Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
email59 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.
93/100
tool-list score
20
tools declared
remote
at its publisher
—
calls last 7d
What it does
Send transactional email from AI agents: sign up by email code, no domain or DNS setup.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http email59-mcp https://email59.com/v1/mcp
# 2 — ask your agent for something these tools do
# auth, get_pricing, get_account and 17 more
email59 costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
EMAll 1 server
email591 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http email59-mcp https://email59.com/v1/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 Authorization header (Bearer key from the auth tool (optional for auth, check_email, get_pricing)) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
20 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.
Sign up or sign in to email59. Pass email to have a 6-digit code emailed, then call again with email and otp to get a session key (a new email is signed up with 200 free emails a day). Or pass api_key to swap an API key for a session key. Send the key as the HTTP header 'Authorization: Bearer <session_key>'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | no | Email address. | |
| otp | string | no | The 6-digit code from the email. |
| api_key | string | no | An e59_live_ API key, instead of email. |
Free daily emails (renewed every day), email credits per dollar, and the packs on sale. No sign-in needed.
No parameter schema on file.
The signed-in account: email, daily_limit, sent_today, remaining_today, credits_remaining, resets_at.
No parameter schema on file.
Set the name, company or brand (the look of every email the account sends) on the account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | — |
| company | string | no | — |
| brand | object | no | name (header band), color (#rrggbb), logo_url and url (https), address (footer line). An empty name clears it. |
Send one email to one recipient: transactional (receipt, code, alert) or marketing (category). It goes out as HTML in a branded template with a text part; give text, html or both. Uses 1 email of today's allowance. Many recipients at once: send_campaign.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | no | Name before the @ (e.g. hello). The domain is always email59.com. Optional. |
| to | string | yes | Recipient address. |
| subject | string | yes | — |
| text | string | no | Plain-text body. Give text, html or both. |
| html | string | no | HTML body. |
| reply_to | string | no | Optional. One address of your own (not at email59.com) where answers should go. Without it the email says replies are not received. |
| category | string | no | Default transactional. marketing: always has the unsubscribe link and skips role addresses and people who unsubscribed. |
| list_id | string | no | Marketing only: your name for the audience. |
| template | string | no | Layout. basic (default), code (one-time code, give code), notice (heading and one button), report (wide tables), letter (personal). |
| heading | string | no | — |
| preheader | string | no | Preview text shown after the subject. |
| button_text | string | no | — |
| button_url | string | no | — |
| code | string | no | The code for template code. |
| brand | object | no | This email's look; the account's brand otherwise. |
Send a marketing email to up to 1,000 recipients; the unsubscribe link is added for you. Invalid, role, blocked or unsubscribed recipients are skipped and cost nothing; each accepted recipient uses 1 email of today's allowance. A campaign that doesn't fit what's left today is refused whole.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | no | Name before the @ (e.g. hello). The domain is always email59.com. Optional. |
| subject | string | yes | — |
| html | string | no | — |
| text | string | no | — |
| list_id | string | no | Your name for this audience, used for unsubscribes. |
| recipients | array | yes | Recipient addresses (max 1,000). |
Free deep check of an email address, no sign-in needed: format, provider username rules, disposable and role addresses, and the domain's MX, SPF, DMARC, DKIM, MTA-STS, TLS-RPT and BIMI records. Returns a report with a score (0-99, likelihood the address is real) and a verdict (likely_valid, risky, likely_invalid, unknown). Gmail, Outlook and other big providers skip DNS. No email is sent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email address. |
List check for a mailing list: up to 1,000 different addresses a call, as emails or the text of a CSV (the column headed email). One status each: valid, risky, role, disposable, no_mx or invalid, with a reason, plus counts per status. Format, provider rules and one MX lookup per domain; no email is sent. Daily limit per account; the answer's quota shows what is left today.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | no | Addresses to check. |
| csv | string | no | Or a CSV file's text with an email column. |
Check an address before sending. Verdicts: ok, invalid, no_mx, disposable, role.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email address. |
Block an email address or a whole domain for this account. Sends to it are refused.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | — |
| value | string | yes | The address or domain. |
| reason | string | no | — |
Remove an email address or domain from the blocklist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | — |
| value | string | yes | — |
The account's blocked addresses and domains.
