plaud-mcp-dcr-bridge
Deploys a Remote MCP server bridge for Plaud on Google Cloud Run, enabling Gemini Enterprise apps to connect via Dynamic Client Registration and OAuth 2.0 proxy.
README
Plaud MCP DCR Bridge for Gemini Enterprise
Package repository for deploying Plaud Remote Model Context Protocol (MCP) with Dynamic Client Registration (DCR) and OAuth 2.0 proxying on Google Cloud Run and connecting to Gemini Enterprise apps.
Target GCP Specifications
- GCP Project:
{YOUR_GCP_PROJECT_ID}(Configurable viaGCP_PROJECT_IDenv var) - Cloud Run Service:
plaud-mcp-dcr-bridge(Region:us-central1)
Prerequisites
- Google Cloud SDK (
gcloudCLI) installed and authenticated:gcloud auth login gcloud config set project <YOUR_PROJECT_ID> - Discovery Engine Service Agent granted Secret Accessor IAM permissions:
gcloud projects add-iam-policy-binding <YOUR_PROJECT_ID> \ --member="serviceAccount:service-<YOUR_PROJECT_NUMBER>@gcp-sa-discoveryengine.iam.gserviceaccount.com" \ --role="roles/secretmanager.secretAccessor"
Environment Setup (.env)
Copy .env.example to .env and fill in your GCP Project ID:
cp .env.example .env
.env configuration example:
# GCP Configuration
GCP_PROJECT_ID={YOUR_GCP_PROJECT_ID}
GCP_REGION=us-central1
SERVICE_NAME=plaud-mcp-dcr-bridge
# Plaud Remote Endpoints
BASE_URL=https://mcp.plaud.ai
API_URL=https://api.plaud.ai
Quick Deployment Command
chmod +x deploy.sh
./deploy.sh
or via gcloud:
gcloud builds submit --tag us-central1-docker.pkg.dev/{YOUR_GCP_PROJECT_ID}/cloud-run-source-deploy/plaud-mcp-dcr-bridge:latest
gcloud run deploy plaud-mcp-dcr-bridge \
--image us-central1-docker.pkg.dev/{YOUR_GCP_PROJECT_ID}/cloud-run-source-deploy/plaud-mcp-dcr-bridge:latest \
--region us-central1 \
--project {YOUR_GCP_PROJECT_ID} \
--allow-unauthenticated
Endpoints Provided
| Endpoint | Method | Description |
|---|---|---|
/.well-known/oauth-authorization-server |
GET | OAuth 2.0 Authorization Server Metadata |
/.well-known/mcp-configuration |
GET | Remote MCP Server discovery metadata |
/register |
POST | Dynamic Client Registration (DCR, RFC 7591) |
/authorize |
GET | OAuth 2.0 Authorization Proxy |
/token |
POST | OAuth 2.0 Token Proxy |
/mcp |
POST / GET | Streamable HTTP MCP Protocol Transport |
/health |
GET | Health Check Endpoint |
How to Get / Generate the Client ID
Option A: Via curl Command in Terminal (Instant)
Run this request to retrieve or generate a Client ID and Secret directly:
curl -X POST https://{YOUR_CLOUD_RUN_SERVICE_URL}/register \
-H "Content-Type: application/json" \
-d '{
"client_name": "Gemini Enterprise App",
"redirect_uris": ["https://cloudaicompanions.google.com/oauth/callback"]
}'
JSON Output Example:
{
"client_id": "eyJ2...",
"client_secret": "plaud-dcr-secret",
"client_name": "Gemini Enterprise App",
"grant_types": ["authorization_code", "refresh_token"],
"response_types": ["code"]
}
Copy the client_id string (eyJ2...) to use in Gemini Enterprise authentication settings.
Option B: Automatically via Gemini Enterprise DCR
When configuring the Extension in Gemini Enterprise, enter the Registration URL (https://{YOUR_CLOUD_RUN_SERVICE_URL}/register). Gemini Enterprise will automatically execute /register and populate the Client ID and Secret fields behind the scenes!
Connecting to Gemini Enterprise
- Open Google Cloud Console -> Gemini Enterprise (or Agent Space).
- Go to Connected data stores -> + New data store -> Add MCP server and enter these parameters:
| Setting Field | Value to Enter |
|---|---|
| MCP Server URL | https://{YOUR_CLOUD_RUN_SERVICE_URL}/mcp |
| Authorization URL | https://{YOUR_CLOUD_RUN_SERVICE_URL}/authorize |
| Token URL | https://{YOUR_CLOUD_RUN_SERVICE_URL}/token |
| Registration URL (DCR) | https://{YOUR_CLOUD_RUN_SERVICE_URL}/register |
| Client ID | eyJ2... (or auto-generated via DCR) |
| Client Secret | plaud-dcr-secret (or auto-generated via DCR) |
| Scopes | offline_access |
| Enable PKCE Support | CHECK / ENABLE ✅ |
| Use HTTP Basic Authentication | UNCHECK / DISABLE ❌ |
- After connecting to Connected data stores, click Actions and select Reload custom actions.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。