Skip to main content
Glama
enesjakozh
ubie-oss

MCP Server for Vertex AI Search

by ubie-oss
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Vertex AI Search 的 MCP 服务器

这是一个使用 Vertex AI 搜索文档的 MCP 服务器。

建筑学

此解决方案结合 Gemini 与 Vertex AI 基础功能，使用您的私人数据搜索文档。基础功能通过将 Gemini 的响应与存储在 Vertex AI 数据存储区中的数据相结合，从而提高搜索结果的质量。我们可以将一个或多个 Vertex AI 数据存储区集成到 MCP 服务器。有关基础功能的更多详细信息，请参阅Vertex AI 基础文档。

建筑学

Related MCP server: ickyMCP

如何使用

有两种方法可以使用此 MCP 服务器。如果您想在 Docker 上运行它，则第一种方法比较好，因为项目中提供了 Dockerfile。

1. 克隆存储库

# Clone the repository
git clone git@github.com:ubie-oss/mcp-vertexai-search.git

# Create a virtual environment
uv venv
# Install the dependencies
uv sync --all-extras

# Check the command
uv run mcp-vertexai-search

安装python包

该软件包尚未发布到 PyPI，但我们可以从仓库中安装它。我们需要一个源自config.yml.template的配置文件来运行 MCP 服务器，因为 Python 软件包中不包含配置模板。有关配置文件的详细信息，请参阅附录 A：配置文件。

# Install the package
pip install git+https://github.com/ubie-oss/mcp-vertexai-search.git

# Check the command
mcp-vertexai-search --help

发展

先决条件

设置本地环境

# Optional: Install uv
python -m pip install -r requirements.setup.txt

# Create a virtual environment
uv venv
uv sync --all-extras

运行 MCP 服务器

它支持两种传输方式：SSE（服务器发送事件）和 stdio（标准输入输出）。我们可以通过设置--transport标志来控制传输。

我们可以使用 YAML 文件配置 MCP 服务器。config.yml.template是配置文件的模板。请根据自己的需求修改配置文件。

uv run mcp-vertexai-search serve \
    --config config.yml \
    --transport <stdio|sse>

测试 Vertex AI 搜索

我们可以在不使用 MCP 服务器的情况下使用mcp-vertexai-search search命令来测试 Vertex AI Search。

uv run mcp-vertexai-search search \
    --config config.yml \
    --query <your-query>

附录 A：配置文件

config.yml.template是配置文件的模板。

  • server

    • server.name ：MCP 服务器的名称

  • model

    • model.model_name ：Vertex AI 模型的名称

    • model.project_id ：Vertex AI 模型的项目 ID

    • model.location ：模型的位置（例如 us-central1）

    • model.impersonate_service_account ：要模拟的服务帐户

    • model.generate_content_config ：生成内容 API 的配置

  • data_stores ：Vertex AI 数据存储列表

    • data_stores.project_id ：Vertex AI 数据存储的项目 ID

    • data_stores.location ：Vertex AI 数据存储的位置（例如我们）

    • data_stores.datastore_id ：Vertex AI 数据存储的 ID

    • data_stores.tool_name ：工具的名称

    • data_stores.description ：Vertex AI 数据存储的描述

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

  • Needle
    com.needle-ai.mcp

    The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.

    RAG SystemsSearchFile Systems
    2
  • Google MapsA
    com.googleapis.mapstools

    The Google Maps MCP server is a fully-managed server provided by the Maps Grounding Lite API that connects AI applications to Google Maps Platform services. It provides three main tools for building LLM applications: searching for places, looking up weather information, and computing routes with details like distance and travel time. The server acts as a proxy that translates Google Maps data into a format that AI applications can understand, enabling agents to accurately answer real-world location and travel queries.

    Location ServicesTravel & TransportationSearch
    53
  • llmrefA
    org.llmref

    Versioned documentation registry and semantic search for AI tools and coding assistants.

    Documentation AccessSearchDeveloper Tools
    42
  • CustomGPT.ai
    ai.customgpt.mcp

    The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.

    RAG SystemsKnowledge & MemorySearch
    2

Related MCP Servers

  • MCP-RAG Server

    apatoliya
    F
    license
    C
    quality
    D
    maintenance
    A server that implements Retrieval-Augmented Generation using GroundX and OpenAI, enabling semantic search and document retrieval with Modern Context Processing for enhanced context handling.
    3
    -

  • ickyMCP

    dl1683
    A
    license
    Not graded
    quality
    D
    maintenance
    RAG-powered document search server that enables semantic search across large collections of legal and business documents (PDF, Word, Excel, PowerPoint) using local embeddings with no API costs.
    4
    MIT

  • Google AI Search MCP

    shariqriazz
    A
    license
    A
    quality
    B
    maintenance
    Provides AI-powered search and documentation tools using Google Vertex AI or Gemini API with real-time web search grounding, enabling technical queries, code analysis, documentation retrieval, and architecture recommendations to overcome LLM knowledge gaps.
    7
    58 npm
    6
    MIT

Appeared in Searches