@jhzhu89/mcp-server-web-search
Enables web search via Azure OpenAI Responses API with the web_search_preview tool, returning results with citations.
README
@jhzhu89/mcp-server-web-search
MCP Server for web search via Azure OpenAI Responses API with web_search_preview tool.
Installation
Prerequisites
- Bun runtime installed
Claude Code (Recommended)
# Install globally (available in all projects)
claude mcp add web-search bunx @jhzhu89/mcp-server-web-search \
-s user \
-e AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com \
-e AZURE_OPENAI_DEPLOYMENT=gpt-5-mini
# Or install for current project only (default)
claude mcp add web-search bunx @jhzhu89/mcp-server-web-search \
-e AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com \
-e AZURE_OPENAI_DEPLOYMENT=gpt-5-mini
Manual Configuration
Add to your .mcp.json:
{
"mcpServers": {
"web-search": {
"type": "stdio",
"command": "bunx",
"args": ["@jhzhu89/mcp-server-web-search"],
"env": {
"AZURE_OPENAI_ENDPOINT": "https://your-resource.openai.azure.com",
"AZURE_OPENAI_DEPLOYMENT": "gpt-5-mini"
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
AZURE_OPENAI_ENDPOINT |
✓ | - | Azure OpenAI endpoint URL |
AZURE_OPENAI_DEPLOYMENT |
gpt-5-mini |
Deployment name | |
AZURE_OPENAI_API_VERSION |
2025-03-01-preview |
API version |
Authentication
This server uses DefaultAzureCredential for Azure authentication. Supported methods:
- Azure CLI (local development): Run
az loginbefore starting - Environment variables: Set
AZURE_CLIENT_ID,AZURE_TENANT_ID,AZURE_CLIENT_SECRET - Managed Identity: Works automatically in Azure environments
Tool: web_search
Search the web for real-time information with source citations.
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
query |
string | ✓ | Search query |
search_context_size |
"low" | "medium" | "high" |
Amount of context (default: "medium") |
|
user_location |
object | {type, city, country, region, timezone} for localized results |
Output (structuredContent)
{
"results": [
{
"query": "original search query",
"text": "Answer text with inline [citations](url)...",
"citations": [
{
"title": "Source Title",
"url": "https://example.com",
"start_index": 0,
"end_index": 100
}
]
}
]
}
Development
# Clone and install
bun install
# Run locally
export AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
az login
bun run start
# Run with HTTP transport
bun run start:http
# Test
bun test
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.