Aarnxen Multiai MCP

⚡ AarnXen Multi-AI MCP Server

The most powerful multi-model AI orchestration server for Claude Code

Quick Start • 31 Tools • 25+ Models • Architecture • Memory Flywheel

______________________________________________________________________

AarnXen是什么？

AarnXen （ax)是a 多模型AI编排MCP服务器 这使Claude Code能够访问多个提供商的25个以上的AI模型。它超越了简单的聊天——它提供 对抗性辩论, 验证链, 陪审团投票, 自我完善, 网接地和a 持久知识库 从每一次互动中学习。

没有其他MCP服务器将多模型编排模式与持久内存和生产基础设施相结合。

关键差异点

______________________________________________________________________

建筑

graph TB
    subgraph Claude Code
        CC[Claude Code / MCP Client]
    end

    subgraph "AarnXen MCP Server (ax)"
        CC -->|MCP Protocol| MW[Tool Middleware]
        MW -->|rate limit, guardrails, events| TOOLS

        subgraph TOOLS["31 Tools"]
            direction LR
            AI["AI Tools
chat, consensus, compare
think, codereview, precommit
challenge, swarm, pipeline
debate, verify, jury, refine"]
            WEB["Web Tools
web_search
web_fetch"]
            KB["KB Tools
kb_store, kb_search
kb_get, kb_remember
kb_recall, kb_relate
kb_search_index
kb_timeline
kb_get_observations
kb_stats"]
            SYS["System Tools
costs, list_models
provider_health
health, events
kb_consolidate"]
        end

        TOOLS --> ROUTER[Smart Router]
        ROUTER -->|tier selection| REG[Provider Registry]
        ROUTER |learns from| KBD[(Knowledge DB)]

        subgraph Providers
            direction LR
            GEM[Gemini API
2.5 Pro, 2.5 Flash
3.1 Pro, 3 Flash]
            OLL[Ollama Cloud
DeepSeek, Kimi
Qwen, GLM, MiniMax
GPT-OSS, Mistral
Cogito, Devstral]
        end

        REG --> GEM
        REG --> OLL

        subgraph Infrastructure
            direction LR
            CACHE[Response Cache
TTL + LRU]
            CB[Circuit Breaker
3-state]
            COST[Cost Tracker
per-request USD]
            EVENTS[Event Bus
async pub/sub]
            GUARD[Guardrails
content filter]
            RATE[Rate Limiter
per-tool]
        end
    end

    style TOOLS fill:#1a1a2e,stroke:#16213e,color:#fff
    style Providers fill:#0f3460,stroke:#16213e,color:#fff
    style Infrastructure fill:#533483,stroke:#16213e,color:#fff

记忆飞轮

其他MCP服务器所没有的独特的自我改进循环：

graph LR
    A[AI Tool Called] -->|auto-learn middleware| B[Store Performance
latency, tokens, cost]
    B --> C[(Knowledge DB
SQLite + FTS5)]
    C -->|memory-informed routing| D[Smart Router
reorders by real perf]
    D -->|picks fastest model| A

    style A fill:#e94560,stroke:#16213e,color:#fff
    style B fill:#533483,stroke:#16213e,color:#fff
    style C fill:#0f3460,stroke:#16213e,color:#fff
    style D fill:#1a1a2e,stroke:#16213e,color:#fff

每个AI工具调用都会自动存储模型性能指标。智能路由器查询此数据以选择最快的可用型号-- 每次交互，系统都会变得更智能.

______________________________________________________________________

快速开始

先决条件

• Python 3.11+
• 紫外线 （推荐）或pip
• 至少一个API密钥（Gemini免费层效果很好）

安装

# Clone
git clone https://github.com/Abhishek-Kraj/AarnXen-MultiAI-MCP.git
cd AarnXen-MultiAI-MCP

# Install (pick one)
uv sync                              # recommended
pip install -e .                      # alternative

# Configure
mkdir -p ~/.aarnxen
cp config.example.yaml ~/.aarnxen/config.yaml
# Edit config.yaml — add your API keys

# Verify
uv run pytest tests/ -q              # 269 tests should pass

添加到克劳德代码

选项A-CLI（推荐）：

claude mcp add ax -s user -- uv --directory /path/to/AarnXen-MultiAI-MCP run ax

选项B——手动配置 (~/.claude/settings.json):

{
  "mcpServers": {
    "ax": {
      "command": "uv",
      "args": ["--directory", "/path/to/AarnXen-MultiAI-MCP", "run", "ax"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-key",
        "OLLAMA_CLOUD_KEY": "your-ollama-cloud-key"
      }
    }
  }
}

