Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Gemini Pro is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Your Google AI Pro plan in Claude, Codex and Gemini CLI: Gemini, Flow, Notebooks, Jules, Veo
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user gemini-pro-mcp '--' uvx gemini-pro-mcp
# 2 — ask your agent for something these tools do
# flow_status, flow_make_video, flow_tools and 33 more
Gemini Pro costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Gemini Pro as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user gemini-pro-mcp '--' uvx gemini-pro-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take GEMINI_API_KEY (Gemini API key for the video and image tools (optional; these tools are billed)), JULES_API_KEY (Jules API key from jules.google.com/settings (optional, for the jules_* tools)), GEMINI_PRO_ENABLE_FLOW (Set to 1 to enable the Google Flow tools), GEMINI_PRO_ENABLE_BROWSER (Set to 1 to enable all browser tools (Gemini app, Notebooks, AI Mode)) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
36 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
EXPERIMENTAL: check that Google Flow is signed in, and show credits left. Free.
Takes no parameters.
EXPERIMENTAL: make a video of any length with Google Flow, as one .mp4.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | The video idea: story, characters, place, style, sound. |
| duration_seconds | integer | no | Total length wanted, e.g. 120 for two minutes (max 600). |
| aspect_ratio | string | no | "16:9" (landscape) or "9:16" (vertical). |
| file_name | string | no | Optional name for the final .mp4. |
| project_id | string | no | Flow project to use; default is the open or most recent one. |
EXPERIMENTAL: list every Flow tool: Google's (Image Editor, Mockup, Shot Explorer, Mask Magic, Video Resizer, Transition Machine, Type Overlays, Shader Effects, Poster Designer...), the community's and the user's own. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | — |
EXPERIMENTAL: open a Flow tool by name and show its interface.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Tool name as listed by flow_tools, e.g. "Video Resizer". |
| project_id | string | no | Flow project; default is the open or most recent one. |
EXPERIMENTAL: progress of flow_make_video jobs. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | no | The job to show; default lists all jobs of this session. |
EXPERIMENTAL: ask Google Flow's agent to make videos or images.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request | string | yes | What to make, in plain words, e.g. "an 8 second 9:16 video of a red tram in Baku at sunset, use Veo 3.1 Fast". For longer videos use flow_make_video. |
| new_session | boolean | no | Start a fresh agent chat (default). False continues the current chat, e.g. to answer a question the agent asked. |
| project_id | string | no | Flow project to use; default is the open or most recent one. |
| wait_seconds | integer | no | How long to wait for the agent's answer. |
| file_name | string | no | Optional base name for saved files (pre-approved mode). |
EXPERIMENTAL: approve Flow's pending request; SPENDS FLOW CREDITS.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wait_seconds | integer | no | How long to wait for the media (videos take minutes). |
| file_name | string | no | Optional base name for the saved files. |
EXPERIMENTAL: decline Flow's pending request. Free.
Takes no parameters.
EXPERIMENTAL: download the newest videos/images of the Flow project. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | integer | no | How many of the newest media items to save. |
| file_name | string | no | Optional base name for the saved files. |
Generate a short video with native sound from a text prompt, with Gemini Omni Flash through the Gemini API, and save it as an .mp4 in GEMINI_PRO_OUTPUT_DIR. One call makes one clip of about 8 seconds; for longer videos chain video_edit, or use flow_make_video on the user's Flow credits when…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | Subject, action, setting, camera and sound, e.g. "A red tram crosses Baku at sunset, slow dolly shot, street noise". English works best; timecodes like "[0-3s] ... [3-6s] ..." sequence the shot. |
| aspect_ratio | no | "16:9" (landscape, default) or "9:16" (vertical). | |
| resolution | no | "720p" (default), "360p", or upscaled "1080p" or "4k". | |
| first_frame | string | no | Local image path the video starts from. |
| last_frame | string | no | Local image path the video ends on. |
| reference_images | array | no | Up to 3 local images of characters or objects to keep. |
| file_name | string | no | Optional .mp4 file name; default is the date plus prompt words. |
| wait_seconds | integer | no | How long to wait for the render (default 300) before returning an id to fetch later with video_check. |
Change or extend a video; the result is saved as a new file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| instruction | string | yes | e.g. "Make it night", or to extend: "Continue the scene: the car drives off" (adds 3-10 s, up to 40 s in total). |
| previous_id | string | no | id returned by an earlier video_generate or video_edit. |
| video_path | string | no | Local video (max 10 s) to edit instead. |
| aspect_ratio | no | "16:9" or "9:16". | |
| resolution | no | "720p" (default), "360p", "1080p" or "4k". | |
| file_name | string | no | Optional .mp4 file name. |
| wait_seconds | integer | no | How long to wait before returning an id for video_check. |
Fetch a video that video_generate or video_edit started but had not finished rendering when they returned, and save it as an .mp4. Free: the video was paid for when it was started, and checking costs nothing. Call it again with the same id if the video is still rendering.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The id returned by video_generate or video_edit. |
| wait_seconds | integer | no | How long to keep waiting in this call (default 120) before returning the current status. |
