Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
Groundmail 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.
96/100
trust score
1k
downloads a day
local
or remote
21
tools declared
What it does
Send transactional email and manage domains, templates, webhooks and suppressions with Groundmail.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GROUNDMAIL_API_KEY=${GROUNDMAIL_API_KEY}' --transport stdio groundmail-mcp '--' npx -y groundmail-mcp
# 2 — ask your agent for something these tools do
# send_email, list_emails, get_email and 18 more
It needs GROUNDMAIL_API_KEY: this reads it from your environment, so export it first.
Groundmail costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GRAll 1 server
Groundmail1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GROUNDMAIL_API_KEY (Groundmail API key (starts with gm_). Create one at https://app.groundmail.dev/api-keys) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx GROUNDMAIL_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GROUNDMAIL_API_KEY=${GROUNDMAIL_API_KEY}' --transport stdio groundmail-mcp '--' npx -y groundmail-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://mcp.groundmail.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http groundmail-mcp https://mcp.groundmail.dev/mcpFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GROUNDMAIL_API_KEY — Groundmail API key (starts with gm_). Create one at https://app.groundmail.dev/api-keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
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.
What you approve
21 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.
Send a transactional email via Groundmail. Provide subject + html/text, or a published template_id / template_alias with optional variables.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Sender address (must match a verified domain or sandbox sender) |
| to | string | yes | Recipient email address |
| subject | string | no | Subject line. Optional when using a published template |
| html | string | no | HTML body. Do not combine with template_id or template_alias |
| text | string | no | Plain-text body. Do not combine with template_id or template_alias |
| reply_to | string | no | Address that replies should go to |
| template_id | string | no | Published template UUID |
| template_alias | string | no | Published template alias |
| variables | object | no | Template variables when using template_id or template_alias |
List recent emails sent from this account.
No parameter schema on file.
Get a single email by public id (msg_…).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Email id (msg_…) |
List sending domains for this account.
No parameter schema on file.
Add a sending domain. DNS must still be applied and verified before production sends.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Domain name (example.com) |
| inbound_enabled | boolean | no | Enable inbound receiving on this domain |
Apply Groundmail DNS records for a domain. Cloudflare and GoDaddy can use credentials stored in the dashboard; GoDaddy also accepts one-time credentials on the request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain name or id of a domain already added to this account (example.com) |
| provider | string | yes | DNS provider that hosts the domain |
| credentials | object | no | Optional inline registrar credentials (GoDaddy api key/secret) |
Verify DNS for a sending domain after records are applied.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain name or id to check (example.com) |
List webhook endpoints for this account.
No parameter schema on file.
Create a webhook endpoint. Returns the endpoint plus a signing secret (shown once).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | HTTPS URL that receives events |
| events | array | no | Optional event types (defaults apply when omitted) |
Delete a webhook endpoint by id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Webhook id (wh_…) |
List suppressed recipient addresses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | no | Optional filter by email |
Add an address to the suppression list.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email address to stop sending to | |
| reason | string | no | Optional note on why the address is suppressed |
Remove a suppression by id or email address.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Suppression id |
| string | no | Email address (alternative to id) |
List email templates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Optional filter by template status |
Get a template by id or alias.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Template id (tpl_…) |
| alias | string | no | Published alias (alternative to id) |
Create a draft email template (html or blocks format).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Template name |
| subject | string | yes | Subject line, may contain {{variables}} |
| format | string | no | Template format (html or blocks) |
| html | string | no | HTML body |
| text | string | no | Plain-text body |
| alias | string | no | Optional short alias to reference the template by instead of its id |
Publish a template, snapshotting an immutable version for sends.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Template id (tpl_…) |
| alias | string | no | Template alias (alternative to id) |
Simulate a webhook event (POST /emails/test) for CI or local webhook testing. Optionally deliver to subscribed endpoints.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| event | string | yes | Webhook event type to simulate |
| email_id | string | no | Optional existing email id (msg_…) |
| deliver | boolean | no | When true (default), enqueue delivery to account webhooks |
Fetch best-effort deliverability metrics for recent sends (7d or 30d window).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| window | string | no | Time window to summarize (default 30d) |
Beta. Import templates, suppressions (bounces, complaints, unsubscribes), sending domains and webhooks from SendGrid, Postmark or Mailgun into Groundmail. Ask the user for their provider API key; it is used for this import only and never stored, so do not write it to a file. Run with dry_run first…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | Provider to import from |
| api_key | string | yes | SendGrid API key, Postmark server API token, or Mailgun private API key (read access is enough) |
| account_api_key | string | no | Postmark only: account API token, needed to import sending domains |
| region | string | no | SendGrid and Mailgun: eu for EU-region accounts (default us) |
| resources | array | no | What to import (default: all four) |
| dry_run | boolean | no | Preview without writing anything |
| cursor | string | no | next_cursor from an import that stopped early, to continue it |
No parameter schema on file.
Free
$0 forever
- 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 Groundmail or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.7.1 · scanned 18 Oct 2026
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.
Threat score100
Client score96
Findings0 threat · 2 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest5af900568842d2c4cfe2bbb99331c88f7fed428c7115967570d530a2f364f4de
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (21 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| send_email | external-sink | external-sink: keyword "send_email", declares readOnlyHint: false, openWorldHint: true |
| list_emails | no tags | |
| get_email | no tags | |
| list_domains | no tags | |
| create_domain | state-write | state-write: declares readOnlyHint: false |
| apply_domain_dns | no tags | |
| verify_domain | no tags | |
| list_webhooks | no tags | |
| create_webhook | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false |
| delete_webhook | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false, destructiveHint: true |
| list_suppressions | no tags | |
| validate_email | no tags | |
| add_suppression | no tags | |
| remove_suppression | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_templates | no tags | |
| get_template | no tags | |
| create_template | state-write | state-write: declares readOnlyHint: false |
| publish_template | no tags | |
| send_test_webhook_event | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true |
| get_deliverability | untrusted-input | untrusted-input: keyword "fetch" |
| import_from_provider | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest5af900568842d2c4
Scanned2026-10-18
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 0.7.1. Pin a release below and the command asks for exactly that one.
0.7.1
18 Oct 2026
latestNo release note was published with this version.
0.6.4
17 Oct 2026
No release note was published with this version.
0.6.3
17 Oct 2026
No release note was published with this version.
0.6.2
undated
- 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.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Groundmail can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.