Gemini Research MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Model for research_web | gemini-3.7-flash |
| GEMINI_API_KEY | Yes | Google AI Studio API key | |
| FETCH_PROXY_URL | No | Default HTTP(S) proxy for fetch_webpage | |
| DEEP_RESEARCH_AGENT | No | Default agent for research_deep | deep-research-preview-04-2026 |
| GEMINI_SUMMARY_MODEL | No | Model for session summaries, titles, and clarification | gemini-3.7-flash |
| GEMINI_RESEARCH_HTTP_HOST | No | Bind host for streamable-http. Non-loopback requires GEMINI_RESEARCH_HTTP_BEARER_TOKEN | 127.0.0.1 |
| GEMINI_RESEARCH_HTTP_PATH | No | URL path for streamable-http | /mcp |
| GEMINI_RESEARCH_HTTP_PORT | No | Bind port for streamable-http | 8000 |
| GEMINI_RESEARCH_TRANSPORT | No | stdio or streamable-http | stdio |
| GEMINI_RESEARCH_EXPORT_DIR | No | Disk-first destination when export_research_session has no output_path | ~/.gemini-research/exports/ |
| GEMINI_RESEARCH_STORAGE_URL | No | Redis URL to share sessions/exports across multiple server instances/workers; falls back to local DiskStore when unset | |
| GEMINI_RESEARCH_TTL_SECONDS | No | Override session/export TTL | |
| GEMINI_RESEARCH_STORAGE_PATH | No | Custom directory for the local DiskStore | |
| GEMINI_RESEARCH_HTTP_BEARER_TOKEN | No | Static bearer token required to call streamable-http. Never reuse GEMINI_API_KEY for this |
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| research_webA | Fast web research with Gemini grounding. Returns answer with citations in seconds. Uses a fixed high thinking level for higher-quality grounded answers. Use for: quick lookups, fact-checking, current events, documentation, "what is", "how to", real-time information, news, API references, error messages. |
| research_deepB | Run the default Deep Research agent with optional File Search and MCP tools. |
| resume_researchA | Resume an interrupted or in-progress Use when a Because Call with no arguments to list recoverable sessions. Call with an
|
| export_research_sessionA | Save (export, download, archive) a completed research session to a file
on disk — Word (.docx), Markdown (.md), or JSON. Use this to recover
your report after a Disk-first contract. The file is always written to disk, and the
absolute path is returned on the first line of the response as
Similar to Google's Deep Research export feature, the DOCX output is a professional Word document suitable for sharing, archiving, or further editing. Supported formats:
Typical recovery flow:
|
| search_toolsA | Search for tools using natural language. Returns matching tool definitions ranked by relevance, in the same format as list_tools. |
| call_toolA | Call a tool by name with the given arguments. Use this to execute tools discovered via search_tools. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_research_models | List available research models and their capabilities. Returns information about the models used by this server: - Quick research model (Gemini + Google Search grounding) - Deep Research Agent (autonomous multi-step research) |
| Available Exports | List all currently cached exports ready for download. |
TDQS
Scored across 6 tools
Each tool has a distinct purpose: quick research vs deep research, resuming interrupted sessions, exporting results, and searching/calling tools. The descriptions clearly differentiate them, though research_web and research_deep could cause minor confusion if not carefully read.
Tool names follow a mostly consistent verb_noun pattern in snake_case (research_web, research_deep, resume_research, export_research_session, search_tools, call_tool). The pattern is clear, though research_web and research_deep use qualifiers instead of straightforward nouns.
6 tools is well-scoped for a research server. It covers quick research, deep research, session recovery, export, and tool discovery/execution without being overwhelming or sparse.
The tool surface covers the main research workflow: quick and deep research, resuming interrupted sessions, exporting results, and meta-tools for discovering and calling tools. Minor gaps like lack of a dedicated cancel or list historical sessions tool, but the set feels complete for most use cases.