google-dev-knowledge-mcp-bridge
A local stdio MCP bridge that forwards tool calls to the Google Developer Knowledge MCP endpoint and enhances search_documents with caching, result expansion, and concise markdown excerpts.
README
google-dev-knowledge-mcp-bridge
Local stdio MCP bridge for the Google Developer Knowledge MCP endpoint. It forwards upstream tool calls and adds a higher-signal search_documents mode that:
- caches semantically equivalent search requests
- expands top search hits with
batch_get_documents - extracts concise markdown sections for easier downstream citation and synthesis
The bridge does not embed credentials in tracked code. Authentication is resolved from Application Default Credentials plus service account impersonation configured through environment variables.
Requirements
- Node.js 18+
gcloudinstalled and authenticated withgcloud auth application-default login- Permission to impersonate the target service account
Installation
-
Install dependencies:
npm install -
Copy the sample environment file:
cp .env.example .env -
Fill in only the values required for your environment.
Environment Variables
Required
GOOGLE_IMPERSONATE_SERVICE_ACCOUNT
Optional
GOOGLE_QUOTA_PROJECT_IDDEBUG_MCP=falseAUTO_EXPAND_SEARCH=trueEXPAND_TOP_N=4EXPAND_MAX_CHARS=9000EXPAND_PER_DOC_MAX_CHARS=2600CACHE_TTL_MS=300000REQUEST_TIMEOUT_MS=20000MAX_RETRIES=2BACKOFF_BASE_MS=400
Authentication Flow
The bridge uses this sequence:
- Loads Application Default Credentials from the local environment.
- Impersonates the service account named in
GOOGLE_IMPERSONATE_SERVICE_ACCOUNT. - Calls the Google Developer Knowledge MCP endpoint with an OAuth access token.
If GOOGLE_QUOTA_PROJECT_ID is set, the bridge also sends it as the quota project header.
MCP Server Launch
Run the bridge directly over stdio:
npm start
Equivalent direct command:
node server.js
Example Codex MCP launch configuration:
{
"mcpServers": {
"google-dev-knowledge-mcp-bridge": {
"command": "node",
"args": ["/absolute/path/to/google-dev-knowledge/server.js"],
"cwd": "/absolute/path/to/google-dev-knowledge",
"env": {
"GOOGLE_IMPERSONATE_SERVICE_ACCOUNT": "service-account@your-project.iam.gserviceaccount.com",
"GOOGLE_QUOTA_PROJECT_ID": "your-project-id",
"AUTO_EXPAND_SEARCH": "true",
"DEBUG_MCP": "false"
}
}
}
}
Repository Layout
server.js: CLI entrypointsrc/config.js: environment parsing and validationsrc/google-client.js: ADC + impersonation + HTTP retry logicsrc/content-pack.js: search expansion and excerpt construction helperssrc/bridge.js: stdio JSON-RPC loop and caching
Upstream MCP Tools
The bridge forwards upstream Google Developer Knowledge MCP tool calls. Common tools include:
search_documentsget_documentbatch_get_documents
When AUTO_EXPAND_SEARCH=true, search_documents responses are transformed into a context pack that includes:
- canonical source links
- top ranked search chunks
- extracted document excerpts sized for model context windows
All other tool calls are passed through unchanged.
Sample MCP Tool Calls
Example search_documents input:
{
"query": "Cloud Storage create bucket required permissions"
}
Example get_document input:
{
"name": "documents/cloud-storage-create-buckets"
}
Example batch_get_documents input:
{
"names": [
"documents/cloud-storage-create-buckets",
"documents/iam-roles-overview"
]
}
Smoke Tests
Syntax check the bridge:
npm run check
Troubleshooting
Missing required environment
- The process exits immediately if
GOOGLE_IMPERSONATE_SERVICE_ACCOUNTis unset.
Failed authentication
- Re-run
gcloud auth application-default login. - Confirm the authenticated principal can impersonate the configured service account.
- If you use quota billing, confirm
GOOGLE_QUOTA_PROJECT_IDis valid for the caller.
Request failures or timeouts
- Increase
REQUEST_TIMEOUT_MSin slower environments. - Leave
MAX_RETRIESabove0if you want automatic retry on429and5xxresponses.
Publishing hygiene
.envandnode_modules/are ignored by.gitignore.- Use
.env.exampleas the only tracked environment template.
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。