Home / Topics / Ollama & Local LLMs MCP servers

Topic · updated 2026-10-05

Ollama & Local LLMs MCP servers

45 Ollama & Local LLMs MCP servers indexed on awesomemcp.in. Every entry links to a live GitHub repository with a known author, is de-duplicated across the official MCP registry and community lists, and carries an automated vulnerability-check badge. Built by @jaspertvdm, @Michael-WhiteCapData, @VrtxOmega, @spanlens, @mrkrsl and 39 other authors.

45servers
44scan passed
1official
14one-click install

Top 45 Ollama & Local LLMs MCP servers

  1. Bridge to a local Ollama server for running Llama, Mistral, Qwen and other local models.

    Scan passed
    ★ 4
    2026-06-10
  2. Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

    Scan passed
    ★ 3
    2026-09-23
  3. Chat, generate, pull, list and inspect models with Ollama.

    Scan passed
    ★ 3
    2026-04-29
  4. by @spanlens · official · TypeScript · spanlens/Spanlens

    Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

    Scan passed
    ★ 13
    2026-10-05
  5. by @mrkrsl · TypeScript · mrkrsl/web-search-mcp

    A server that provides local, full web search, summaries and page extration for use with Local LLMs.

    Needs review
    ★ 1,166
    2025-08-08
  6. Multi-cluster Kubernetes management and operations with a management UI and logging, covering common DevOps tasks for standard and CRD resources.

    Scan passed
    ★ 885
    2026-10-03
  7. MCP server for generating rough-draft project plans from natural-language prompts.

    Scan passed
    ★ 400
    2026-10-04
  8. by @noskillish · TypeScript · noskillish/bankmcp

    Read-only MCP server for your own bank accounts via Enable Banking. Self-hosted, one user.

    Scan passed
    ★ 275
    2026-09-28
  9. Self-hosted AI studio exposing local image, video and music-video generation, upscaling, RAG and code intelligence, with renders queued on your own GPU.

    Scan passed
    ★ 248
    2026-10-03
  10. Self-hosted homelab dashboard with a built-in read-only MCP server (hosts, Docker, GPU, services).

    Scan passed
    ★ 214
    2026-10-05
  11. Subscription-aware LLM router for Claude Code: routes tasks to providers like OpenAI, Gemini, Groq and Ollama by complexity, subscription usage and cost.

    Scan passed
    ★ 93
    2026-10-05
  12. Query multiple Ollama models and combine their responses for diverse perspectives on a single question.

    Scan passed
    ★ 88
    2025-04-02
  13. Cybersecurity assessment of documents, questionnaires and reports: multi-format parsing, RAG knowledge base, risks, compliance gaps and remediations.

    Scan passed
    ★ 88
    2026-10-05
  14. by @tobocop2 · Python · tobocop2/lilbee

    Index files, code and crawled websites and answer with source citations, using its own local models or an existing Ollama or LM Studio setup.

    Scan passed
    ★ 62
    2026-10-04
  15. Local-first AI PKM memory for coding conversations.

    Scan passed
    ★ 58
    2026-10-05
  16. Code indexing with SQLite FTS5, tree-sitter and embeddings for symbol search, call graphs, git intelligence and hybrid semantic search.

    Scan passed
    ★ 57
    2026-09-30
  17. Self-hosted server suite for Odoo ERP 15-19, plus GitHub, Portainer, OCA and Teams, with a browser terminal, Qdrant/Ollama memory and Bulgarian localization.

    Scan passed
    ★ 50
    2026-09-30
  18. Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.

    Scan passed
    ★ 43
    2026-10-02
  19. by @gzoonet · TypeScript · gzoonet/cortex

    Local-first developer knowledge graph: watches project files, extracts entities and relationships with LLMs, and offers queries, a web dashboard and a CLI.

    Scan passed
    ★ 23
    2026-09-30
  20. Self-hosted knowledge backend for AI agents with hybrid search and MCP tools

    Scan passed
    ★ 18
    2026-10-05
  21. by @HZYAI · Python · HZYAI/RagScore

    Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

    Scan passed
    ★ 15
    2026-05-29
  22. by @Cavinooo · TypeScript · Cavinooo/claude-find

    Pull Deep Memory from across your Claude Code Sessions — when you need it.

