Interact with Microsoft 365 and Office services through the Microsoft Graph API.
G-Krusch Workspace 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
Local-first Google Workspace MCP server with hybrid FTS5 Drive RAG, Docs, Calendar, and Gmail.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user g-krusch-workspace-mcp '--' npx -y g-krusch
# 2 — ask your agent for something these tools do
# get_agent_steering, search_drive_rag, read_drive_file and 9 more
G-Krusch Workspace 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 G-Krusch Workspace 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 Node.js — the current LTS (24) is the safe choice; npx 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 g-krusch-workspace-mcp '--' npx -y g-kruschReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
12 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.
Retrieve the authoritative agent.md steering directives, persona rules, and active project state directly from Google Drive.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| force_refresh | boolean | no | Force re-fetch from Google Drive ignoring local cache |
Perform semantic vector and keyword search across all indexed files in the Google Drive workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query or question to retrieve context for |
| limit | integer | no | Maximum number of matching chunks to return (two-stage Top-128 reranked) |
Read the content of any document or file from Google Drive (Google Docs are automatically exported as clean markdown).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_id | string | no | Google Drive File ID |
| path | string | no | Relative path in workspace (e.g. "context/spec.md", "agent.md") |
Create or update a file, native Google Doc, Google Sheet, or Google Slides presentation in Google Drive (supports Markdown -> Google Docs, CSV/Markdown tables -> Google Sheets, and "---"-separated Markdown slides -> Google Slides).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Relative path in workspace (e.g. "output/summary.md", "output/report.gdoc", "output/metrics.gsheet", "output/pitch.slides") |
| content | string | yes | Text, Markdown, CSV, or "---"-separated Markdown slides to write |
| mime_type | string | no | MIME type (default: "text/markdown"; or "application/vnd.google-apps.document" / "docs", "application/vnd.google-apps.spreadsheet" / "sheets", "application/vnd.google-apps.presentation" / "slides") |
Safely move a file inside the G-Krusch Google Drive workspace to trash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_id | string | no | Google Drive File ID to delete |
| path | string | no | Relative path in workspace (e.g. "output/temp.md") |
List all files and subdirectories inside the G-Krusch Google Drive workspace.
No parameter schema on file.
Trigger a fresh synchronization of Google Drive workspace files into the local vector RAG index.
No parameter schema on file.
Get real-time operational status of Google Drive connection, workspace root, and RAG index statistics.
No parameter schema on file.
List upcoming events from the user's primary Google Calendar.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| max_results | integer | no | Maximum number of upcoming events to return |
| time_min | string | no | Optional ISO-8601 lower bound timestamp (defaults to now) |
| query | string | no | Optional free-text search filter for event titles or descriptions |
Schedule a new event or reservation hold on the user's primary Google Calendar.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| summary | string | yes | Title of the calendar event |
| start_time | string | yes | ISO-8601 start timestamp (e.g. "2026-10-18T19:30:00-07:00") |
| end_time | string | no | Optional ISO-8601 end timestamp (defaults to +1 hour) |
| description | string | no | Optional event notes, booking links, or agenda |
| location | string | no | Optional venue address or meeting link |
Search messages in the user's Gmail inbox using standard Gmail search operators (e.g. "is:unread", "from:alex").
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Gmail search query |
| max_results | integer | no | Maximum number of matching messages to return |
Create a RFC-2822/RFC-2047 sanitized Gmail draft or send an email immediately (e.g. for reservations, follow-ups, or replies).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | Recipient email address |
| subject | string | yes | Email subject line |
| body | string | yes | Plain-text email body |
| send_immediately | boolean | no | Set true to send the email immediately; false creates a Gmail draft |
- 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 G-Krusch Workspace 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 | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 (12 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 |
|---|---|---|
| get_agent_steering | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_drive_rag | no tags | |
| read_drive_file | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| write_drive_file | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| delete_drive_file | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| list_drive_workspace | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sync_drive_rag | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_workspace_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_calendar_events | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_calendar_event | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| search_gmail_messages | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| compose_gmail_message | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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 1.0.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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 G-Krusch Workspace 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.