Gemini Research MCP Server

MCP server for AI-powered research using Gemini. Fast grounded search, URL extraction, comprehensive Deep Research, and session management.

FastMCP 3.1 now exposes a compact BM25 tool-search surface by default. Clients see research_web, research_deep, search_tools, and call_tool; utility tools such as URL reading, follow-up, resume, sessions, templates, and export are discovered on demand.

Architecture

<details> <summary>Mermaid source</summary>

flowchart TB
    subgraph Client["MCP Client"]
        Claude["Claude / Copilot"]
    end

    subgraph Server["gemini-research-mcp"]
        direction TB
        FastMCP["FastMCP 3 Server<br/>@mcp.tool()"]
        
        subgraph Tools["Tools"]
            RW["research_web<br/>Quick lookup 5-30s"]
            RD["research_deep<br/>Autonomous 3-20min"]
            RF["research_followup<br/>Continue session"]
            RR["resume_research<br/>Recover interrupted"]
            FW["fetch_webpage<br/>Content extraction"]
            EX["export_research_session<br/>MD/JSON/DOCX"]
            LS["list_research_sessions"]
            LT["list_format_templates"]
        end

        subgraph Modules["Core Modules"]
            Quick["quick.py<br/>Web grounding"]
            Deep["deep.py<br/>Deep research agent"]
            Content["content.py<br/>SSRF protection"]
          StorageMod["storage.py<br/>Session manager"]
            Templates["templates.py<br/>Format templates"]
        end
    end

    subgraph External["External Services"]
        Gemini["Google Gemini API"]
        Web["Web Sources<br/>via trafilatura"]
    end

    subgraph Storage["Persistence"]
        SQLite["SQLite<br/>~/.gemini-research/"]
    end

    Claude -->|"MCP Protocol"| FastMCP
    FastMCP --> Tools
    
    RW --> Quick
    RD --> Deep
    RF --> StorageMod
    RR --> StorageMod
    FW --> Content
    LT --> Templates
    
    Quick -->|"grounding"| Gemini
    Deep -->|"agentic"| Gemini
    Content -->|"httpx"| Web
    StorageMod --> SQLite

</details>

Tools

Client-Visible Tools

Tool	Description	Latency
research_web	Fast web search with citations	5-30 sec
research_deep	Multi-step autonomous research (requires MCP Tasks)	3-20 min
resume_research	Resume or check an interrupted research_deep session	instant
export_research_session	Export a session to Markdown, JSON, or DOCX (disk-first)	instant
search_tools	BM25 search across the server's utility tools	instant
call_tool	Invoke a utility tool discovered through search_tools	instant

Utility Tools Available via search_tools

Tool	Description	Latency
fetch_webpage	Extract article content from a specific URL (SSRF-protected, chunkable)	0.5-2 sec
research_followup	Continue conversation after research	5-30 sec
list_research_sessions	List saved research sessions	instant
list_format_templates	Browse report format templates	instant

Discovered utility tools remain directly callable for clients that already know the tool name.

fetch_webpage Parameters

fetch_webpage is discoverable through search_tools in the default server listing.

The fetch_webpage tool supports chunked reading for large pages and optional proxy routing:

Parameter	Type	Default	Description
url	string	required	HTTP/HTTPS URL to fetch
max_length	integer | null	null	Maximum characters to return (chunk size)
start_index	integer	0	Character offset for pagination
proxy_url	string | null	null	Optional HTTP(S) proxy URL for the request

Notes:

• SSRF protection is always applied (private/internal hosts are blocked).
• robots.txt is checked before fetch when protego is installed.
• When output is truncated, the response includes a continuation hint with next start_index.
• If proxy_url is omitted, the server falls back to FETCH_PROXY_URL when set.
• proxy_url must be a public HTTP(S) host (private/internal proxy hosts are blocked).

