Gaia X

MCP搜索检索

提供方 YFGaia

搜索检索 未标注 无需鉴权 社区 / 第三方 ClaudeVS Code

Gaia-X 基于AI新范式的下一代企业级AI应用平台。Gaia-X旨在实现类人脑的、针对企业办公业务场景的AI化赋能,包括一系列新颖而稳定的企业级AI功能,包括不限于:企业级管理功能、MCP Server支持(且支持将企业内部系统API转换为MCP Server提供服务)、支持自然语言驱动的RPA(大模型操作电脑)、划词分析和悬浮球等。

一句话选型结论

按资料字段整理

Gaia X 属于搜索检索类 MCP 服务器,传输方式未标注,无需鉴权,可直接接入 Claude、VS Code,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类搜索检索 传输方式未标注 鉴权无需鉴权 部署方式未标注
GitHub 星标 27 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

搜索检索
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

research-and-datagaia-xenterprise-aiai-platform企业AITypeScript本地部署多代理协作

安装与配置

未标注 无需鉴权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
联网搜索取证

让模型查最新资料并给出出处。

资料聚合

把一个主题的网页、文档集中抓回来整理。

情报与竞品检索

按关键词持续检索行业动态和竞品信息。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Claude、VS Code,换客户端不用重新研究配置。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在搜索检索场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、VS Code 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Gaia X当前 未标注 未标注 未标注 无 2026-05-18
Brave Search 433812ff 2 未标注 未标注 无 2026-05-17
Sequentialthinking 1 SSE · 服务端推送 远程部署 有 2026-05-18
Baidu Netdisk 未标注 未标注 未标注 无 2026-05-17
ragflow 未标注 stdio · 本地进程 本地部署 有 2026-04-11
mindsdb (430e18) 未标注 未标注 未标注 有 2026-05-17

服务器档案

搜索检索
字段来自项目仓库与公开索引,中文说明由本站标注
提供方YFGaia上游标注的维护方 YFGaia
分类搜索检索本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-18上游最后核验时间

详细介绍

8.3 KB
来自项目仓库与上游目录的原文,未做删改

Gaia-X Next-Generation Enterprise AI Application Platform Based on AI New Paradigm

🌟 Project Overview

Gaia-X is the first chatbot application platform designed for enterprise scenarios based on the new AI paradigm, addressing the core pain points of existing AI products with innovative technical architecture:

🚀 Enterprise Management · 🤖 MCP Protocol Support · 👥 Multi-Agent Collaboration
💻 Natural Language RPA · ✅ Human Confirmation Mechanism · 🎨 Intelligent Canvas Rendering

Try Now · Admin Center · Documentation Center

🎯 Core Pain Point Solutions

Pain Point Area Gaia-X Innovative Solutions
Lack of Enterprise Management Complete user/permission/billing system and LLM API hosting
No MCP Protocol Support The first enterprise-grade MCP support
Risk of Sensitive Operations ReAct tool calls with human confirmation, dynamic rendering
Difficulty in Natural Language RPA Large model-driven RPA automation
Weak Multi-Agent Collaboration Intelligent Agent retrieval and multi-agent collaboration for complex tasks

📦 Project Architecture

1.1 Overall Project Architecture

1.2 MCP Call Process

During the Agent call process, the management center is not responsible for calling MCP tools. Instead, after the client's node program receives the response results, it will uniformly determine if there are function calls. If so, it will call the corresponding MCP tools to execute. The execution chain is roughly as follows:```mermaid
graph LR
U --> |1|C[Gaia-X Client]
C-->|2|API[Admin Center]
API-->|3|LLM[LLM API]
LLM-->|4|API[Admin Center]
API-->|5|C[Gaia-X Client]
C-->|6|B{Function Call?}
B -- No -->U[User]
B -- Yes --> MCP[MCP Servers]
MCP -->|8a. Call| H[Tool 1]
MCP -->|8b. Call| I[Tool 2]
H-->|8.1|C[Gaia-X Client]
I-->|8.1|C[Gaia-X Client]
C-->|8.2|API[Admin Center]
API-->|8.3|LLM[LLM API]
LLM-->|8.4|API[Admin Center]
API-->|8.5|C[Gaia-X Client]
C-->|8.6|U[User]

subgraph Possible Nested/Iterative Calls
H
I
end


### 1.3 Client Authentication Logic at Startup

As this is an enterprise-level project, the client needs to complete login authentication before entering the Chatbot interface. Using OAuth2.0 as an example (other logic is similar), the authentication process is as follows:```mermaid
sequenceDiagram
participant C as Client Program
participant A as Admin Center
participant O as OAuth2.0 Server
participant U as User

C->>A: Request authentication page (non-OAuth2.0 login page)
A->>A: Check current login status
alt Not logged in
A->>O: Redirect and open OAuth2.0 login page
O->>U: Display login interface
U->>O: Submit credentials for login
O->>A: Return authentication result (e.g., Token)
A->>A: Generate JWT after verifying Token and update login status
else Already logged in
A->>U: Display authorization button
end
U->>A: Click authorize
A->>C: Redirect back to client and pass authorization information (gaia://oauth-callback?code=xyz)
C->>C: Client completes login process

Process Explanation:

  1. Client requests authentication page from admin center;
  2. Admin backend determines user login status;
  3. If not logged in, redirects to OAuth2.0 login page;
  4. User submits credentials on OAuth2.0 login page, returns authentication result after successful login;
  5. After OAuth2.0 login, redirects to admin backend with authentication information, generates JWT and updates login status;
  6. User clicks authorize button, admin backend redirects back to client, completing the login.

