Gemini Research MCP Server

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

Built on FastMCP 4.0.0b5 (beta, exact-pinned) with the modern sessionless MCP protocol, Gemini 3.7 Flash, MCP Tasks (SEP-1732), the guard-pattern elicitation flow, a BM25-compacted tool catalog, and pluggable Disk/Redis storage for multi-worker deployments.

Architecture

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

    subgraph Server["gemini-research-mcp"]
        direction TB
        FastMCP["FastMCP 4 Server<br/>@mcp.tool()<br/>BM25SearchTransform"]
        
        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 + artifact store"]
            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"]
        Disk["DiskStore<br/>XDG data directory"]
        Redis["Redis/Valkey<br/>shared multi-worker storage"]
    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 --> Disk
    StorageMod -.-> Redis

Tools

The server exposes a BM25-compacted catalog: only the 5 tools below plus the synthetic search_tools/call_tool pair are listed by default (fastmcp.server.transforms.search.BM25SearchTransform). Utility tools (fetch_webpage, research_followup, list_research_sessions, list_format_templates, refine_research_plan, inspect_mcp_server_for_gemini) are hidden from the default listing to keep the catalog small for LLM tool-selection, but remain fully callable directly by name or via the call_tool proxy, and are discoverable by relevance through search_tools.

research_deep / research_deep_max Deep Research parameters

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:

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. On the modern sessionless MCP protocol this uses a stateless guard pattern (InputRequiredResult, two independent tool calls, no server-held connection); legacy handshake clients still use MCP Elicitation (ctx.elicit())
• Deep Research Max: research_deep_max exposes Google's Max agent for exhaustive, high-stakes, and offline research workflows
• Collaborative Planning: research_deep(..., collaborative_planning=True) returns the drafted plan for approval before running the full report; refine or approve it with refine_research_plan
• Visualization: visualization="auto" lets Deep Research produce supporting images, persisted as downloadable MCP resource artifacts
• MCP Tasks: Real-time progress with streaming updates
• Session Persistence: Research sessions are automatically saved and can be resumed later; shareable across instances with Redis (see Storage backends)
• Persistent, Disk-First Exports: Export to Markdown, JSON, or professional DOCX with Table of Contents; artifacts survive restarts and can be shared through Redis while files are still written to disk by default
• File Search: Search your own data alongside web using file_search_store_names
• Remote MCP sources: research_deep_max can call remote MCP servers using mcp_servers
• Format Instructions: Control report structure (sections, tables, tone)
• LangChain-ready: verified consumable via langchain.mcp.MCPAdapter (LangChain 1.4.0a2) over both stdio and streamable-http - see scripts/langchain_interop_smoke.py. LangChain is never a dependency of this package.

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

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

Transports

The server defaults to stdio, matching every existing VS Code/Claude Desktop configuration - no changes required for local, single-client use.

Streamable HTTP is opt-in, for remote or multi-client/multi-worker deployments, and is sessionless (no sticky session required across calls):

# Local-only (no auth required, loopback binding):
uv run gemini-research-mcp --transport streamable-http

# Remote-accessible (bearer token required - refuses to start otherwise):
GEMINI_RESEARCH_HTTP_BEARER_TOKEN=$(openssl rand -hex 32) \
  uv run gemini-research-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Binding to any non-loopback host (0.0.0.0, ::, a LAN/public IP, etc.) without GEMINI_RESEARCH_HTTP_BEARER_TOKEN set causes the server to refuse to start - this prevents accidentally exposing your Gemini API quota to the public internet. 127.0.0.1/localhost/::1 never require a token.

--transport, --host, --port, and --path CLI flags mirror the GEMINI_RESEARCH_TRANSPORT/GEMINI_RESEARCH_HTTP_HOST/GEMINI_RESEARCH_HTTP_PORT/GEMINI_RESEARCH_HTTP_PATH environment variables (CLI flags take precedence).

Storage backends

Research sessions and export artifacts are stored through a single backend-agnostic layer:

• Local (default): a DiskStore under the XDG data directory (GEMINI_RESEARCH_STORAGE_PATH to override) - zero configuration, single process/single machine.
• Distributed (Redis/Valkey): set GEMINI_RESEARCH_STORAGE_URL=redis://host:6379/0 to share sessions and exports across multiple server instances or workers - a session created (or an export produced) on one instance is immediately readable from another. Requires the distributed extra:

uv add 'gemini-research-mcp[distributed]'

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 exposes remote MCP server wiring through the Interactions API. In this package, pass mcp_servers to research_deep_max when the agent needs a specialized/private data source.

Experimental: remote MCP is gated to deep-research-max-preview-04-2026. The standard deep-research-preview-04-2026 agent has reproduced provider-side finalization/retrieval 500 api_error failures after successful MCP tool calls; use research_deep_max or set DEEP_RESEARCH_AGENT=deep-research-max-preview-04-2026. See https://github.com/googleapis/python-genai/issues/2126.

Known limitation (live-verified): even on research_deep_max, the provider-side agent may call the remote MCP tool successfully (confirmed via server-side access logs) yet fail to ground its final report in the returned data — paraphrasing a marker token instead of quoting it verbatim, or omitting specific evidence IDs/facts from a retrieved evidence ledger. This is preview-API agent behavior, not a bug in this package. Treat research_deep_max MCP evidence as best-effort: always verify citations against your own audit/quarantine path before trusting a report for decisions.

Example research_deep_max mcp_servers argument:

{
  "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 Max 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.

Live E2E validation is intentionally skipped by default because it is paid, slow, and depends on preview APIs. There are two useful levels:

1. Minimal marker smoke test: proves remote MCP result inclusion with a stable HTTPS MCP fixture that returns MCP_E2E_FIXTURE_7B9F2A from get_guardrail_summary.

GEMINI_API_KEY=... \
GEMINI_MCP_E2E_URL=https://fresh-stable-fixture.example/mcp \
uv run pytest -m e2e tests/test_deep_research_max_mcp_e2e.py -q

2. Realistic evidence-inclusion test: proves Deep Research Max can start a new research task and integrate substantive MCP-only evidence into the final report. The fixture should expose read-only tools such as market_get_mission, market_get_evidence_ledger, market_get_runtime_policy, and market_generate_report.

GEMINI_API_KEY=... \
GEMINI_MCP_REALISTIC_E2E_URL=https://fresh-realistic-fixture.example/mcp \
GEMINI_MCP_E2E_ARTIFACT_DIR=/tmp/gemini-realistic-e2e \
uv run pytest -m e2e tests/test_deep_research_max_mcp_e2e.py \
  -q -s -k realistic_evidence_inclusion

The realistic test checks for multiple MCP-only evidence IDs, distinctive metrics, platform constraints, a derived gate recommendation, and absence of the hidden/disallowed tool canary.

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 backed by the persistent research://exports/{id} resource store 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

Resources

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

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

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

License

MIT