Design & media

Gemini Web MCP

Try it

Extend an agent with Gemini assistance, multimodal creation, and explicit account workflows.

What it does

Use this skill when an agent should extend itself with Gemini Web: get a second opinion, search current web sources, understand images/files/URLs, run Deep Research, generate or edit image/video/music artifacts, or explicitly work with Gemini account data. Route by user intent instead of loading every tool. This skill is the compatibility router; prefer the focused gemini-assist skill when only assistance and understanding are needed. Do not use for repository implementation, tests, CI, packaging, or releases—use gemini-web-mcp-development instead.

The skill document

Gemini Web MCP

Use this Skill to complete the user's task with Gemini, not to tour the Gemini tool surface.

The product priority is:

1. Agent assistance and multimodal understanding
2. Generated artifacts
3. Explicit Gemini account management

Choose one lane for the current task. Do not expose or load account-management tools merely because they exist.

Choose the Capability Lane

User intentPreferred current routeWhat success means
Second opinion, critique, code/design reviewlow-token chat; primary gemini_chat when exact controls are neededuseful Gemini result incorporated into the agent's work
Quick current-web lookupchat or gemini_chat with an explicit request for current sourcesanswer plus observed source URLs; otherwise label it ungrounded or escalate to Research
Understand one image or screenshotlow-token chat(image_path=...); primary gemini_chat(image_paths=[...])analysis returned to the agent and used in the surrounding task
Understand files, URLs, or mixed evidenceprimary gemini_upload_file, gemini_analyze_url, and image chat as neededsource identity preserved and conclusions synthesized
Deep, multi-source researchprimary gemini_deep_research(wait_for_completion=false, retain_chat=true)an opaque operation/chat handle is preserved immediately; a later result yields a report
Generate or edit imageslow-token create(type="image") / edit; primary media tools when exact controls are neededa usable image Artifact, preferably a verified local file
Generate video or musiclow-token `create(type="video""music")` or primary media tools
History, Notebook, Scheduled, Gem, Prompt, usage, or cleanuplow-token account facades or narrow primary profilesonly the explicitly requested account operation is performed

Load workflows.md for detailed task routes.

Default Server Choice

Use gemini-mcp-skill-server for the smallest current tool surface when it can complete the task.

Use the primary server only for a narrow profile:

  • GEMINI_TOOLS=model for text/session work;
  • GEMINI_TOOLS=core for files, URLs, media, and Deep Research;
  • GEMINI_TOOLS=history or history-organize for explicit history work;
  • GEMINI_TOOLS=account-read for explicit account inventory;
  • GEMINI_TOOLS=scheduled-admin only for requested scheduled mutations.

Do not use GEMINI_TOOLS=all as a general-agent default.

The repository is migrating toward three dedicated products. gemini-assist is now implemented as the dedicated gemini-mcp-assist server (gemini_ask, gemini_search, gemini_understand_image, gemini_understand, gemini_research) with its own gemini-assist Skill; gemini-create and gemini-account are not implemented yet. This Skill remains the compatibility router until they land.

Standard Workflow

  1. Identify the user's intended outcome.
  2. Choose exactly one capability lane.
  3. Call the narrowest current tool that can complete it.
  4. Read the structured result before trusting compatibility prose.
  5. Continue the user's actual task with the result or Artifact.
  6. Use manifest or diagnostics only when discovery or recovery is needed.

Do not call the manifest before every known workflow. Use gemini_get_tool_manifest or account(action="manifest") when:

  • the expected tool is unavailable;
  • a schema or profile appears different;
  • the user asks what is supported;
  • upstream drift is suspected.

Information Versus Artifacts

Search and understanding normally return information to the calling agent. The agent should synthesize it and continue working rather than dumping raw Gemini output.

Generation normally returns an Artifact. The agent should pass that file or URI to the next relevant tool:

  • add the image to the document, website, slide, or app;
  • use the edited image instead of merely reporting its path;
  • attach the video or audio to the requested project;
  • read and cite the research report.

A path, URI, or success sentence alone is not completion. Load artifacts.md for acceptance and handoff rules.

Long Operations

Deep Research, video, and music are long operations. Start them asynchronously by default.

Preserve every returned operation_id, upstream_operation_id, upstream_chat_id, and Artifact identity. Do not start a duplicate operation merely because one MCP call timed out.

Until the shared local operation registry lands, use start-only/current typed states and retain the upstream IDs. The target contract is an opaque, restart-safe handle stored in local SQLite with no prompt, chat, Cookie, or raw-response content.

Load operations.md before running or recovering a long operation.

Account Workflows

Only load or use account operations when the user explicitly asks to work with Gemini account data.

Start with list/search/read actions, identify the exact object, then mutate or delete it. A remote request being accepted is not proof that the target state changed; require positive read-back before claiming success.

For browser Cookie export, obtain explicit user approval because it can create sensitive account-authentication material in a local cache. Session reset changes only MCP/Gemini conversation state; it never changes agent memory or agent instructions.

Load tool_surface.md only when detailed account, privacy, destructive, or profile information is needed.

Recovery

Load recovery.md when a tool is missing, authentication fails, an entitlement is unavailable, a long operation times out, an Artifact is incomplete, or Gemini Web behavior appears to have drifted.

Do not convert an unavailable entitlement, an ungrounded answer, a queued operation, or an accepted-but-unverified mutation into a success claim.

Related skills

Connect to Google Search and Gemini through the built-in local-mcp Google adapter and one fixed UXC link. Use when the user wants to run Google searches, cha...

14 installs

Generate and edit images, video, and music with Google Gemini models via MCP. Use when the user asks to generate, create, or edit images (Gemini / Nano Banana), produce a consistent set of images, compose/blend multiple images, generate a short video (text→video or image→video, via the omni model), or generate music/audio clips (via Lyria). Triggers on phrases like "generate an image of", "edit this image with Gemini", "create a set of consistent images", "make a video of", "generate a video", "generate music", "make a song/audio clip", "use Nano Banana to make", or any request to produce images, video, or music via the Gemini API. Requires the @chrischall/gemini-mcp package installed and the gemini server registered (see Setup below).

8 installs

Ask questions and read documentation about any GitHub repository using DeepWiki MCP. Use when you need to understand a codebase, find specific APIs, or get c...

29 installs

当用户希望实际使用 Gemini 网页版完成一次对话时使用本 Skill,包括发送 Prompt、继续已有对话、上传图片或文件、获取 Gemini 回复以及恢复 Gemini 登录状态。典型请求包括:"帮我问 Gemini"、"用 Gemini 回答"、"把这段话发给 Gemini"、"让 Gemini 看这张图...

Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready st...

30 installs

Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear,...