Install the web extra for the highest-quality fetch_webpage experience:

pip install 'gemini-research-mcp[web]'
# or
uv add 'gemini-research-mcp[web]'

Without [web], fetch_webpage still works using the built-in HTML fallback, but trafilatura extraction and protego-based robots.txt checks are unavailable.

Power User Workflow

Key insight: Gemini Deep Research runs asynchronously on Google's servers. Even if VS Code disconnects, your research continues. The resume_research tool retrieves completed work.

Features

• Auto-Clarification: research_deep asks clarifying questions for vague queries via MCP Elicitation
• MCP Tasks: Real-time progress with streaming updates
• Session Persistence: Research sessions are automatically saved and can be resumed later
• Export Formats: Export to Markdown, JSON, or professional DOCX with Table of Contents
• File Search: Search your own data alongside web using file_search_store_names
• Remote MCP sources: Deep Research can call remote MCP servers using mcp_servers
• Format Instructions: Control report structure (sections, tables, tone)

Installation

PyPI (recommended)

pip install gemini-research-mcp
# or
uv add gemini-research-mcp

Claude Desktop (MCPB Bundle)

Download the .mcpb bundle from GitHub Releases and open it in Claude Desktop for single-click installation.

The bundle uses UV runtime - dependencies are installed automatically, no Python required.

Configuration

Variable	Required	Default	Description
GEMINI_API_KEY	Yes	—	Google AI Studio API key
GEMINI_MODEL	No	gemini-3.1-pro-preview	Model for research_web
GEMINI_SUMMARY_MODEL	No	gemini-3-flash-preview	Model for session summaries (fast)
DEEP_RESEARCH_AGENT	No	deep-research-pro-preview-12-2025	Agent for research_deep
FETCH_PROXY_URL	No	—	Default HTTP(S) proxy for fetch_webpage

cp .env.example .env
# Edit .env with your API key

Deep Research vs Deep Research Max

Google exposes Deep Research variants through the Gemini Interactions API agent field, not the regular Gemini model field:

• research_deep uses deep-research-preview-04-2026 by default. Use it for interactive research, comparisons, investigations, and latency/cost-sensitive synthesis.
• research_deep_max uses deep-research-max-preview-04-2026. Use it when the user explicitly asks for Max, exhaustive/comprehensive due diligence, market maps, literature reviews, board-ready reports, offline/nightly research, or maximum completeness over speed.

For Copilot and other LLM clients, the two tools are intentionally separate so Max can be selected from the tool name and description. There is no public model parameter for Deep Research, because follow-up and quick research use Gemini models while Deep Research uses Interactions agents.

Remote MCP servers for Deep Research

Google Deep Research supports remote MCP servers through the Interactions API. Pass mcp_servers to research_deep or research_deep_max when the agent needs a specialized/private data source.

{
  "query": "Use the Market Researcher MCP evidence ledger to analyze the approved market gate.",
  "mcp_servers": [
    {
      "name": "Market Researcher MCP",
      "url": "https://example.com/mcp",
      "headers": {
        "Authorization": "Bearer ${TOKEN}"
      },
      "allowed_tools": [
        "market_get_mission",
        "market_get_runtime_policy",
        "market_get_task_status",
        "market_generate_report"
      ]
    }
  ]
}

Use allowed_tools aggressively. For evidence-led workflows, expose read-only ledger/report/status tools to Deep Research and import the resulting report back through your own audit/quarantine path. The MCP server tool accepts the user-friendly string list shown above and normalizes it to the Gemini Interactions API allowed_tools object shape before sending the request.

If Gemini returns a generic 400 invalid_request before the research task starts, use inspect_mcp_server_for_gemini first. It lists the remote MCP server tools and flags common compatibility problems such as missing tool descriptions, empty input schemas, unsupported JSON Schema keywords, or allowed_tools names that do not exist on the server. Public quick-tunnel hosts may still be rejected before Gemini contacts the server; prefer a stable HTTPS deployment for production E2E tests.

