Google PageRank for AI agents. 25,000+ tools indexed.

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

  1. #1
    open-webui/open-webui

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

    96.0
    Ranks here on adopted by 272 downstream projects and 155k GitHub stars, plus an active commit 8 days ago.
    Dependents
    22.0
    Freshness
    19.9
    Issue health
    19.6
    Downloads
    13.0
    Stars
    10.0
    ★ 155k commit 7d ago Python 272 dependents
  2. #2
    LibreChat-AI/LibreChat

    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,...

    95.0
    Ranks here on 46k GitHub stars and a commit within the last week, plus 84% of issues closed.
    Freshness
    30.7
    Issue health
    25.7
    Stars
    15.4
    Contributors
    12.3
    Description
    6.2
    ★ 46k commit 7d ago TypeScript
  3. #3
    clay-good/OpenLore

    Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

    94.5
    Ranks here on 320 GitHub stars and a commit within the last week, plus 100% of issues closed.
    Issue health
    30.8
    Freshness
    30.6
    Stars
    12.9
    Contributors
    11.2
    License
    4.6
    ★ 320 commit 7d ago TypeScript
  4. #4
    raullenchai/Rapid-MLX

    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...

    93.1
    Ranks here on 4.0k GitHub stars and a commit within the last week, plus 98% of issues closed.
    Freshness
    25.6
    Issue health
    25.1
    Downloads
    13.4
    Stars
    12.8
    Contributors
    10.3
    ★ 4.0k commit 7d ago Python
  5. #5
    PDFMathTranslate/PDFMathTranslate

    [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

    92.7
    Ranks here on 38k GitHub stars and a commit within the last week, plus 82% of issues closed.
    Freshness
    30.7
    Issue health
    25.3
    Stars
    15.4
    Contributors
    12.3
    Description
    6.2
    ★ 38k commit 7d ago Python
  6. #6
    stacklok/toolhive

    ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

    92.0
    Ranks here on 2.3k GitHub stars and a commit within the last week, plus 80% of issues closed.
    Freshness
    30.7
    Issue health
    24.6
    Stars
    15.4
    Contributors
    12.3
    License
    4.6
    ★ 2.3k commit 7d ago Go
  7. #7
    thevibeworks/claude-code-docs

    Everything Anthropic ships for builders, archived and updated 4× daily. 3,900+ files. 12 sources. API, Claude Code, MCP, docs, cookbooks, skills, plugins.

    90.5
    Ranks here on a commit within the last week and 96% of issues closed.
    Freshness
    30.7
    Issue health
    29.5
    Stars
    11.1
    Contributors
    8.4
    Description
    6.2
    ★ 143 commit 7d ago Jupyter Notebook
  8. #8
    jacob-bd/perplexity-web-mcp

    MCP server and Anthropic API-compatible interface for Perplexity AI web interface

    90.0
    Ranks here on 200 GitHub stars and an active commit 16 days ago, plus 100% of issues closed.
    Issue health
    30.8
    Freshness
    27.5
    Stars
    11.8
    Contributors
    8.4
    License
    4.6
    ★ 200 commit 15d ago Python
  9. #9
    houtini-ai/houtini-lm

    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.

    89.5
    Ranks here on an active commit 10 days ago and 100% of issues closed.
    Issue health
    30.8
    Freshness
    29.6
    Stars
    10.7
    Contributors
    6.5
    Description
    6.2
    ★ 121 commit 10d ago TypeScript
  10. #10
    varun29ankuS/shodh-memory

    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.

    89.1
    Ranks here on 306 GitHub stars and an active commit 8 days ago, plus 79% of issues closed.
    Freshness
    30.3
    Issue health
    24.4
    Stars
    12.8
    Contributors
    10.4
    Description
    6.2
    ★ 306 commit 8d ago Rust

More AI Models MCP Servers

# Tool Score Stars Last Commit Language
11 MerkyorLynn/Lynn 88.4 53 8d ago TypeScript
12 artokun/comfyui-mcp-panel 87.8 127 15d ago JavaScript
13 waybarrios/vllm-mlx 87.6 1.6k 7d ago Python
14 AtomicBot-ai/atomic-agent 87.3 3.3k 7d ago TypeScript
15 ASCIT31/Dark-Moon 87.2 1.0k 19d ago Python
16 7df-lab/devo 87.1 322 7d ago Rust
17 mudler/LocalAI 86.8 50k 7d ago Go
18 HoldMyBeer-gg/blenderwright 86.5 168 11d ago Python
19 kekzl/imp 86.3 44 7d ago C++
20 aovestdipaperino/plank 85.5 35 7d ago Rust
21 bug-ops/zeph 85.3 64 13d ago Rust
22 plmbr/notebook-intelligence 84.9 347 14d ago Python
23 cloud-apim/otoroshi-llm-extension 84.8 19 10d ago Scala
24 managoat/fountain 84.7 16 7d ago Elixir
25 PyModel/pythinker-code 84.5 29 8d ago TypeScript
26 blakeox/courtlistener-mcp 84.4 15 14d ago TypeScript
27 makifbaysal/tasktrooper 84.0 112 8d ago Go
28 yuzushi-dev/Sando 83.9 51 11d ago JavaScript
29 tonhowtf/omniget 83.8 14k 25d ago Rust
30 vshulcz/deja-vu 83.2 1.2k 7d ago Go
31 blak0p/git-courer 83.0 44 10d ago Go
32 Muvon/octomind 82.8 162 8d ago Rust
33 helv-io/skgate 82.1 10 7d ago Go
34 shashankswe2020-ux/rigspark 81.7 20 7d ago Rust
35 chalie-ai/chalie 81.4 25 7d ago Python
36 mockzilla/mockzilla-mcp 81.0 5 10d ago JavaScript
37 arcobaleno64/agy-plugin-cc 80.5 14 8d ago JavaScript
38 AbyssCN/oh-my-dag 80.2 43 8d ago TypeScript
39 launchapp-dev/animus-cli 79.9 39 7d ago Rust
40 fkiene/llmtrim 79.4 246 18d ago Rust
41 everyapi-ai/everyapi-ai 79.2 3 10d ago Go
42 majiayu000/sage 79.0 12 12d ago Rust
43 hussainn7/plip-oss 78.6 29 10d ago Python
44 Veloresearch/velocity-local-services 78.6 24 7d ago —
45 truehot/LMLocal 78.5 28 9d ago C#
46 permacommons/chabeau 78.2 41 9d ago Rust
47 rokbenko/quackd 77.7 259 7d ago Python
48 linuxserver/docker-lm-studio 77.7 7 8d ago Shell
49 weselben/gomodel-admin-mcp 77.3 3 7d ago TypeScript
50 TheVingance/TCC-PromptInjection 77.3 13 11d ago Python