A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Google 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
Search and work in Gmail, Calendar, Drive, Docs, Sheets and Slides across several Google accounts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GOOGLE_OAUTH_CLIENT_FILE=${GOOGLE_OAUTH_CLIENT_FILE}' --env 'GMAIL_ADDRESSES=${GMAIL_ADDRESSES}' --env 'GMAIL_MODIFY_ACCOUNTS=${GMAIL_MODIFY_ACCOUNTS}' --transport stdio foreverworks-google-workspace-mcp '--' npx -y @foreverworks/mcp-google
# 2 — ask your agent for something these tools do
# begin_consent, complete_consent, find_people and 105 more
It needs GOOGLE_OAUTH_CLIENT_FILE, GMAIL_ADDRESSES, GMAIL_MODIFY_ACCOUNTS: this reads them from your environment, so export them first.
Google 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 Google 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. Claude Code reads GOOGLE_OAUTH_CLIENT_FILE (Path of your OAuth client's JSON (a Desktop app client from the Google Cloud console)), GMAIL_ADDRESSES (Each account's label and address, e.g. personal=ana@example.com,work=ana@example.org), GMAIL_MODIFY_ACCOUNTS (Where each mailbox's Gmail grant is kept, e.g. personal=/path/to/grants/gmail-personal.json; consent writes it there. Without it the other products work,…) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx GOOGLE_OAUTH_CLIENT_FILE …, setx GMAIL_ADDRESSES …, setx GMAIL_MODIFY_ACCOUNTS … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GOOGLE_OAUTH_CLIENT_FILE=${GOOGLE_OAUTH_CLIENT_FILE}' --env 'GMAIL_ADDRESSES=${GMAIL_ADDRESSES}' --env 'GMAIL_MODIFY_ACCOUNTS=${GMAIL_MODIFY_ACCOUNTS}' --transport stdio foreverworks-google-workspace-mcp '--' npx -y @foreverworks/mcp-googleReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GOOGLE_OAUTH_CLIENT_FILE — Path of your OAuth client's JSON (a Desktop app client from the Google Cloud console).; GMAIL_ADDRESSES — Each account's label and address, e.g. personal=ana@example.com,work=ana@example.org.; GMAIL_MODIFY_ACCOUNTS — Where each mailbox's Gmail grant is kept, e.g. personal=/path/to/grants/gmail-personal.json; consent writes it there. Without it the other products work, but no mailbox does.. You set them in your own client’s config, on your machine — this marketplace never holds it.
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.
108 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.
Start granting one product access to one account: gmail (its own gmail.modify grant), calendar, editors
| Parameter | Type | Required | Notes |
|---|---|---|---|
| product | string | yes | — |
| account | string | yes | The account label, as list_accounts names it. |
| grant | string | no | Gmail only: the grant to consent. modify is the only one this server holds. |
Finish a consent from the URL the approval redirected to (http://localhost:...?state=...&code=...). The
| Parameter | Type | Required | Notes |
|---|---|---|---|
| redirect_url | string | yes | The whole URL from the browser's address bar. |
Find a person's email address by name, across every account at once: each account's contacts, the addresses
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A name or its start ("Ana Pop"), or the start of an address or a phone number. |
| account | yes | — | |
| sources | array | no | Where to look: "contacts", "other" (saved from mail) and "directory" (Workspace). Default all three. |
| limit | integer | no | Per account and source, before merging. |
The Google Meet meetings one account took part in, each with its transcripts, smart notes (Gemini's notes) and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| account | yes | — | |
| event_id | string | no | An event's eventId from agenda, in this account's calendar. |
| calendar_id | string | no | The event's calendarId, with event_id. |
| meeting | string | no | A Meet link (https://meet.google.com/abc-defg-hij) or its code. |
| days | integer | no | Without event_id or meeting: how many days back. |
| limit | integer | no | The newest meetings, at most. |
A Meet transcript as text, one line per thing said: "[0:12:05] Ana Popescu: ...", the time counted from when
| Parameter | Type | Required | Notes |
|---|---|---|---|
| account | yes | — | |
| transcript | string | yes | The transcript's name, from list_meetings. |
| page_token | string | no | nextPageToken from the previous part. |
| max_chars | integer | no | — |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
- 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 Google 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 | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (108 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>".
