Best MCP Servers for AI Models in 2026
1,260 tools indexed · avg score 92.2 · sorted by AgentRank score
The AgentRank index tracks 1,260 ai models tools. The top-ranked entry is open-webui/open-webui at 96.0 points. Across the 10 shown here, the average AgentRank score is 92.2, and 10 had a commit in the last 30 days. The most common primary language is Python.
AI model provider tools give agents programmatic access to language models, embedding models, image generators, and speech services. These range from official provider SDKs (OpenAI, Anthropic, Google) to local inference tools (Ollama, llama.cpp, LM Studio) that run models on your own hardware.
In multi-agent architectures, model provider tools often serve as the "brain" that other specialized agents call. An orchestrator might use a fast, cheap model for routing decisions while delegating complex reasoning tasks to a more capable model — all through a unified model provider interface.
Local inference tools deserve special attention: Ollama in particular has become the standard for running open models (Llama, Mistral, Phi, Gemma) locally. This matters for privacy-sensitive workloads, offline operation, and cost control at scale. The tradeoff is hardware requirements and latency vs. API-based models.
Top 10 AI Models MCP Servers
- Ranks here on adopted by 272 downstream projects and 155k GitHub stars, plus an active commit 8 days ago.Dependents 22.0Freshness 19.9Issue health 19.6Downloads 13.0Stars 10.0
- #2LibreChat-AI/LibreChat95.0
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching,...
Ranks here on 46k GitHub stars and a commit within the last week, plus 84% of issues closed.Freshness 30.7Issue health 25.7Stars 15.4Contributors 12.3Description 6.2 - #3clay-good/OpenLore94.5
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
Ranks here on 320 GitHub stars and a commit within the last week, plus 100% of issues closed.Issue health 30.8Freshness 30.6Stars 12.9Contributors 11.2License 4.6 - #4raullenchai/Rapid-MLX93.1
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster t...
Ranks here on 4.0k GitHub stars and a commit within the last week, plus 98% of issues closed.Freshness 25.6Issue health 25.1Downloads 13.4Stars 12.8Contributors 10.3 - #5PDFMathTranslate/PDFMathTranslate92.7
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero
Ranks here on 38k GitHub stars and a commit within the last week, plus 82% of issues closed.Freshness 30.7Issue health 25.3Stars 15.4Contributors 12.3Description 6.2 - #6stacklok/toolhive92.0
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
Ranks here on 2.3k GitHub stars and a commit within the last week, plus 80% of issues closed.Freshness 30.7Issue health 24.6Stars 15.4Contributors 12.3License 4.6 - #7thevibeworks/claude-code-docs90.5
Everything Anthropic ships for builders, archived and updated 4× daily. 3,900+ files. 12 sources. API, Claude Code, MCP, docs, cookbooks, skills, plugins.
Ranks here on a commit within the last week and 96% of issues closed.Freshness 30.7Issue health 29.5Stars 11.1Contributors 8.4Description 6.2 - #8jacob-bd/perplexity-web-mcp90.0
MCP server and Anthropic API-compatible interface for Perplexity AI web interface
Ranks here on 200 GitHub stars and an active commit 16 days ago, plus 100% of issues closed.Issue health 30.8Freshness 27.5Stars 11.8Contributors 8.4License 4.6 - #9houtini-ai/houtini-lm89.5
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Ranks here on an active commit 10 days ago and 100% of issues closed.Issue health 30.8Freshness 29.6Stars 10.7Contributors 6.5Description 6.2 - #10varun29ankuS/shodh-memory89.1
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
Ranks here on 306 GitHub stars and an active commit 8 days ago, plus 79% of issues closed.Freshness 30.3Issue health 24.4Stars 12.8Contributors 10.4Description 6.2
More AI Models MCP Servers
| # | Tool | Score | Stars | Last Commit | Language |
|---|---|---|---|---|---|
| 11 | MerkyorLynn/Lynn | 53 | 8d ago | TypeScript | |
| 12 | artokun/comfyui-mcp-panel | 127 | 15d ago | JavaScript | |
| 13 | waybarrios/vllm-mlx | 1.6k | 7d ago | Python | |
| 14 | AtomicBot-ai/atomic-agent | 3.3k | 7d ago | TypeScript | |
| 15 | ASCIT31/Dark-Moon | 1.0k | 19d ago | Python | |
| 16 | 7df-lab/devo | 322 | 7d ago | Rust | |
| 17 | mudler/LocalAI | 50k | 7d ago | Go | |
| 18 | HoldMyBeer-gg/blenderwright | 168 | 11d ago | Python | |
| 19 | kekzl/imp | 44 | 7d ago | C++ | |
| 20 | aovestdipaperino/plank | 35 | 7d ago | Rust | |
| 21 | bug-ops/zeph | 64 | 13d ago | Rust | |
| 22 | plmbr/notebook-intelligence | 347 | 14d ago | Python | |
| 23 | cloud-apim/otoroshi-llm-extension | 19 | 10d ago | Scala | |
| 24 | managoat/fountain | 16 | 7d ago | Elixir | |
| 25 | PyModel/pythinker-code | 29 | 8d ago | TypeScript | |
| 26 | blakeox/courtlistener-mcp | 15 | 14d ago | TypeScript | |
| 27 | makifbaysal/tasktrooper | 112 | 8d ago | Go | |
| 28 | yuzushi-dev/Sando | 51 | 11d ago | JavaScript | |
| 29 | tonhowtf/omniget | 14k | 25d ago | Rust | |
| 30 | vshulcz/deja-vu | 1.2k | 7d ago | Go | |
| 31 | blak0p/git-courer | 44 | 10d ago | Go | |
| 32 | Muvon/octomind | 162 | 8d ago | Rust | |
| 33 | helv-io/skgate | 10 | 7d ago | Go | |
| 34 | shashankswe2020-ux/rigspark | 20 | 7d ago | Rust | |
| 35 | chalie-ai/chalie | 25 | 7d ago | Python | |
| 36 | mockzilla/mockzilla-mcp | 5 | 10d ago | JavaScript | |
| 37 | arcobaleno64/agy-plugin-cc | 14 | 8d ago | JavaScript | |
| 38 | AbyssCN/oh-my-dag | 43 | 8d ago | TypeScript | |
| 39 | launchapp-dev/animus-cli | 39 | 7d ago | Rust | |
| 40 | fkiene/llmtrim | 246 | 18d ago | Rust | |
| 41 | everyapi-ai/everyapi-ai | 3 | 10d ago | Go | |
| 42 | majiayu000/sage | 12 | 12d ago | Rust | |
| 43 | hussainn7/plip-oss | 29 | 10d ago | Python | |
| 44 | Veloresearch/velocity-local-services | 24 | 7d ago | — | |
| 45 | truehot/LMLocal | 28 | 9d ago | C# | |
| 46 | permacommons/chabeau | 41 | 9d ago | Rust | |
| 47 | rokbenko/quackd | 259 | 7d ago | Python | |
| 48 | linuxserver/docker-lm-studio | 7 | 8d ago | Shell | |
| 49 | weselben/gomodel-admin-mcp | 3 | 7d ago | TypeScript | |
| 50 | TheVingance/TCC-PromptInjection | 13 | 11d ago | Python |