Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
MailPace 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.
97/100
trust score
416
downloads a day
local
runs on your machine
12
tools declared
What it does
Send transactional email and manage MailPace domains from MCP clients.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mailpace-mcp '--' npx -y @mailpace/mcp
# 2 — ask your agent for something these tools do
# mailpace_send_email, mailpace_get_email_status, mailpace_list_domains and 9 more
MailPace costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MAAll 1 server
mailpace1 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 runs on your machine: your client starts MailPace 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.
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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user mailpace-mcp '--' npx -y @mailpace/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free 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
Nothing is required, but it can take MAILPACE_API_TOKEN (Domain API token for sending email and domain-scoped status lookups.), MAILPACE_ORGANIZATION_TOKEN (Organization API token for domain and domain API token management.), MAILPACE_ALLOWED_RECIPIENTS (Optional comma-separated recipient allowlist of exact addresses or @domain rules.), MAILPACE_REQUEST_TIMEOUT_MS (Optional per-request timeout in milliseconds. Defaults to 30000.), MAILPACE_MAX_RETRIES (Optional retry count for idempotent requests and 429 responses. Defaults to 2.) if you want to set them.
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
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.
Send a transactional email through MailPace. Requires a domain API token.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Sender email address or RFC 822 name & addr-spec, for example 'Name <user@example.com>'. The domain must match the API token. |
| to | string | yes | Recipient address or comma-separated list of recipients (maximum 50 total including cc and bcc) |
| subject | string | no | Email subject |
| htmlbody | string | no | HTML body. Required if textbody is not provided. |
| textbody | string | no | Plain-text body. Required if htmlbody is not provided. |
| cc | string | no | Optional comma-separated CC recipients |
| bcc | string | no | Optional comma-separated BCC recipients |
| replyto | string | no | Optional Reply-To address |
| inreplyto | string | no | Optional In-Reply-To message ID |
| references | string | no | Optional space-separated References message IDs |
| list_unsubscribe | string | no | Optional List-Unsubscribe header value |
| attachments | array | no | Optional attachments. Total email size must not exceed 30 MB. |
| tags | no | Optional tag or list of tags for filtering and analytics | |
| idempotency_key | string | no | Optional unique key (for example a UUIDv4) that prevents sending the same email twice when retrying |
Get the delivery status of an email, including bounce or deferral details.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | ID of the domain the email was sent from |
| id | integer | yes | Email ID returned by mailpace_send_email |
List the domains belonging to your MailPace organization.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| offset | integer | no | — |
| sort | string | no | — |
| direction | string | no | — |
Get a single MailPace domain by ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | The domain ID |
Create a new sending domain in your MailPace organization.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Lower-case domain with TLD, for example example.com |
| name | string | no | Friendly name for your reference |
Update the name or URL of a MailPace domain. Changing the URL may require DNS verification again.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | The domain ID |
| name | string | no | Friendly name for your reference |
| url | string | no | Lower-case domain with TLD, for example example.com |
Check the DKIM and advanced verification DNS records for a MailPace domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | The domain ID |
List the API tokens for a MailPace domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | The domain ID |
Get a single API token for a MailPace domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | The domain ID |
| id | integer | yes | The API token ID |
Create a new API token for a MailPace domain. Store the returned token securely; it may not be shown again.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | The domain ID |
| name | string | no | Friendly token label |
Update the name of an API token for a MailPace domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | The domain ID |
| id | integer | yes | The API token ID |
| name | string | no | Friendly token label |
Revoke an API token for a MailPace domain. This cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain_id | integer | yes | The domain ID |
| id | integer | yes | The API token ID |
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 MailPace 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 97 / 100
Release 2.0.1 · scanned 11 Nov 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 score97
Findings0 threat · 3 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digestda8ca36ac012d7042f896a2bb72fbc7303d4c78c9424a4a9f2cf560f721891f0
Score vectorthreat 100 → client 97
| 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 |
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 (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>".
1 of the 12 recovered tools are registered only when apiToken holds (build/index.js:508) — 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 none of the recovered tools.
1 of the 12 recovered tools are registered only when apiToken || organizationToken holds (build/index.js:547) — 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 none of the recovered tools.
10 of the 12 recovered tools are registered only when organizationToken holds (build/index.js:577) — 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 none of the recovered tools.
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.
No tool is registered unconditionally · (1) 1 only when apiToken holds (build/index.js:508) · (2) 1 only when apiToken || organizationToken holds (build/index.js:547) · (3) 10 only when organizationToken holds (build/index.js:577) — typically when a key or option is configured. All 12 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| mailpace_send_email conditional (1) | external-sink | external-sink: keyword "send_email", declares readOnlyHint: false, openWorldHint: true |
| mailpace_get_email_status conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_list_domains conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_get_domain conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_create_domain conditional (3) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| mailpace_update_domain conditional (3) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| mailpace_verify_domain conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_list_domain_api_tokens conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_get_domain_api_token conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| mailpace_create_domain_api_token conditional (3) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| mailpace_update_domain_api_token conditional (3) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| mailpace_revoke_domain_api_token conditional (3) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestda8ca36ac012d704
Scanned2026-11-11
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 2.0.1. Pin a release below and the command asks for exactly that one.
2.0.1
undated
latestNo release note was published with this version.
—
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 MailPace 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.