InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. ask-llm

    MCP servers

    Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity

    Indexed Official MCP Registry, io.github.Lykhoyda Updated 2 days ago 2 notes

    @ask-llm/mcp@1.4.0
  2. blenderwright

    MCP servers

    MCP server for Blender. Hundreds of tools for modeling, materials, rendering and more, driven by Claude, Cursor, Codex, Ollama, llama.cpp, or any MCP client.

    Stale GitHub, HoldMyBeer-gg 178 ★MITUpdated 22 days ago

    git clone https://github.com/HoldMyBeer-gg/blenderwright.git
  3. MCPBridge

    MCP servers

    Unified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.

    Stale Official MCP Registry, io.github.iamjrmh Updated 6 months ago 1 note

    @iamjrmh/mcpbridge@1.0.0
  4. localmodels

    MCP servers

    Talk to a local Ollama server: list, pull, inspect, generate, chat and embed.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 16 days ago 1 note

    @reneturcios/localmodels@0.1.0
  5. ragnarok

    MCP servers

    Local RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.

    Stale Official MCP Registry, io.github.freyr Updated 6 days ago 1 note

    ragnarok-mcp@2.3.0
  6. Connapse

    MCP servers

    Self-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.

    Indexed GitHub, Destrayon 23 ★MITUpdated yesterday

    git clone https://github.com/Destrayon/Connapse.git
  7. massive-context-mcp

    MCP servers

    Handles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.

    Stale Official MCP Registry, io.github.egoughnour Updated 10 months ago 1 note

    massive-context-mcp@3.0.1
  8. Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.

    Stale Official MCP Registry, io.github.DalecB Updated 5 months ago 1 note

    @dalecb/obsidian-semantic-mcp@0.2.1
  9. offline-mcp

    MCP servers

    Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.

    Stale Official MCP Registry, io.github.gabrielmahia Updated 7 days ago 1 note

    offline-mcp@0.1.13
  10. Sezzlee Local LLM

    MCP servers

    Let a planning agent hand bounded language work to a local Ollama model.

    Stale Official MCP Registry, io.github.sezzlee Updated 37 days ago 1 note

    @sezzlee/llm-mcp@0.1.3
  11. Nightshift Grid

    MCP servers

    Cited knowledge graphs from local documents, extracted by small Ollama models on idle machines.

    Indexed Official MCP Registry, io.github.redd34 Updated 2 days ago 1 note

    nightshift-grid@0.1.3
  12. qsp-client

    MCP servers

    QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

    Stale Official MCP Registry, io.github.qso-graph Updated 9 days ago 1 note

    qsp-client@0.5.2
  13. qsp-mcp

    MCP servers

    QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

    Stale Official MCP Registry, io.github.qso-graph Updated 50 days ago 2 notes

    qsp-mcp@0.1.1
  14. Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.

    Stale Official MCP Registry, io.github.MakeaMouse Updated 6 months ago 2 notes

    fish-bridge-mcp@0.1.3
  15. agentic-research

    MCP servers

    Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

    Stale Official MCP Registry, io.github.TheAiSingularity Updated 7 months ago 2 notes

    agentic-research-engine@0.1.3
  16. Paw Pulse

    MCP servers

    Heartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.

    Stale Official MCP Registry, com.dougalpaw Updated 28 days ago 1 note

  17. blender-ai-mcp-addon

    MCP servers

    AI 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.

    Stale GitHub, LiCinCan 975 ★MITUpdated 27 days ago

    git clone https://github.com/LiCinCan/blender-ai-mcp-addon.git
  18. cli-bridge-mcp

    MCP servers

    Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.

    Stale Official MCP Registry, io.github.JoaoBerne Updated 2 months ago 1 note

    cli-bridge-mcp@0.3.0
  19. Local Coding Agent

    MCP servers

    Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.

    Stale Official MCP Registry, io.github.pvnc228 Updated 14 days ago 1 note

    local-coding-agent@1.2.0
  20. MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens

    Stale Official MCP Registry, io.github.BlackFoil Updated 7 months ago 1 note

    claude-token-saver-mcp@0.3.2
  21. Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.

    Indexed Official MCP Registry, io.github.zhaoxinghua09-cell Updated yesterday 1 note

    medxpert-library-connector@1.0.2
  22. Paw Pulse

    MCP servers

    Heartbeat and tokens/sec monitoring for self-hosted LLM servers (Ollama etc.), with down alerts.

    Stale Official MCP Registry, dev.workers.dougalpaw.pawpulse Updated 28 days ago 2 notes

  23. Local AI MCP

    MCP servers

    Run, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).

    Stale Official MCP Registry, io.github.TMHSDigital Updated 14 days ago 2 notes

    @tmhs/local-ai-mcp@0.6.1
  24. Algernon MCP

    MCP servers

    Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.

    Stale Official MCP Registry, io.github.sammyboi81 Updated 2 months ago 1 note

    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.