Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Gemini Google Search
This package turns Gemini’s Google Search grounding into an MCP tool. Builders can connect it to Claude Code or any MCP client and ask for web searches with source citations.
Builders who want their agent to look up current information from Google Search during a session.
You can ask your agent to search the web and get cited answers without leaving the terminal.
What it does
Google Search tool
Provides a `google_search` MCP tool that takes a query string and returns search results.
Grounded results with citations
Uses Gemini’s Grounding with Google Search feature so responses include source citations.
MCP stdio transport
Runs as an MCP server over stdio, which fits terminal-based agent clients.
Google AI Studio and Vertex AI support
Works with either a Gemini API key or a Vertex AI project setup.
How to get it
- 1Run
npm install -g mcp-gemini-google-search
- 2On Windows, wrap the npx command with cmd /c
claude mcp add gemini-google-search \ -e GEMINI_API_KEY="your-api-key-here" \ -- cmd /c npx mcp-gemini-google-search
- 3Example
latest TypeScript features
README
MCP Gemini Google Search
A Model Context Protocol (MCP) server that provides Google Search functionality using Gemini's built-in Grounding with Google Search feature.
This project is inspired by the GoogleSearch tool from gemini-cli.
Features
- Uses Gemini's built-in Grounding with Google Search feature
- Provides real-time web search results with source citations
- Compliant with MCP standard protocol
- Supports stdio transport
- Supports both Google AI Studio and Vertex AI
Requirements
- Node.js 18 or later
- Google AI Studio API key (Get one here) or Google Cloud Project with Vertex AI enabled
Installation
npm install -g mcp-gemini-google-search
Usage
Environment Variables
# For Google AI Studio (default)
export GEMINI_API_KEY="your-api-key-here"
export GEMINI_MODEL="gemini-2.5-flash" # Optional (default: gemini-2.5-flash)
# For Vertex AI
export GEMINI_PROVIDER="vertex"
export VERTEX_PROJECT_ID="your-gcp-project-id"
export VERTEX_LOCATION="us-central1" # Optional (default: us-central1)
export GEMINI_MODEL="gemini-2.5-flash" # Optional (default: gemini-2.5-flash)
Claude Code Configuration
You can set up this MCP server in Claude Code using the CLI:
For Google AI Studio
# Add to user scope (available across all projects)
claude mcp add gemini-google-search \
-s user \
-e GEMINI_API_KEY="your-api-key-here" \
-e GEMINI_MODEL="gemini-2.5-flash" \
-- npx mcp-gemini-google-search
# Or add to project scope to share with your team
claude mcp add gemini-google-search \
-s project \
-e GEMINI_API_KEY="your-api-key-here" \
-e GEMINI_MODEL="gemini-2.5-flash" \
-- npx mcp-gemini-google-search
For Vertex AI
# Add to user scope (available across all projects)
claude mcp add gemini-google-search \
-s user \
-e GEMINI_PROVIDER="vertex" \
-e VERTEX_PROJECT_ID="your-gcp-project-id" \
-e VERTEX_LOCATION="us-central1" \
-e GEMINI_MODEL="gemini-2.5-flash" \
-- npx mcp-gemini-google-search
# Or add to project scope to share with your team
claude mcp add gemini-google-search \
-s project \
-e GEMINI_PROVIDER="vertex" \
-e VERTEX_PROJECT_ID="your-gcp-project-id" \
-e VERTEX_LOCATION="us-central1" \
-e GEMINI_MODEL="gemini-2.5-flash" \
-- npx mcp-gemini-google-search
Windows Users
On Windows, wrap the npx command with cmd /c:
claude mcp add gemini-google-search \
-e GEMINI_API_KEY="your-api-key-here" \
-- cmd /c npx mcp-gemini-google-search
Available Tools
google_search
Search Google for information.
Parameters:
query(string, required): Search query
Example:
latest TypeScript features
Example Response
It appears you're asking about the latest features in TypeScript. Here's a summary of recent updates and key features, based on the provided search results:
**Key Features in Recent TypeScript Updates:**
* **Satisfies Operator:** This operator lets you specify that a value conforms to a specific type without fully enforcing it.[1,2]
* **Const Type Parameters:** Using `const` with type parameters provides more precision with function generics, helping specify literal types and prevent unwanted transformations.[2] This ensures arrays are treated as immutable, maintaining their literal types.[2]
* **Improved Enum Types:** Enums are more robust, especially `const enum`, which optimizes enums by inlining their values at compile time.[2] From version 5.0, all enums are treated as a type union, even with calculated values.[1]
* **Template Literal Types:** Template literal types are more expressive, allowing you to create types that build on literals, similar to JavaScript template strings.[2]
* **Unions and Intersections with Discriminated Unions:** TypeScript offers better handling for union and intersection types, which are frequently used to build flexible types.[2] Discriminated unions allow you to create complex structures with ease and clear type guards.[2]
* **New ECMAScript Set Methods:** Support for new methods like `union`, `intersection`, and `difference` for more powerful set operations.[3]
**TypeScript 5.8 Highlights (March 2025):**
* **Module Node18 Flag:** Provides a stable reference point for users fixed on Node.js 18, without incorporating certain behaviors of `--module nodenext`.[4]
* **Optimizations:** Introduces optimizations that improve the time to build up a program and update it based on file changes, especially in `--watch` mode or editor scenarios.[4] This includes avoiding array allocations during path normalization.[4]
* **Import Assertions:** `--module nodenext` in TypeScript 5.8 will issue an error if it encounters an import assertion, as Node.js 22 no longer accepts them using the `assert` syntax, recommending `with` instead.[4]
**Other Notable Features & Improvements:**
* **Inferred Type Predicates:** Improved type inference, especially with arrays and filtering.[3]
* **Control Flow Narrowing for Constant Indexed Accesses:** Better type narrowing for accessing object properties.[3]
* **Regular Expression Syntax Checking:** Basic syntax checks are performed on regular expressions, flagging errors like unclosed parentheses.[3]
* **Array filter Fixes:** Properly filters the type of arrays when you use the filter function.
