Google Search MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_CX | Yes | Your Programmable Search Engine ID (CX) | |
| GOOGLE_API_KEY | Yes | Your Google Cloud API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| google_searchA | Simple Google search for quick lookups. Returns snippets only without fetching full page content. For deep research with full page content, use deep_search instead. |
| deep_searchA | Performs a comprehensive web search using Google Custom Search API, fetching the FULL content from top results using advanced content extraction (Readability algorithm), and returning consolidated content. Supports web, news, and image search types. Includes retry logic for reliability. |
| deep_search_newsA | Searches for recent news articles on a topic using Google Custom Search API, fetches full article content, and returns consolidated results. Optimized for news and current events. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The tools have overlapping purposes that could cause misselection. Both deep_search and deep_search_news perform similar comprehensive searches with full content extraction, differing mainly in search type (general vs. news), while google_search is a simpler alternative. An agent might struggle to choose between deep_search and deep_search_news for news-related queries, as their descriptions suggest functional overlap.
The tool names follow a consistent snake_case pattern throughout, with clear and descriptive verbs (deep_search, deep_search_news, google_search). The naming is predictable and readable, making it easy for an agent to understand the tool set's structure without confusion.
With only 3 tools, the server feels thin for a Google Search domain, which typically involves more varied operations like filtering, pagination, or specialized searches (e.g., by date or region). While the tools cover basic search needs, the count is borderline for comprehensive search functionality, potentially limiting agent capabilities.
There are significant gaps in the tool surface for a Google Search server. Missing operations include advanced filtering options, image or video search handling beyond basic mentions, pagination support, and error handling tools. The server focuses on content retrieval but lacks tools for refining or managing search results, which could lead to agent failures in complex tasks.