Create a new image from a prompt, or edit local images, with Nano Banana through the Gemini API, and save the result in GEMINI_PRO_OUTPUT_DIR. Pass previous_id to refine an earlier result step by step ("make the sky darker") without starting over.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | What to draw, or how to change the input images, e.g. "Turn this sketch into a clean flat app icon on a white background". |
| model | no | "gemini-nano-banana-2.1" (default), "gemini-3.1-flash-lite-image" (cheapest, 1K only) or "gemini-3-pro-image" (best, for hard tasks). | |
| aspect_ratio | no | "1:1" (default), "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9" or "21:9". | |
| image_size | no | "1K" (default), "2K" or "4K". | |
| input_images | array | no | Local image paths to edit or to use as references. |
| previous_id | string | no | The id of an earlier image_generate result to refine. |
| file_name | string | no | Optional file name; default is the date plus prompt words. |
Ask Gemini a question or give it a reading task, through the Antigravity CLI on the user's Google AI Pro plan (no API cost; uses the plan's limits).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | The question or task. |
| model | string | no | Model id from gemini_models (e.g. "gemini-3.8-flash-medium"); default is agy's (or GEMINI_PRO_AGY_MODEL). |
| paths | array | no | Local files or folders Gemini may read. |
| conversation_id | string | no | Continue an earlier gemini_ask/gemini_research chat. |
| effort | no | Reasoning effort: low, medium, high, xhigh or max. |
Research a question on the live web with Gemini and Google Search, and get an answer that cites its sources. Use it for current facts, releases, prices, docs or comparisons that may be newer than your training data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | What to find out, with context that narrows it, e.g. "What changed in Flutter 3.47 for Android builds?". |
| model | string | no | Model id from gemini_models, e.g. "gemini-4-argon-high"; omit for agy's default (or GEMINI_PRO_AGY_MODEL). |
| effort | no | Reasoning effort: "low", "medium", "high", "xhigh" or "max". |
Delegate a coding task to Gemini, which reads and EDITS files in one local folder through the Antigravity agent on the user's Google AI Pro plan (no API cost). This changes files: tell the user, and review the result afterwards, e.g. with git diff. Terminal commands run in a sandbox and only the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | What to change and how to know it is done, e.g. "Add unit tests for parse_date in utils/dates.py; all tests must pass". |
| folder | string | yes | Absolute path of the project folder Gemini may edit. |
| model | string | no | Model id from gemini_models; omit for agy's default. |
| agent | string | no | Name of an Antigravity agent from gemini_agents to run the task. |
| effort | no | Reasoning effort: "low", "medium", "high", "xhigh" or "max". | |
| conversation_id | string | no | Continue an earlier gemini_code or gemini_ask chat, e.g. to ask for fixes to the previous change. |
List the custom Antigravity agents the user has made or installed, such as a "reviewer" or "test-writer" agent with its own instructions.
Takes no parameters.
List the models the user's Google account can use through the Antigravity CLI, e.g. Gemini 4 Argon and Gemini 3.8 Flash at several thinking levels.
Takes no parameters.
List everything a Google AI Pro plan includes and which tool of this server reaches each part, or why a part cannot be reached (mobile-only, US-only, purchases). Read-only, free and offline. Call it first when the user asks what their plan can do or which tool to use.
Takes no parameters.
Show a Google AI site as text with numbered elements, in the user's signed-in Chrome: Gemini app and Notebooks, AI Studio, Jules, Colab, AI Mode, Flow, Flow Music, Docs/Drive... Free. Use with google_act.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | A page to open first, e.g. "https://gemini.google.com/app" or "https://jules.google.com". Without it the site's tab is shown as is. |
| site | string | no | Which open tab to show (a host like "gemini.google.com"); default is the one used last. |
Act on an element from the last google_page snapshot, like a person:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | Element number from the snapshot, e.g. "12" or "f1:3". |
| action | no | click, type, replace, press (a key), upload (local files), select (option label in text), hover or scroll. | |
| text | string | no | Text to type, key to press or option to select. |
| files | array | no | Local paths for action="upload". |
| wait_seconds | integer | no | How long to wait afterwards (e.g. 120 for an export). |
| site | string | no | Tab host if not the one of the last google_page call. |
Use the Gemini app (gemini.google.com) on the user's Google AI Pro plan:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | The request. |
| tool | no | "chat" (default), "image", "video", "music", "canvas", "deep_research" (starts a long report; fetch it later with gemini_app_result) or "guided_learning". | |
| model | string | no | "argon" (4 Argon, complex tasks), "pro" (3.1 Pro), "flash" (3.8 Flash) or "flash-lite"; default is the app's current choice. |
| thinking | string | no | "low", "medium" or "high" thinking level. |
| files | array | no | Local files to attach (images, PDFs, documents...). |
| temporary | boolean | no | Use a temporary chat that is not kept in the history. |
| wait_seconds | integer | no | How long to wait for the answer. |
Read the latest answer of a Gemini app chat (e.g. a Deep Research report) and save its images/videos. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chat_url | string | yes | The "Chat:" URL returned by gemini_app. |
| wait_seconds | integer | no | How long to wait if Gemini is still writing. |
Ask Google Search's AI Mode (Gemini 4 Argon with live search, on the user's Pro plan) and return its answer with source links. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | What to search for. |
| wait_seconds | integer | no | How long to let the answer finish. |
List the GitHub repositories the user has connected to Jules, Google's cloud coding agent. Read-only and free. Call it before jules_start to get the exact repo name; Jules can only work on repositories listed here.