1 of the 108 recovered tools are registered only when first === undefined is false (dist/editors/mcp/reference.js:29) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 107.
dist/domain/errors.d.ts (4 KB) was not read: over the file-count budget.
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. moderate is the level these add up to.
107 tools are registered unconditionally · 1 more only when first === undefined is false (dist/editors/mcp/reference.js:29) — typically when a key or option is configured. All 108 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| agenda | no tags | |
| list_calendars | no tags | |
| get_event | no tags | |
| create_event | no tags | |
| update_event | no tags | |
| delete_event | no tags | |
| respond_to_invite | no tags | |
| free_busy | no tags | |
| find_time | no tags | |
| list_comments | no tags | |
| add_comment | no tags | |
| reply_to_comment | no tags | |
| edit_comment | no tags | |
| delete_comment | no tags | |
| list_revisions | no tags | |
| download_revision | untrusted-input | untrusted-input: keyword "download" |
| update_revision | no tags | |
| list_permissions | no tags | |
| share_file | no tags | |
| update_permission | no tags | |
| remove_permission | no tags | |
| begin_consent | no tags | |
| complete_consent | no tags | |
| find_people | no tags | |
| resolve_path | no tags | |
| path_of | no tags | |
| list_folder | no tags | |
| find_files | no tags | |
| describe_file | no tags | |
| read_doc | no tags | |
| download_file | untrusted-input | untrusted-input: keyword "download" |
| copy_file | no tags | |
| move_file | file-write | file-write: keyword "move_file" in tool name |
| rename_file | no tags | |
| create_folder | no tags | |
| trash_file | no tags | |
| untrash_file | no tags | |
| start_drive_cursor | no tags | |
| drive_changes | no tags | |
| upload_file | external-sink | external-sink: keyword "upload_file" |
| editors_api_reference conditional | no tags | |
| get_attachment | untrusted-input | untrusted-input: keyword "fetch" |
| harvest_attachments | no tags | |
| create_draft | no tags | |
| update_draft | no tags | |
| get_draft | no tags | |
| list_drafts | no tags | |
| delete_draft | no tags | |
| send_draft | no tags | |
| list_filters | no tags | |
| create_filter | no tags | |
| delete_filter | no tags | |
| list_history | no tags | |
| list_labels | no tags | |
| create_label | no tags | |
| update_label | no tags | |
| delete_label | no tags | |
| modify_labels | no tags | |
| modify_labels_matching | no tags | |
| trash | no tags | |
| untrash | no tags | |
| mark_spam | no tags | |
| unmark_spam | no tags | |
| reply | no tags | |
| forward | no tags | |
| send_message | external-sink | external-sink: keyword "send_message" |
| sender_breakdown | no tags | |
| search_threads | no tags | |
| get_thread | untrusted-input | untrusted-input: keyword "fetch" |
| get_message | untrusted-input | untrusted-input: keyword "fetch" |
| get_messages | untrusted-input | untrusted-input: keyword "fetch" |
| list_accounts | no tags | |
| health | no tags | |
| list_meetings | no tags | |
| get_transcript | no tags | |
| get_spreadsheet | no tags | |
| get_values | no tags | |
| update_values | no tags | |
| clear_values | no tags | |
| append_values | no tags | |
| batch_update_spreadsheet | no tags | |
| search_developer_metadata | no tags | |
| copy_sheet_to | no tags | |
| link_sheet_cells | no tags | |
| write_range | no tags | |
| format_range | no tags | |
| add_chart | no tags | |
| read_sheet_cells | no tags | |
| list_sheets | no tags | |
| read_rows | no tags | |
| append_rows | no tags | |
| upsert_rows | no tags | |
| create_spreadsheet | no tags | |
| get_presentation | no tags | |
| batch_update_presentation | no tags | |
| create_presentation | no tags | |
| list_layouts | no tags | |
| read_deck | no tags | |
| create_deck_from_outline | no tags | |
| fill_placeholders | no tags | |
| get_thumbnails | no tags | |
| list_task_lists | no tags | |
| list_tasks | no tags | |
| create_task | no tags | |
| update_task | no tags | |
| complete_task | no tags | |
| move_task | no tags | |
| create_task_list | no tags |
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 0.1.0. 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 Google 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.