    Scan passed
    ★ 11
    2026-06-10
  23. Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

    Scan passed
    ★ 11
    2026-03-08
  24. by @MetriLLM · TypeScript · MetriLLM/metrillm

    Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

    Scan passed
    ★ 8
    2026-06-02
  25. Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.

    Scan passed
    ★ 6
    2026-10-05
  26. Synthetic monitoring for cloud and local LLM inference endpoints: TTFT, latency, throughput and errors, with Prometheus and OpenTelemetry export.

    Scan passed
    ★ 6
    2026-05-16
  27. by @motock · Python · motock/fagan

    Autonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.

    Scan passed
    ★ 5
    2026-10-05
  28. Search and match German public procurement tenders (OCDS) from your local LLM.

    Scan passed
    ★ 5
    2026-07-26
  29. AI execution pipeline with NAEF logic constraints, VERITAS build gates, semantic vault integration and Tri-Node Cortex validations to curb hallucination.

    Scan passed
    ★ 5
    2026-09-07
  30. by @dimpagk92 · TypeScript · dimpagk92/cellar

    Hybrid computer-use runtime combining the accessibility tree, Chrome DevTools Protocol and vision into structured context, with offline support via Ollama.

    Scan passed
    ★ 5
    2026-09-28
  31. MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens

    Scan passed
    ★ 4
    2026-03-31
  32. SOTA 2026 Yahboom Raspbot v2 ROS 2 MCP Server

    Scan passed
    ★ 4
    2026-09-28
  33. Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.

    Scan passed
    ★ 4
    2026-09-21
  34. Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse of its project logs, with no outbound calls.

    Scan passed
    ★ 4
    2026-06-10
  35. Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.

    Scan passed
    ★ 3
    2026-10-05
  36. Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

    Scan passed
    ★ 3
    2026-09-16
  37. by @Kyrzin · TypeScript · Kyrzin/kybase

    Self-hosted Markdown memory for AI agents: notes you can read and edit, with hybrid search.

    Scan passed
    ★ 3
    2026-10-02
  38. by @Medhovarsh · JavaScript · Medhovarsh/forkmind

    Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.

    Scan passed
    ★ 3
    2026-08-19
  39. Local-first knowledge graphs from your documents: build, search (GraphRAG) and edit on your machine.

    Scan passed
    ★ 3
    2026-10-03
  40. by @iamjrmh · JavaScript · iamjrmh/MCPBridge

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

    Scan passed
    ★ 3
    2026-05-20
  41. Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.

    Scan passed
    ★ 3
    2026-10-05
  42. Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.

    Scan passed
    ★ 2
    2026-07-30
  43. Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion and optional RAG answers via local Ollama.

    Scan passed
    ★ 2
    2026-09-07
  44. Local searchable index of PDFs, EPUBs and Word documents for grounded answers with page and section citations.

    Scan passed
    ★ 1
    2026-09-18
  45. Local meeting pipeline: Whisper transcription plus Ollama summaries, action items and decisions. Reference implementation of the memnex spec.

    Scan passed
    ★ 1
    2026-09-07

Quick install

Add the most popular option to Claude Code:

# see https://github.com/jaspertvdm/mcp-server-ollama-bridge for setup

FAQ

What is the best ollama & local llms mcp server?

By GitHub stars, the most popular is mcp-server-ollama-bridge by @jaspertvdm (4 stars). awesomemcp.in lists 45 MCP servers for this topic, ranked by official status and popularity.

Are these MCP servers safe to install?

44 of 45 passed our automated vulnerability check (OSV.dev advisories for the published package, OpenSSF Scorecard, license, maintenance and provenance). The check is automated and does not guarantee 100% safety — review the code and permissions before installing.

How do I install mcp-server-ollama-bridge?

With Claude Code: # see https://github.com/jaspertvdm/mcp-server-ollama-bridge for setup. Every listing on awesomemcp.in includes an install command and, where available, an mcp.json snippet for Claude Desktop, Cursor and other MCP clients.

Can AI agents read this list?

Yes. The full catalog is available as JSON at https://awesomemcp.in/api/mcps.json and https://awesomemcp.in/api/skills.json, and as plain text at https://awesomemcp.in/llms.txt.

Related topics