* **Object Key Inference Fixes:** Improves type inference.
**Performance Enhancements:**
* **Go Rewrite:** A full rewrite of TypeScript in Go has been promised for version 7.0, which has demonstrated significant speed improvements (up to 10x-15x in some cases).[5] This will affect the compiler (`tsc`) and IDE performance (loading, hovers, errors, etc.).[5] The team chose Go for its structural similarity to the current JavaScript implementation.[5]
* **TypeScript 5.0:** This update aimed to accelerate coding processes and simplify development by refining code, data structures, and streamlining import/export operations.[6]
In summary, TypeScript is continuously evolving with new features and improvements aimed at enhancing developer productivity, code quality, and performance.[6]
Sources:
[1] edicomgroup.com (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFILdgh_4-Yh0OuwzDOqwCfvLGHdhm_PGhdAIzMK_DFwW38X9qK8b3Tj_ws2VZ2VLxWW_NJtuzot8B_wYYH4rOHBY_1HYZ7PyCHOCR3GzQpwQUi71ufAf6izU13O3W6GzjQAQnVjnheeRLLLf4mD7uueIS-g0yeivFo2XWZKJF4wtRtDfdTYjtHvRYmB7rY6Q==)
[2] dev.to (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFFMJOcmJDu8TUJsc6cKjVMDTR7ggjQMUc1aMAIVKRhbTq7Zjzh5f_h-UpZn6LE6xB-nTqUmQwHCiUmhvAZ_uYmzXIzNmJvtoDUjDcB9hJDw_aPPvJjd411APwVfiNvd3yhlrB7MFsnxH25-hxNetmoZJrriZ0mGm6ZaYbm0yMeiruDqC5mnqXJwuyGLMdrg-M3LpRAGrxVAT9b1veE)
[3] dev.to (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFfDcb-2QNwLZ0TpjSkNCWCvh-dvslYtllEMyyTXCSu-3jbOBD4vvq0j5Hqyuw8BcmEpKjBBeBZS83E-GCKax48hg5Oc1Fam6GQy296DxQkEQOfg7pvmnRhE3tdDbDCBqXKdYPonoR_AVLBAlGdKg==)
[4] microsoft.com (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEWKA9uZsB7lcOGcnOLveyjImsqVwNItCj3n3QiCrCkyL6iY4rA16Wp37FecAoKgX58lcDcBOuXye97fgw5SAbLwDkl3M-vCUK0I0HxtCx8qMaBVM42sxyFEQjn1iz4Qgzud3P7pDlc4frHf6Wkgs8nNcoIlMriePVOb0l9vmY=)
[5] totaltypescript.com (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFysE6zFlg_XiXfGqAiDapTIj2bsVWlkuq3Trpfacjd1a7gMDrUh35MKW-No9qdSKti68W3M2b1j6VqlnZ7v_yBOjE8hK_3d57U7UePyjMOUDdbBBGRK8CZeUug3hBOFsZjbnQoDdoL446oZL1R38gJrc9JvGmlWQno)
[6] rabitsolutions.com (https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEY1brKmgxI5YOA1HrB89SnHNPyhm3Dlz-zumJMoi-wBegLSOjto360JJrA29TwVB8A02qHWZBtwua0QHn8NxAjWUCCkLxD7lZa_xW4Mtp8diiAXl1ppIWEHq6T7B1Mm6_dMs3lWoOKOJSjCUrk6-P4ao40V-nYULfPtA==)
Development
To contribute to this project:
# Clone the repository
git clone https://github.com/yukukotani/mcp-gemini-google-search.git
cd mcp-gemini-google-search
# Install dependencies
npm install
# Development mode (watch for file changes)
npm run dev
# Build
npm run build
# Run locally
npm run start
# Debug with MCP Inspector
npm run inspect
Debugging with MCP Inspector
Running npm run inspect will open the MCP Inspector in your browser. This allows you to:
- View available tools
- Execute tools and see responses
- Debug in real-time
License
Apache License 2.0
Files in the repo
- examples
- src
- .gitignore
- CLAUDE.md
- LICENSE
- package-lock.json
- package.json
- README_ja.md
- README.md
- tsconfig.json
- tsup.config.ts
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.