google-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_CX | Yes | Your Programmable Search Engine ID (CX). Obtained from the Programmable Search Engine control panel by creating a search engine that searches the entire web. | |
| GOOGLE_API_KEY | Yes | Your Google Custom Search API key. Obtained from Google Cloud Console by enabling the Custom Search API. |
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. For deep research with full page content, use google_research or deep_search instead. |
| deep_searchA | Performs a comprehensive web search by querying Google, 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. This is TRUE deep research - it actually READS the pages, not just snippets. |
| deep_search_newsA | Searches for recent news articles on a topic, fetches full article content, and returns consolidated results. Optimized for news and current events. |
| google_researchA | Perform extensive DEEP research on a topic using Anthropic's Multi-Agent Research Architecture. This tool implements the FULL multi-agent system:
Process Flow:
Depth Levels:
|
| fetch_pageA | Fetch and extract the full readable content from a single URL. Uses Readability-style extraction to get the main content, removing navigation, ads, etc. |
| research_sessionA | Create or manage a research session for multi-step research workflows. Actions:
|
| add_sourceC | Add a source to a research session after fetching its content. |
| web_searchA | Search the web with source quality scoring. For full page content, follow up with fetch_page or use deep_search. |
| get_citationsA | Get formatted citations from a research session. Supports markdown, numbered, and APA formats. |
| run_subagentA | Manually spawn and run a subagent for a specific research aspect. This allows fine-grained control over the multi-agent research process. The subagent will:
|
| evaluate_coverageB | Evaluate the current research coverage and identify gaps. This implements the "More research needed?" decision point from Anthropic's architecture. |
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 11 tools
Most tools are distinct, but google_search and web_search both provide simple search with subtle differences, and deep_search vs google_research overlap as deep research options. Descriptions help, but an agent might struggle to choose between them.
All names are snake_case, but the pattern mixes noun-first names (google_search, web_search, research_session, deep_search) with verb-first names (fetch_page, add_source, get_citations, run_subagent, evaluate_coverage). This is readable but not fully consistent.
With 11 tools covering search, full-content extraction, multi-agent research, session management, citations, and subagent coordination, the count is well-scoped for the server's purpose and each tool generally has a place.
The tool set covers the entire research workflow: simple search, deep search, news search, URL fetching, session lifecycle, source addition, citation generation, subagent execution, and coverage evaluation. No critical gaps are apparent.