Usage

VS Code MCP

Add to .vscode/mcp.json:

{
  "servers": {
    "gemini-research": {
      "command": "uvx",
      "args": ["gemini-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Or run from source:

{
  "servers": {
    "gemini-research": {
      "command": "uv",
      "args": ["run", "--directory", "path/to/gemini-research-mcp", "gemini-research-mcp"],
      "envFile": "${workspaceFolder}/path/to/gemini-research-mcp/.env"
    }
  }
}

Command Line

uv run gemini-research-mcp
# or
uvx gemini-research-mcp

DOCX Export

Export research sessions to professional Word documents with:

• Cover page with title, date, and research metadata
• Clickable Table of Contents with navigation to sections
• Professional typography: Calibri fonts, 1-inch margins, 1.5x line spacing
• Executive summary with elegant formatting
• Full research report with proper heading hierarchy
• Sources section with full clickable URLs
• Metadata table with session details

VS Code Setup

To enable DOCX export, install with the [docx] extra:

{
  "servers": {
    "gemini-research": {
      "command": "uvx",
      "args": ["--from", "gemini-research-mcp[docx]", "gemini-research-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key"
      }
    }
  }
}

Downloading Files

export_research_session is disk-first: the file is always written to disk and the absolute path is returned on the first line of the response text (e.g. ✅ **Saved to:** /…/report.docx). This means any MCP client — GUI or headless — gets a usable file path back.

By default exports are written to GEMINI_RESEARCH_EXPORT_DIR (defaults to ~/.gemini-research/exports/; falls back to the system temp dir if that location isn't writable). Override per-call with the output_path argument:

{
  "name": "export_research_session",
  "arguments": {
    "interaction_id": "v1_...",
    "format": "docx",
    "output_path": "/absolute/or/relative/path/report.docx"
  }
}

When output_path is supplied, the parent directory must already exist (no silent mkdir). GUI hosts (e.g. VS Code Copilot Chat) also receive an EmbeddedResource attachment for native "Save As" — clients that can't render it can safely ignore it.

Client compatibility

research_deep requires MCP Tasks support (SEP-1732) on the client. Clients that do not advertise the tasks capability will receive a -32600 error.

Known client status:

• VS Code Copilot Chat / MCP Inspector / Claude Desktop — supported.
• GitHub Copilot CLI — tracked upstream at github/copilot-cli#2538; until that lands, use research_web from the CLI.

Installation (pip/uv)

# Install with DOCX support
pip install 'gemini-research-mcp[docx]'
# or
uv add 'gemini-research-mcp[docx]'

Features

Feature	Description
Cover Page	Title, date, duration, tokens, AI agent
Clickable TOC	Internal hyperlinks navigate to sections
Syntax Highlighting	Pygments-powered code blocks with GitHub colors
Professional Styling	Calibri fonts, proper heading hierarchy (H1-H4)
Page Margins	Standard 1-inch (2.54cm) margins
Heading Spacing	keep_with_next prevents orphan headings
Sources	Full URLs as clickable hyperlinks
Pure Python	No external binaries (Pandoc not required)

Resources

MCP Resources provide read-only data that clients can access:

Resource	Description
research://models	Available models and their capabilities
research://exports	List cached exports ready for download
research://exports/{id}	Download an exported file (Markdown, JSON, or DOCX)

File Downloads

The export_research_session tool creates exports and returns a resource URI. Clients (like VS Code) can then fetch the resource to download the file with proper MIME type handling.

Development

uv sync --extra dev
uv run pytest
uv run mypy src/
uv run ruff check src/

Tests

uv run pytest                    # Unit tests
uv run pytest -m e2e             # E2E tests (requires GEMINI_API_KEY)
uv run pytest --cov=src/gemini_research_mcp  # With coverage

Pricing

Tool	Typical Cost
research_web	~$0.01-0.05 per query
research_deep	~$2-5 per task

Deep Research uses ~80-160 searches and ~250k-900k tokens per task.

License

MIT