Takes no parameters.
Start a Jules session: Google's coding agent works on a task in one of the user's GitHub repositories, in the cloud and asynchronously, within the Google AI Pro plan's Jules limits (no extra cost). It can push a branch and open a pull request, so confirm the task with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | The task with acceptance criteria, e.g. "Add input validation to the /signup endpoint and tests for it". |
| repo | string | no | Repository from jules_sources, e.g. "github/owner/repo"; omit for a session without a repository. |
| branch | string | no | Branch Jules starts from (default "main"). |
| title | string | no | Optional session title; Jules makes one up otherwise. |
| create_pr | boolean | no | True lets Jules open a pull request automatically when done. |
| require_plan_approval | boolean | no | True makes Jules wait for jules_approve_plan before it changes any code. |
Check on a Jules session started with jules_start: its state, its most recent activities (plan, progress messages, questions, completion) and the pull request it opened, if any. Read-only and free; call it again to poll a session that is still working.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | Session id from jules_start or jules_sessions, or its full "sessions/<id>" name or web link. |
| activities | integer | no | How many of the latest activities to show (default 15). |
List the user's most recent Jules sessions, newest first, to find a session id or see which tasks are still running. Read-only and free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many sessions to list (default 10). |
Approve the plan Jules proposed, so it starts writing code. Only for a session started with jules_start(require_plan_approval=True) whose state is awaiting plan approval; read the plan with jules_status first and show it to the user. To change the plan instead, send feedback with jules_message.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | Session id from jules_start or jules_sessions. |
Send a message to Jules inside an existing session: answer a question it asked, give feedback on its plan or code, or ask for a change. Jules replies asynchronously, so read the answer later with jules_status. To give Jules a new task, use jules_start instead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | Session id from jules_start or jules_sessions. |
| message | string | yes | What to tell Jules, in plain language. |
List the user's Gemini Notebooks (formerly NotebookLM). Free.
Takes no parameters.
Create a Gemini Notebook with sources. Up to 300 sources per notebook on Pro.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| files | array | no | Local files (PDF, Word, slides, images, audio...). |
| urls | array | no | Web pages or YouTube links. |
| text | string | no | Text to paste as a source. |
| title | string | no | Notebook title (default: Notebook names it from the sources). |
Add sources to a Gemini Notebook.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notebook | string | yes | Notebook id or URL (from notebook_list). |
| files | array | no | Local files to upload. |
| urls | array | no | Web pages or YouTube links. |
| text | string | no | Text to paste as a source. |
Ask a question answered only from a notebook's sources, with citations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notebook | string | yes | Notebook id or URL (from notebook_list). |
| question | string | yes | The question. |
| wait_seconds | integer | no | How long to wait for the answer. |
Make a Studio output from a notebook's sources: Audio Overview (podcast), Video Overview, Slide Deck, Mind Map, Report, Flashcards, Quiz, Infographic or Data Table. Uses the plan's Notebook limits. Audio and video files are downloaded when ready.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notebook | string | yes | Notebook id or URL (from notebook_list). |
| output | yes | Which Studio output to make. | |
| wait_seconds | integer | no | How long to wait (audio/video overviews take minutes). |
Join local video clips, in the given order, into one .mp4 with ffmpeg.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| clips | array | yes | Paths of the clips, first to last (at least one). |
| file_name | string | no | Name for the joined file, saved in GEMINI_PRO_OUTPUT_DIR; a number is added if it already exists. |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Gemini Pro or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| gemini_ask | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gemini_research | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gemini_code | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gemini_agents | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gemini_models | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| google_pro_benefits | no tags | |
| flow_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| flow_tools | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| flow_open_tool | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| flow_job | no tags | |
| flow_reject | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| flow_collect | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| flow_make_video | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| flow_generate | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| flow_approve | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| google_act | external-sink | external-sink: keyword "upload_file", declares readOnlyHint: false, openWorldHint: true |
| gemini_app | untrusted-inputexternal-sink | untrusted-input: keyword "fetch"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| google_page | external-sinkuntrusted-input | external-sink: keyword "send_message"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| gemini_app_result | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| google_ai_mode | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| jules_sources | no tags | |
| jules_start | no tags | |
| jules_status | no tags | |
| jules_sessions | no tags | |
| jules_approve_plan | no tags | |
| jules_message | no tags | |
| video_check | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| video_generate | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| video_edit | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| image_generate | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| notebook_create | no tags | |
| notebook_add_sources | no tags | |
| notebook_studio | no tags | |
| notebook_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| notebook_ask | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| video_stitch | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.5. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Gemini Pro can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.