2. Core Features (Some still under development)

2.1 MCP (Model Context Protocol) Support

  • [x] Support for integrating any community MCP Servers.
  • [ ] Unified management of all MCP Servers through the enterprise management center.
  • [x] All MCP Servers run in isolated sandbox environments on the client, ensuring operational security and data isolation.
  • [ ] Independent MCP Server display page (similar to the official MCP Inspector effect)

2.2 Multi-Agent Intelligent Coordination

  • [ ] Support for intelligent collaboration based on task orchestration or RAG, automatically completing complex tasks without manual selection of Agents or Workflows.
  • [ ] Built-in key agents for computer operations, Python programming, web browsing, etc.

2.3 New Paradigm Infinite Canvas

  • [ ] Each Agent process in Multi-Agent conversations is an independent canvas, automatically generating summaries as permanent memory.
  • [x] Support for common Artifacts, including but not limited to:
  • SVG, HTML
  • Mermaid, Echarts, PlantUML
  • [x] Support for MCP tools to dynamically render forms, allowing users to interactively modify and control submissions.
  • [ ] Support for Python, TypeScript, HTML and other code execution

2.4 Intelligent Computer Operations

  • [X] Integration with Claude Sonnet 3.5+, Zhipu CogAgent, ByteDance UI-TARS, OpenAI computer-use and other models.
  • [X] Agents can autonomously execute any computer operation.

2.5 Text Selection Analysis

2.6 Enterprise Management Center

  • [x] Unified Authentication and User Management: OAuth 2.0, LDAP, DingTalk, Feishu and other authentication methods.
  • [x] Unified Model and Tool Management: Centralized configuration and authorization management in the backend.
  • [ ] Quota Management: Fine-grained control of user quotas and API quotas.
  • [ ] Enterprise Internal Application Ecosystem: MCP marketplace, Agent marketplace, application task marketplace (for specific complex tasks), etc.
  • [ ] Business Reports: Comprehensive user, model, and Agent usage data analysis reports.

2.7 Third-party Agent Integration

  • [x] Native support for integrating third-party Agent platforms such as Dify and Coze, with unified authorization management.

3. Technology Stack

3.1 Client

The client adopts a plugin-based design, and will later be architected with a micro-kernel plugin architecture similar to VS Code, enabling arbitrary extensions.

  • Framework: Electron + React
  • LLM UI: Ant Design X
  • Text Selection Monitoring Technology: C++ (Windows), Objective-C (MacOS)

3.2 Admin Backend

The client only serves as an interactive UI and MCP management execution, without actual model calls. Model calls and tool calls are implemented by the backend. However, the backend is not responsible for the specific execution of MCP tools.

  • Large Model Interaction: Eino Framework + Self-developed Multi-Agent
  • Admin UI: Ant Design Pro (refactoring the frontend page code of GVA for technology stack uniformity)
  • API Service: golang + Gin (based on the GVA framework)

3.3 MCP Server

  • Runs in independent sandbox environment
  • Supports implementation in both Python and TypeScript

4. Model Selection Reference

  • Computer Operation Models: Claude Sonnet 3.5+, CogAgent, UI-TARS, OpenAI computer-use
  • ReAct Recommended Models: Claude Sonnet 3.5+, GPT 4o (DeepSeek v3 model performs poorly, not recommended for critical tasks)

5. Acknowledgements

  • The admin API is built based on Gin-Vue-Admin, reducing much of our basic management backend development work.

  • Eino by ByteDance is one of the few golang-based large model application development frameworks, solving basic model integration and Agent issues.

  • We used Ant Design Pro to refactor the frontend pages of Gin-Vue-Admin, unifying the UI frameworks for both the admin backend and client, reducing community development difficulty.

  • We've made many secondary developments based on Eino, including integration of common model providers and Multi-Agent architecture. After secondary development, we published it as Eino-X.

  • To solve the problem of running MCP Servers on ordinary user clients, we packaged an embedded binary MCP runtime environment (supporting MacOS and Windows) under the project mcp-runtime.


6. License

This project is licensed under the Apache 2.0 License. Feel free to customize or contribute!


7. Community Support

We welcome feedback and suggestions through Issues. We look forward to your participation in building the future enterprise AI application ecosystem together.

🎉 Thank you for your attention and support to the project!

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
Gaia X 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Gaia X 怎么在 Claude、VS Code 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Gaia X 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Gaia X 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Gaia X 支持哪些客户端?

资料标注支持 Claude、VS Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Gaia X 能提供哪些能力?

资料显示能力标签包括 多代理协作、TypeScript、Claude。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-18。