Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
MepMail 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.
100/100
trust score
14
downloads a day
local
or remote
2k
downloads in 30d
What it does
Transactional email and agent mailboxes: send, broadcasts, domains, Correio inboxes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mepmail-mcp '--' npx -y @mepmail/mcp
# 2 — ask your agent for something these tools do
# list_emails, get_email, get_email_insights and 25 more
MepMail costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user mepmail-mcp '--' npx -y @mepmail/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://api.mepmail.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http mepmail-mcp https://api.mepmail.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
Nothing is required, but it can take MEPMAIL_API_KEY (MepMail API key, for sending email (optional when only Correio is used)), MEPMAIL_MAIL_TOKEN (Correio agent key (mmb_ or mmt_), for mailboxes (optional when only sending)) 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
28 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.
List the team's transactional emails (sent, queued and scheduled), oldest first, with cursor pagination.
No parameter schema on file.
Get one email by id: sender, recipients, subject, body, schedule and delivery status (last_event: queued, sent, delivered, bounced, complained, ...).
No parameter schema on file.
Get the best-practice report for one email, computed when it was sent: per-check results and a 0-10 score. The score measures compliance with sending best practices — it is NOT an inbox-placement probability.
No parameter schema on file.
Get the team's deliverability standing over the trailing 30 days: headline score with band, complaint and hard-bounce rates, and guardrail status. Improve it by fixing per-email failures and list hygiene, never by disabling tracking or stripping content.
No parameter schema on file.
Get the team's plan and quota picture before bulk work: effective plan, send limit, domain and contact limits, emails accepted today (UTC) and, on monthly plans, the billing period picture.
No parameter schema on file.
List the team's sending domains with their verification status.
No parameter schema on file.
Get one sending domain: status, region and required DNS records (DKIM, MAIL FROM).
No parameter schema on file.
List contacts of the team, oldest first, with cursor pagination. Pass segment_id to list only that segment's members.
No parameter schema on file.
Get one contact by id or email, including custom properties and global unsubscribe state.
No parameter schema on file.
List broadcasts with their status (draft, scheduled, sending, sent).
No parameter schema on file.
Get one broadcast: audience, content, schedule and status.
No parameter schema on file.
List the team's templates (name, id, publication status).
No parameter schema on file.
Get one template: name, subject, html and variables.
No parameter schema on file.
List the team's webhooks (endpoint, subscribed events, status).
No parameter schema on file.
List suppressed addresses — bounces, complaints and manual blocks that every send skips — oldest first, with cursor pagination.
No parameter schema on file.
Send a transactional email (or schedule it with scheduled_at). Suppressed and topic-opted-out recipients are skipped automatically. Returns the email id.
No parameter schema on file.
Send up to 100 emails in one call; each entry has the same shape as send_email. Returns one id per accepted email.
No parameter schema on file.
Reschedule a scheduled email that has not been sent yet.
No parameter schema on file.
Cancel a scheduled email before it is sent.
No parameter schema on file.
Create a contact in the team audience, optionally placing it in segments and setting topic subscriptions. Fails with 409 if the email already exists.
No parameter schema on file.
Update a contact's name, custom properties or global unsubscribe flag. Omitted fields are left unchanged.
No parameter schema on file.
Delete a contact and its segment memberships; its emails stay in the log. Pass erase=true to also scrub the address from email history (GDPR/LGPD). This cannot be undone.
No parameter schema on file.
No parameter schema on file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| folder | string | no | Which folder to list |
| mailbox | string | no | Mailbox address (or id) from mailbox_list_accounts. Needed when the credential covers several mailboxes and has no default. |
| limit | integer | no | Messages per page: default 50 (25 when searching), at most 100 (50 when searching) |
| cursor | string | no | nextCursor from the previous page of this same listing |
| query | string | no | Search words, quoted phrases and operators |
| from | string | no | Sender address, domain or name words |
| subject | string | no | Words of the subject |
| unread | boolean | no | Only received messages the mailbox owner has not opened yet |
| after | string | no | Only messages from this day (YYYY-MM-DD) or ISO time on |
| before | string | no | Only messages before this day (YYYY-MM-DD) or ISO time |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Message id from mailbox_list_messages |
| mailbox | string | no | Mailbox address (or id) from mailbox_list_accounts. Needed when the credential covers several mailboxes and has no default. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Message id |
| revision | integer | yes | The message's revision from mailbox_read_message |
| index | integer | yes | Attachment index from mailbox_read_message |
| mailbox | string | no | Mailbox address (or id) from mailbox_list_accounts. Needed when the credential covers several mailboxes and has no default. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | array | yes | Recipient addresses |
| cc | array | no | Copy (Cc) addresses |
| bcc | array | no | Blind copy (Bcc) addresses: they receive the message, and no other recipient sees them; To, Cc and Bcc together count up to 20 |
| subject | string | yes | Subject line, one line |
| text | string | yes | Plain-text body |
| expected_revision | integer | no | 0 for a new draft; the draft's current revision when editing |
| id | string | no | Draft id, when editing an existing draft |
| source_item_id | string | no | Received message this draft replies to or forwards |
| mode | string | no | With source_item_id |
| attachments | array | no | — |
| keep_attachments | array | no | Attachment indexes to keep from the edited draft or forwarded message |
| mailbox | string | no | Mailbox address (or id) from mailbox_list_accounts. Needed when the credential covers several mailboxes and has no default. |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Draft id |
| expected_revision | integer | yes | The draft's current revision |
| mailbox | string | no | Mailbox address (or id) from mailbox_list_accounts. Needed when the credential covers several mailboxes and has no default. |
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 MepMail 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 100 / 100
Release 0.3.2 · scanned 16 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 score100
Findings1 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest23f696a124b18132f5886c535849755d22fe71bd7b2ecdff844f09220c9b2357
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest23f696a124b18132
Scanned2026-10-16
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 0.3.2. Pin a release below and the command asks for exactly that one.
0.3.2
16 Oct 2026
latestNo release note was published with this version.
0.3.1
13 Oct 2026
No release note was published with this version.
0.2.1
9 Oct 2026
No 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 MepMail 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.