Vector MCP (Knuckles Team)

矢量数据库-A2A|AG-UI|MCP

*版本：1.10.0*

概述

这是一个MCP服务器实现，允许标准化 跨矢量数据库技术的采集管理系统。

这在很大程度上受到了微软Autogen V1框架的RAG实现的启发， 这被更改为MCP服务器模型。

AI代理可以：

• 混合搜索文档信息（词汇/向量）
• 使用存储在本地文件系统或URL上的文档创建集合
• 将文档添加到集合
• 利用集合进行检索增强生成（RAG）
• 删除收藏

支持：

• 色度数据库
• PG向量
• Couchbase 的
• Qdrant
• MongoDB

此存储库正在积极维护中-欢迎投稿和错误报告！

计划进行自动化测试

主控程序

MCP工具

A2A代理

架构：

---
config:
  layout: dagre
---
flowchart TB
 subgraph subGraph0["Agent Capabilities"]
        C["Agent"]
        B["A2A Server - Uvicorn/FastAPI"]
        D["MCP Tools"]
        F["Agent Skills"]
  end
    C --> D & F
    A["User Query"] --> B
    B --> C
    D --> E["Platform API"]

     C:::agent
     B:::server
     A:::server
    classDef server fill:#f9f,stroke:#333
    classDef agent fill:#bbf,stroke:#333,stroke-width:2px
    style B stroke:#000000,fill:#FFD600
    style D stroke:#000000,fill:#BBDEFB
    style F fill:#BBDEFB
    style A fill:#C8E6C9
    style subGraph0 fill:#FFF9C4

组件交互图

sequenceDiagram
    participant User
    participant Server as A2A Server
    participant Agent as Agent
    participant Skill as Agent Skills
    participant MCP as MCP Tools

    User->>Server: Send Query
    Server->>Agent: Invoke Agent
    Agent->>Skill: Analyze Skills Available
    Skill->>Agent: Provide Guidance on Next Steps
    Agent->>MCP: Invoke Tool
    MCP-->>Agent: Tool Response Returned
    Agent-->>Agent: Return Results Summarized
    Agent-->>Server: Final Response
    Server-->>User: Output

用法

MCP-CLI

用作MCP服务器

MCP服务器可以在两种模式下运行： stdio （用于本地测试）或 http （用于网络访问）。要启动服务器，请使用以下命令：

在stdio模式下运行（默认）：

vector-mcp --transport "stdio"

在HTTP模式下运行：

vector-mcp --transport "http"  --host "0.0.0.0"  --port "8000"

创建收藏

AI提示：

Create a collection called zapdos with the documents in this directory:
/home/user/Documents/Chroma

AI回应：

The collection named "zapdos" has been successfully created or retrieved from the vector database
using the documents in the directory /home/user/Documents/Chroma.
Let me know if you'd like to perform any further actions, such as querying the collection or adding more documents!

从集合中检索

AI提示：

Create a collection called zapdos with the documents in this directory:
/home/user/Documents/Chroma

AI回应：

The collection named "zapdos" has been successfully created or retrieved from the vector database
using the documents in the directory /home/user/Documents/Chroma.
Let me know if you'd like to perform any further actions, such as querying the collection or adding more documents!

删除收藏

AI提示：

Delete the collection called memory

AI回应：

The collection named "memory" has been successfully deleted.
Let me know if you'd like to create a new collection or perform any other actions!

A2A-CLI

端点

• Web 用户界面: http://localhost:8000/ （如果启用）
• A2A: http://localhost:8000/a2a （发现： /a2a/.well-known/agent.json)
• AG-UI: http://localhost:8000/ag-ui （职位）

将MCP服务器部署为服务

MCP服务器可以使用Docker部署，具有可配置的身份验证、中间件和Eunomia授权。

使用Docker运行

docker pull knucklessg1/vector-mcp:latest

docker run -d \
  --name vector-mcp \
  -p 8004:8004 \
  -e HOST=0.0.0.0 \
  -e PORT=8004 \
  -e TRANSPORT=http \
  -e AUTH_TYPE=none \
  -e EUNOMIA_TYPE=none \
  knucklessg1/vector-mcp:latest

