Run one research job on the selected engine as a background Task.

Each new submission can start a separate paid research job; a retried or resubmitted Task is a new job. Use get_research_run with the returned run_id to inspect or recover the result.

Run the same question on exactly two engines and return attributed reports.

This can incur two research workloads. No synthesis, merging or scoring is performed; the caller combines the reports.

Web research with Gemini grounding. Returns an answer with citations.

Uses a fixed high thinking level for higher-quality grounded answers. Latency varies with the query and provider load.

Use for: quick lookups, fact-checking, current events, documentation, "what is", "how to", real-time information, news, API references, error messages.

Comprehensive autonomous research agent. Takes 3-20 minutes.

Uses the fast/default April 2026 Deep Research agent. Use this by default for interactive questions, exploratory research, competitive analysis, comparisons, and latency/cost-sensitive multi-source synthesis.

For maximum-comprehensiveness research, use research_deep_max instead.

For vague queries, the tool automatically asks clarifying questions to refine the research scope before starting (when elicitation is available).

Maximum-comprehensiveness autonomous research agent.

Use when the user explicitly says "Max", "deep research max", "exhaustive", "comprehensive", "due diligence", "market map", "literature review", "high stakes", "board-ready", "offline/nightly", or asks for maximum completeness over speed.

For ordinary interactive research, use research_deep instead.

Resume an interrupted or in-progress research_deep session.

Use when a research_deep call was cut short (client disconnect, transport error, cancellation) or when you want to check whether a long-running session has since completed on Gemini's servers.

Because research_deep persists its session at the start, the research continues on Gemini's side even when the MCP client goes away — this tool retrieves the result once it's ready.

Call with no arguments to list recoverable sessions. Call with an interaction_id (returned by the original research_deep call or by list_research_sessions) to check a specific session's status; if it has completed, the full report is returned. Hand the result off to export_research_session(format="docx") to save the report to disk.

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 research_deep run completes or is interrupted, and to convert reports into a shareable Word document.

Disk-first contract. The file is always written to disk, and the absolute path is returned on the first line of the response as Saved to: <path>. When output_path is omitted the file lands in GEMINI_RESEARCH_EXPORT_DIR (default ~/.gemini-research/exports/). An EmbeddedResource is still attached so GUI hosts can expose their native "Save As" affordance.

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:

• docx: Word document with headings, lists, and table of contents

• markdown: Clean .md file with full report and citations

• json: Machine-readable, all metadata preserved

Typical recovery flow:

1. research_deep(...) completes (or is resumed via resume_research).

2. export_research_session(format="docx") — no other arguments needed; the path on disk is returned in the response text.

Search for tools using natural language.

Returns matching tool definitions ranked by relevance, in the same format as list_tools.

Call a tool by name with the given arguments.

Use this to execute tools discovered via search_tools.