Gemini DeepSearch MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Gemini API key | |
| LANGSMITH_API_KEY | No | Your LangSmith API key for tracing | |
| LANGSMITH_TRACING | No | Enable LangSmith tracing | true |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| deep_searchC | Perform a deep search on a given query using an advanced web research agent. Args: query: The research question or topic to investigate. effort: The amount of effect for the research, low, medium or hight (default: low). Returns: A dictionary containing the file path to a JSON file with the answer and sources. |
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 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'deep_search' has a clear, distinct purpose focused on performing deep web research.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'deep_search' follows a clear verb_noun pattern and is descriptive of its function.
A single tool is generally too few for most server purposes, as it limits functionality and flexibility. While it might suffice for a very narrow scope, it feels thin and incomplete for a server named 'Gemini DeepSearch MCP', which suggests broader research capabilities.
The server is severely incomplete for a deep search/research domain. There are no tools for refining searches, managing search history, filtering results, or handling different types of queries. The single tool provides a basic search function but lacks the comprehensive coverage expected for a research-oriented server.