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
@dalecb/obsidian-semantic-mcp@0.2.1 -
offline-mcp
MCP serversLocal AI over Ollama for low connectivity: status, local inference, model and deployment guides.
offline-mcp@0.1.13 -
Sezzlee Local LLM
MCP serversLet a planning agent hand bounded language work to a local Ollama model.
@sezzlee/llm-mcp@0.1.3 -
Nightshift Grid
MCP serversCited knowledge graphs from local documents, extracted by small Ollama models on idle machines.
nightshift-grid@0.1.3 -
qsp-client
MCP serversQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
qsp-client@0.5.2 -
qsp-mcp
MCP serversQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
qsp-mcp@0.1.1 -
fish-bridge — Session Knowledge Graph
MCP serversCompresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
fish-bridge-mcp@0.1.3 -
agentic-research
MCP serversLocal research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
agentic-research-engine@0.1.3 -
Paw Pulse
MCP serversHeartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.
-
blender-ai-mcp-addon
MCP serversAI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration.
git clone https://github.com/LiCinCan/blender-ai-mcp-addon.git -
cli-bridge-mcp
MCP serversOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
cli-bridge-mcp@0.3.0 -
Local Coding Agent
MCP serversDelegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.
local-coding-agent@1.2.0 -
claude-token-saver-mcp
MCP serversMCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
claude-token-saver-mcp@0.3.2 -
MedXpert 图书馆连接器(通用版)
MCP serversLocal RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
medxpert-library-connector@1.0.2 -
Paw Pulse
MCP serversHeartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.
-
Local AI MCP
MCP serversRun, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).
@tmhs/local-ai-mcp@0.6.1 -
Algernon MCP
MCP serversFan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.
algernon-mcp@0.1.1
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.