No parameter schema on file.
Record an opt-out. Campaigns to that list (or every list, if list_id is empty) skip the address.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email address. | |
| list_id | string | no | Empty = every list. |
Start buying a pack (pack_5 = $5, pack_10 = $10, pack_50 = $50; each $1 adds 3,636 email credits, which don't renew and last until used, plus a purchase fee of 5% or at least $0.50 at checkout; GET /v1/pricing has the totals). Returns a checkout_url for a person to pay; the credits arrive once the payment clears. First show the person the refund policy and terms from GET /v1/policy; pass agree=tru
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pack_id | string | yes | — |
| agree | boolean | yes | The person agreed to the refund policy and terms (GET /v1/policy) |
| policy_version | string | yes | version from GET /v1/policy |
Status of an order from buy_pack: pending or paid.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | integer | yes | — |
Create a long-lived API key (max 10 per account). It is shown only once. mode 'test' makes an e59_test_ key for staging and CI: its sends are accepted and stored, never delivered, and use no allowance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| label | string | no | — |
| mode | string | no | Default live. |
Emails sent with a test key (e59_test_...), newest first: accepted, stored, never delivered. Pass id for one email with its html and text (a verify_start code is in there), or to to filter by recipient.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | A test email id (test_...). Optional. |
| to | string | no | Only emails to this address. Optional. |
| limit | integer | no | Default 50, at most 100. |
The account's API keys (ids and labels, never the keys themselves).
No parameter schema on file.
Email a one-time verification code to an address (sign-up, sign-in, confirming an email). email59 makes the code, sends it, limits resends and expires it; the code is never returned to you. Returns an id. Uses 1 email of today's allowance. A new code to the same address replaces the one waiting there. Then call verify_check with what the person typed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | The address to verify. |
| app_name | string | no | Your app's name, shown in the subject and body. Optional. |
| from | string | no | Name before the @; the domain is always email59.com. Default verify. |
| code_length | integer | no | Digits in the code, 4 to 10. Default 6. |
| expires_in | integer | no | Seconds the code works, 60 to 3600. Default 600. |
Check a code from verify_start. Give to (checks the newest code sent there) or id, and code. Returns valid true or false and a status: approved, wrong_code, expired, too_many_attempts (5 wrong codes lock it), already_used, replaced or not_found. A right code works once. Uses no allowance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | no | The address the code was sent to. |
| id | string | no | Or the id from verify_start. |
| code | string | yes | The code the person typed. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 email59 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: —
ATool-list grade · score 93 / 100
Release 0.5.0 · scanned 25 Oct 2026
Graded from the tools this server lists, not from its source code.
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 score93
Findings0 threat · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest0061808772c1e161eadb45cb30b636952866c2a32017deb5e4d28b64790a39c7
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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 |
|---|---|---|
| auth | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_pricing | no tags | |
| get_account | no tags | |
| update_account | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| send_email | external-sink | external-sink: keyword "send_email", declares readOnlyHint: false, openWorldHint: true |
| send_campaign | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| check_email | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| check_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| validate_email | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| block | state-write | state-write: declares readOnlyHint: false |
| unblock | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_blocklist | no tags | |
| add_unsubscribe | state-write | state-write: declares readOnlyHint: false |
| buy_pack | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| order_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_api_key | state-write | state-write: declares readOnlyHint: false |
| list_test_messages | no tags | |
| list_api_keys | no tags | |
| verify_start | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| verify_check | state-write | state-write: declares readOnlyHint: false |
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 digest0061808772c1e161
Scanned2026-10-25
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.5.0.
0.5.0
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 email59 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.