对于高级身份验证（例如JWT、OAuth代理、OIDC代理、远程OAuth）或Eunomia，添加相关的环境变量：

docker run -d \
  --name vector-mcp \
  -p 8004:8004 \
  -e HOST=0.0.0.0 \
  -e PORT=8004 \
  -e TRANSPORT=http \
  -e AUTH_TYPE=oidc-proxy \
  -e OIDC_CONFIG_URL=https://provider.com/.well-known/openid-configuration \
  -e OIDC_CLIENT_ID=your-client-id \
  -e OIDC_CLIENT_SECRET=your-client-secret \
  -e OIDC_BASE_URL=https://your-server.com \
  -e ALLOWED_CLIENT_REDIRECT_URIS=http://localhost:*,https://*.example.com/* \
  -e EUNOMIA_TYPE=embedded \
  -e EUNOMIA_POLICY_FILE=/app/mcp_policies.json \
  knucklessg1/vector-mcp:latest

使用Docker Compose

创建一个 docker-compose.yml 文件：

services:
  vector-mcp:
    image: knucklessg1/vector-mcp:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8004
      - TRANSPORT=http
      - AUTH_TYPE=none
      - EUNOMIA_TYPE=none
    ports:
      - 8004:8004

对于具有身份验证和Eunomia的高级设置：

services:
  vector-mcp:
    image: knucklessg1/vector-mcp:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8004
      - TRANSPORT=http
      - AUTH_TYPE=oidc-proxy
      - OIDC_CONFIG_URL=https://provider.com/.well-known/openid-configuration
      - OIDC_CLIENT_ID=your-client-id
      - OIDC_CLIENT_SECRET=your-client-secret
      - OIDC_BASE_URL=https://your-server.com
      - ALLOWED_CLIENT_REDIRECT_URIS=http://localhost:*,https://*.example.com/*
      - EUNOMIA_TYPE=embedded
      - EUNOMIA_POLICY_FILE=/app/mcp_policies.json
    ports:
      - 8004:8004
    volumes:
      - ./mcp_policies.json:/app/mcp_policies.json

运行服务：

docker-compose up -d

配置 mcp.json AI集成

{
  "mcpServers": {
    "vector_mcp": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "vector-mcp",
        "vector-mcp"
      ],
      "env": {
        "DATABASE_TYPE": "chromadb",                   // Optional
        "COLLECTION_NAME": "memory",                   // Optional
        "DOCUMENT_DIRECTORY": "/home/user/Documents/"  // Optional
      },
      "timeout": 300000
    }
  }
}

安装Python包

python -m pip install vector-mcp

PGVector依赖关系

python -m pip install vector-mcp[postgres]

全部

python -m pip install vector-mcp[all]

或

uv pip install --upgrade vector-mcp[all]

存储库所有者

微软Autogen V1特别推荐♥️

MCP配置示例

1.标准IO（stdio）部署

{
  "mcpServers": {
    "vector-mcp": {
      "command": "uv",
      "args": [
        "run",
        "vector-mcp"
      ],
      "env": {
        "AGENT_DESCRIPTION": "",
        "AGENT_SYSTEM_PROMPT": "",
        "API_TOKEN": "",
        "CHUNK_SIZE": "",
        "COLLECTION_MANAGEMENTTOOL": "True",
        "COLLECTION_NAME": "",
        "DATABASE_PATH": "",
        "DATABASE_TYPE": "",
        "DBNAME": "",
        "DB_HOST": "",
        "DB_PORT": "",
        "DEFAULT_AGENT_NAME": "",
        "DOCUMENT_DIRECTORY": "",
        "LLM_API_KEY": "",
        "LLM_BASE_URL": "",
        "MISCTOOL": "True",
        "MODEL_ID": "",
        "PASSWORD": "",
        "PROVIDER": "",
        "SEARCHTOOL": "True",
        "USERNAME": ""
      }
    }
  }
}

2.流式HTTP（SSE）部署

{
  "mcpServers": {
    "vector-mcp": {
      "command": "uv",
      "args": [
        "run",
        "vector-mcp",
        "--transport",
        "http",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ],
      "env": {
        "AGENT_DESCRIPTION": "",
        "AGENT_SYSTEM_PROMPT": "",
        "API_TOKEN": "",
        "CHUNK_SIZE": "",
        "COLLECTION_MANAGEMENTTOOL": "True",
        "COLLECTION_NAME": "",
        "DATABASE_PATH": "",
        "DATABASE_TYPE": "",
        "DBNAME": "",
        "DB_HOST": "",
        "DB_PORT": "",
        "DEFAULT_AGENT_NAME": "",
        "DOCUMENT_DIRECTORY": "",
        "LLM_API_KEY": "",
        "LLM_BASE_URL": "",
        "MISCTOOL": "True",
        "MODEL_ID": "",
        "PASSWORD": "",
        "PROVIDER": "",
        "SEARCHTOOL": "True",
        "USERNAME": ""
      }
    }
  }
}