提示： 服务器注册为 ax --所有工具显示为 mcp__ax__chat, mcp__ax__consensus等等。

______________________________________________________________________

工具

人工智能编排工具（15）

知识库工具（10）

系统工具（6）

______________________________________________________________________

模型

Gemini（本地API）

Ollama Cloud（20多种型号，免费）

所有Ollama Cloud型号均 自由 -无API成本。Smart Router会根据预算级别的任务对它们进行优先级排序。

智能路由层

graph LR
    subgraph Budget["💰 Budget Tier"]
        B1[gemini-3.1-flash-lite]
        B2[gemini-3-flash]
        B3[gpt-oss:20b]
        B4[qwen3.5:397b]
    end

    subgraph Balanced["⚖️ Balanced Tier"]
        M1[kimi-k2:1t]
        M2[deepseek-v3.2]
        M3[glm-5]
        M4[mistral-large-3:675b]
    end

    subgraph Premium["👑 Premium Tier"]
        P1[gemini-3.1-pro]
        P2[kimi-k2-thinking]
        P3[minimax-m2.5]
        P4[cogito-2.1:671b]
    end

    Q[Query] --> R{Smart Router}
    R -->|simple task| Budget
    R -->|general task| Balanced
    R -->|complex reasoning| Premium

    style Budget fill:#2d6a4f,stroke:#1b4332,color:#fff
    style Balanced fill:#e85d04,stroke:#dc2f02,color:#fff
    style Premium fill:#7b2cbf,stroke:#5a189a,color:#fff

______________________________________________________________________

用法示例

基本聊天

"Use ax chat to ask gemini-2.5-flash about Python async patterns"

多模型共识

"Use ax consensus to get opinions from 3 models on microservices vs monolith"

对抗性辩论

"Use ax debate with topic='Is Rust better than Go for backend services?' rounds=3"

事实核查

"Use ax verify with claim='Python is the most popular programming language' web_check=true"

评审团评价

"Use ax jury to score this code with criteria=code and num_jurors=5"

自我精炼

"Use ax refine with prompt='Write a Redis connection pool in Python' iterations=3"

代码审查

"Use ax codereview with focus=security on this authentication handler"

预提交检查

"Use ax precommit to review my staged changes"

网络研究

"Use ax web_search for 'best practices for MCP server development'"
"Use ax web_fetch url='https://docs.anthropic.com/en/docs/agents-and-tools/mcp'"

知识库

"Use ax kb_remember 'Always use connection pooling for PostgreSQL in production'"
"Use ax kb_recall 'PostgreSQL'"
"Use ax kb_search 'database optimization'"

管道（链式工具）

"Use ax pipeline with steps:
  1. web_search for 'Python GIL changes in 3.13'
  2. think about the implications
  3. codereview on our threading code"

______________________________________________________________________

工具交互模式

graph TD
    subgraph "Single Model"
        chat[chat]
        think[think]
        codereview[codereview]
    end

    subgraph "Multi-Model Parallel"
        consensus[consensus]
        jury[jury]
        swarm[swarm]
    end

    subgraph "Multi-Model Sequential"
        debate[debate
FOR ↔ AGAINST → Judge]
        verify[verify
Draft → Questions → Answers → Verdict]
        refine[refine
Generate → Critique → Refine × N]
        pipeline[pipeline
Tool₁ → Tool₂ → Tool₃]
    end

    subgraph "Web Grounding"
        web_search[web_search]
        web_fetch[web_fetch]
    end

    verify -.->|optional web_check| web_search

    style chat fill:#2d6a4f,color:#fff
    style think fill:#2d6a4f,color:#fff
    style codereview fill:#2d6a4f,color:#fff
    style consensus fill:#e85d04,color:#fff
    style jury fill:#e85d04,color:#fff
    style swarm fill:#e85d04,color:#fff
    style debate fill:#7b2cbf,color:#fff
    style verify fill:#7b2cbf,color:#fff
    style refine fill:#7b2cbf,color:#fff
    style pipeline fill:#7b2cbf,color:#fff
    style web_search fill:#1d3557,color:#fff
    style web_fetch fill:#1d3557,color:#fff

______________________________________________________________________

配置

最小配置(~/.aarnxen/config.yaml)

default_model: "auto"
default_temperature: 0.7

providers:
  - name: gemini
    api_key_env: GEMINI_API_KEY
    priority: 1
    models:
      - gemini-2.5-pro
      - gemini-2.5-flash
      - gemini-3.1-pro-preview
      - gemini-3-flash-preview

cache:
  enabled: true
  ttl_seconds: 3600

memory:
  enabled: true
  path: "~/.aarnxen/conversations.db"

cost_tracking: true

Ollama Cloud的完整配置

providers:
  - name: gemini
    api_key_env: GEMINI_API_KEY
    priority: 1
    models:
      - gemini-3.1-pro-preview
      - gemini-3-flash-preview
      - gemini-2.5-pro
      - gemini-2.5-flash
      - gemini-2.5-flash-lite

