MCP Gemini Web Search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL | No | Default model to use (optional) | gemini-3-flash-preview |
| MAX_RETRIES | No | Max retry attempts (optional) | 5 |
| JITTER_FACTOR | No | Jitter factor 0-1 for retries (optional) | 0.1 |
| GEMINI_API_KEY | No | Google AI API key (required if GOOGLE_API_KEY not provided) | |
| GENAI_BASE_URL | No | Custom API endpoint base URL (optional) | |
| GOOGLE_API_KEY | No | Google AI API key (required if GEMINI_API_KEY not provided) | |
| RATE_LIMIT_RPM | No | Requests per minute limit (optional) | 60 |
| GEMINI_BASE_URL | No | Custom API endpoint base URL (optional) | |
| MAX_RETRY_DELAY | No | Max delay in ms for retries (optional) | 60000 |
| REQUEST_TIMEOUT | No | Default request timeout in ms (optional) | 60000 |
| BASE_RETRY_DELAY | No | Base delay in ms for retries (optional) | 1000 |
| RATE_LIMIT_MAX_BURST | No | Max burst capacity (optional) | 10 |
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 |
|---|---|
| web_searchA | Grounded search with citations. mode='normal' for a single pass; mode='research' for a multi-step, deeper approach. Use verbosity to control output length. |
| web_search_batchA | Run multiple web search queries in parallel. All queries are executed concurrently for faster results. Returns results for each query with individual success/failure status. |
| health_checkA | Returns health status and metrics including request counts, rate limit status, and error information. |
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
health_check is clearly distinct from the two search tools, monitoring server status rather than performing searches. web_search and web_search_batch are differentiated by single vs. parallel execution, and the descriptions make their use cases unambiguous.
The search tools follow a consistent web_search / web_search_batch pattern, which makes their relationship obvious. health_check is a minor deviation in structure (noun_verb vs. web_search prefix) but still follows a readable naming style.
Three tools cover health monitoring and two search modes, which is well-scoped for a web search server. Every tool serves a distinct, justified purpose without redundancy or unnecessary bloat.
The core domain of web search is fully covered with both single and batch search capabilities, plus operational health metrics. No obvious missing operations like result refinement or search customization are implied by the descriptions.