Provides tools to analyze and summarize content from URLs using Google Gemini's URL Context capability, with optional grounding through Google Search for enhanced research capabilities.
URL-Context-MCP MCP Server
The URL-Context-MCP MCP Server provides a tool to analyze and summarize the content of URLs using Google Gemini's URL Context capability via the Gemini API.
Now also supports optional grounding with Google Search alongside URL Context. The server is designed to follow prompt-only orchestration: control whether to search or scrape via the instruction text you provide.
Installation
Prerequisites
- Node.js 18+
- Set
GOOGLE_API_KEY
in your environment
Get a Gemini API key
- Sign in to Google AI for Developers and create an API key
- Copy the generated key and set it as
GOOGLE_API_KEY
for this server- Cursor (project): add to
.cursor/mcp.json
underenv
- Claude CLI one-liner example: shown below
- Or set it in your shell before launching
- Cursor (project): add to
Published Package
This MCP server is now available as a published npm package: @taiyokimura/url-context-mcp
- No need to clone the repository locally
- Can be run directly via
npx @taiyokimura/url-context-mcp@latest
- See setup instructions below for Cursor and Claude Code
Build locally
Setup: Claude Code (CLI)
Use this one-line command (replace with your real API key):
To remove the server from Claude Code:
Setup: Cursor
Create .cursor/mcp.json
at your repository root:
Other Clients and Agents
Install in VS Code
Install in VS Code Insiders
Or add via CLI:
Follow the MCP install guide and use the standard config above:
- Guide: https://modelcontextprotocol.io/quickstart/user
Add MCP Server with:
- Command: npx
- Args: ["@taiyokimura/url-context-mcp@latest"]
- Env: GOOGLE_API_KEY=sk-your-real-key
Advanced settings → Extensions → Add custom extension:
- Type: STDIO
- Command: npx
- Args: @taiyokimura/url-context-mcp@latest
- Enabled: true
Example ~/.config/opencode/opencode.json
:
Open Qodo Gen (VSCode/IntelliJ) → Connect more tools → + Add new MCP → Paste the standard config JSON → Save.
Follow Windsurf MCP documentation and use the standard config above:
- Docs: https://docs.windsurf.com/windsurf/cascade/mcp
Configuration (Env)
- GOOGLE_API_KEY: Your Gemini API key
Available Tools
- analyze_urls
- inputs:
- urls: string | string[] (1-20 total)
- instruction?: string
- model?: string (default: gemini-2.5-flash)
- use_google_search?: boolean (default: false) — enable grounding with Google Search in addition to URL Context
- inputs:
Prompt recipes (prompt-only orchestration)
- Scraping-only (user provided URLs). Example instruction:
- "ユーザーが貼ったこれらのURLのみをURLコンテキストで解析し、要約・キーファクト・引用URLを日本語で提示。外部検索は禁止。取得失敗は明示。"
- Research with search + scraping, iterative up to 5 rounds. Example instruction:
- "以下のテーマを調査。まずGoogle検��で候補を収集し、引用する全URLは必ずURLコンテキストで取得・要約・統合。カバレッジ不十分なら最大5回まで再検索・再収集して補完。日本語で簡潔に要約・キーファクト・引用URLを提示。"
Example invocation (MCP tool call)
Scraping-only example
Research + scraping (iterative) example
Troubleshooting
- 401 auth errors: verify
GOOGLE_API_KEY
- Ensure Node 18+
- For npx usage:
npx @taiyokimura/url-context-mcp@latest
should work without local build - For local development: use absolute path to
build/index.js
References
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
The URL-Context-MCP MCP Server provides a tool to analyze and summarize the content of URLs using Google Gemini's URL Context capability via the Gemini API.
Now also supports optional grounding with Google Search alongside URL Context. The server is designed to follow prompt-only orchestration: con
Related MCP Servers
- AsecurityFlicenseAqualityAn MCP (Model Context Protocol) server that provides Google search capabilities and webpage content analysis tools. This server enables AI models to perform Google searches and analyze webpage content programmatically.Last updated -10138
- AsecurityAlicenseAqualityMCP (Model Context Protocol) server that utilizes the Google Gemini Vision API to interact with YouTube videos. It allows users to get descriptions, summaries, answers to questions, and extract key moments from YouTube videos.Last updated -476MIT License
- -securityAlicense-qualityA Model Context Protocol (MCP) server implementation for the Google Gemini language model. This server allows Claude Desktop users to access the powerful reasoning capabilities of Gemini-2.0-flash-thinking-exp-01-21 model.Last updated -1MIT License
- AsecurityAlicenseAqualityImplementation of Model Context Protocol (MCP) server that provides tools for accessing Google Cloud's Vertex AI Gemini models, supporting features like web search grounding and direct knowledge answering for coding assistance and general queries.Last updated -201185MIT License