  - name: ollama-cloud
    base_url: "https://ollama.com"
    api_key_env: OLLAMA_CLOUD_KEY
    priority: 2
    models:
      - deepseek-v3.2
      - kimi-k2:1t-cloud
      - kimi-k2.5
      - kimi-k2-thinking
      - qwen3.5:397b-cloud
      - glm-5
      - minimax-m2.5
      # ... see config.example.yaml for full list

______________________________________________________________________

仪表盘

AarnXen包括一个 零依赖web仪表板 该自动程序从MCP服务器启动。

http://localhost:8765

特征：

• 实时模型状态和延迟
• 每个型号/供应商的成本跟踪
• 事件流查看器
• 知识库统计

独立运行： aarnxen-dashboard 或 ax （仪表板自动启动）

______________________________________________________________________

基础设施

中间件管道

每个工具调用都通过中间件堆栈：

sequenceDiagram
    participant C as Claude Code
    participant MW as Middleware
    participant RL as Rate Limiter
    participant GR as Guardrails
    participant T as Tool Handler
    participant AL as Auto-Learn
    participant EB as Event Bus

    C->>MW: tool call
    MW->>RL: check rate limit
    RL-->>MW: ✅ allowed
    MW->>GR: validate input
    GR-->>MW: ✅ safe
    MW->>EB: emit tool.start
    MW->>T: execute handler
    T-->>MW: result
    MW->>AL: store model performance
    MW->>EB: emit tool.complete
    MW-->>C: response

断路器

三态断路器可防止供电中断：

CLOSED → (3 failures) → OPEN → (30s cooldown) → HALF_OPEN → (1 success) → CLOSED
                                                            → (1 failure) → OPEN

三层知识库搜索

针对代币效率进行了优化：

10倍代币节省 vs提前获取所有东西。

______________________________________________________________________

发展

# Install dev dependencies
uv sync --group dev

# Run tests
uv run pytest tests/ -q                    # all 269 tests
uv run pytest tests/test_router.py -q      # specific module
uv run pytest tests/ -q -x                 # stop on first failure

# Run server locally
uv run ax

# Run dashboard standalone
uv run aarnxen-dashboard

项目结构

src/aarnxen/
├── server.py              # FastMCP server + tool registration
├── config.py              # YAML config loader
├── dashboard.py           # Web dashboard (auto-starts)
├── core/
│   ├── router.py          # Smart 3-tier routing + memory-informed
│   ├── tool_middleware.py  # Rate limit, guardrails, events, auto-learn
│   ├── knowledge.py       # SQLite + FTS5 knowledge base
│   ├── circuit_breaker.py # 3-state circuit breaker
│   ├── events.py          # Async event bus
│   ├── guardrails.py      # Content filtering
│   ├── rate_limit.py      # Per-tool rate limiting
│   ├── cost.py            # USD cost tracking
│   ├── cache.py           # TTL + LRU response cache
│   ├── retry.py           # Exponential backoff + fallback
│   ├── conversation.py    # Persistent conversation memory
│   ├── extractor.py       # Entity extraction
│   └── validation.py      # Input validation
├── providers/
│   ├── registry.py        # Provider registry + model resolution
│   ├── base.py            # Base provider interface
│   ├── gemini.py          # Google Gemini (native SDK)
│   ├── ollama.py          # Ollama Local + Cloud
│   └── openai_compat.py   # OpenAI-compatible endpoints
├── tools/
│   ├── chat.py            # Single model chat
│   ├── consensus.py       # Parallel multi-model
│   ├── compare.py         # A/B comparison
│   ├── think.py           # Deep reasoning
│   ├── codereview.py      # Code review
│   ├── precommit.py       # Pre-commit gate
│   ├── challenge.py       # Devil's advocate
│   ├── debate.py          # Adversarial debate
│   ├── verify.py          # Chain of Verification
│   ├── jury.py            # N-model jury voting
│   ├── refine.py          # Self-Refine
│   ├── web_search.py      # DuckDuckGo search
│   ├── web_fetch.py       # URL → markdown
│   ├── swarm.py           # Parallel sub-tasks
│   └── pipeline.py        # Sequential tool chain
└── pricing/
    └── models.py          # Per-model pricing data

______________________________________________________________________

分支

______________________________________________________________________

许可证

麻省理工学院——见 许可证

______________________________________________________________________

Built by Abhishek

Making AI orchestration accessible, powerful, and self-improving.