Community Gmail server with auto-auth: search, read and send email via MCP.
Naver Mail 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
Read, search, reply to and organize Naver Mail with the same tools as the Gmail MCP (IMAP/SMTP).
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'NAVER_ID=${NAVER_ID}' --env 'NAVER_APP_PASSWORD=${NAVER_APP_PASSWORD}' --transport stdio naver-mail-mcp '--' npx -y naver-mail-mcp
# 2 — ask your agent for something these tools do
# get_profile, search_threads, get_thread and 27 more
It needs NAVER_ID, NAVER_APP_PASSWORD: this reads them from your environment, so export them first. Remote: OAuth sign-in · Package: API key.
Naver Mail 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 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.
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 NAVER_ID (Naver ID (without @naver.com)), NAVER_APP_PASSWORD (Naver app password (2-step verification required)) 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 NAVER_ID …, setx NAVER_APP_PASSWORD … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'NAVER_ID=${NAVER_ID}' --env 'NAVER_APP_PASSWORD=${NAVER_APP_PASSWORD}' --transport stdio naver-mail-mcp '--' npx -y naver-mail-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://naver-mail-mcp.yeonuunim521.workers.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http naver-mail-mcp https://naver-mail-mcp.yeonuunim521.workers.dev/mcpIt reaches a system of yours, so it needs your own credential rather than the publisher’s: NAVER_ID — Naver ID (without @naver.com); NAVER_APP_PASSWORD — Naver app password (2-step verification required). 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.
30 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.
Returns the connected Naver Mail address, total messages and unread count in the inbox. Use it to confirm which account is connected.
No parameter schema on file.
IMPORTANT: results are previews (up to 5 messages per thread, from this page only). Never answer questions about the latest or unread email from previews alone; call get_thread to read relevant threads in full.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| pageSize | integer | no | Max messages to return (grouped into threads). Default 20, max 50. |
| pageToken | string | no | nextPageToken from a previous call. |
| includeTrash | boolean | no | Include messages in Trash. Default false. |
| view | string | no | THREAD_VIEW_MINIMAL (default) includes subject and snippet; THREAD_VIEW_METADATA_ONLY excludes them. |
Retrieves an email thread (conversation) with all its messages, oldest first, across folders (inbox, sent, user folders). Drafts are omitted. Threads are reconstructed from Message-ID/References headers. Use PLAIN_TEXT to save context.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | Thread id from search_threads. |
| messageFormat | string | no | — |
Retrieves a single email message by id, including body and attachment metadata. For whole conversations use get_thread. Use PLAIN_TEXT to prevent context exhaustion.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | Message id from search_threads or get_thread. |
| messageFormat | string | no | — |
Downloads one attachment of a message. Returns text for text-like files (txt, csv, html, json, ics) and base64 data (up to 8MB).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| attachmentId | string | yes | attachmentId from get_message (zero-based index). |
Lists labels with message and unread counts. In Naver Mail labels are folders: system labels INBOX, SENT, DRAFT, TRASH, SPAM map to the matching folders; user labels are folder paths. STARRED (important mark) and UNREAD are flags. Use the returned id with label tools.
No parameter schema on file.
Creates a new user label (a Naver Mail folder). Nested labels use '/', e.g. 'Projects/Alpha'; missing parents are created.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| displayName | string | yes | Label name, e.g. 'Receipts' or 'Projects/Alpha'. |
Renames a user label (folder).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| labelId | string | yes | User label id from list_labels. |
| displayName | string | yes | New name. |
Deletes a user label. WARNING: in Naver Mail a label is a folder, so the messages inside it are deleted too. Confirm with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| labelId | string | yes | User label id from list_labels. |
Adds labels to a message: STARRED marks important, UNREAD marks unread, a folder label moves it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| labelIds | array | yes | — |
Removes labels from a message, e.g. remove UNREAD to mark as read, STARRED to unstar.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| labelIds | array | yes | — |
Adds and/or removes labels on a message in one call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| addLabelIds | array | no | — |
| removeLabelIds | array | no | — |
Adds labels to every message in a thread (e.g. STARRED, or a folder label to move the conversation).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
| labelIds | array | yes | — |
Removes labels from every message in a thread, e.g. remove UNREAD to mark the whole conversation as read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
| labelIds | array | yes | — |
Moves a message to Trash (soft delete). Default tool when the user asks to delete a message without asking for permanent deletion.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
Moves every message of a thread to Trash (soft delete).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
Moves a message out of Trash (to Sent if you sent it, otherwise Inbox).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
Moves the messages of a thread out of Trash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
Moves a message to the Spam folder.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
Moves every message of a thread to the Spam folder.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
Moves a message out of Spam back to the Inbox.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
Moves the messages of a thread out of Spam.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threadId | string | yes | — |
Sends an email immediately from the Naver Mail account (SMTP) and saves a copy in Sent. To send an existing draft, give draftId. To thread under an existing conversation give replyThreadId or replyToMessageId. Confirm recipients and content with the user before sending.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | yes | — | |
| cc | yes | — | |
| bcc | yes | — | |
| subject | string | no | — |
| body | string | no | Plain text body. Do NOT format with Markdown; use htmlBody for rich text. If htmlBody is also given, this is the plain-text alternative. |
| htmlBody | string | no | HTML body (valid HTML tags). |
| attachments | array | no | Attachments. Combined size must not exceed 25MB. |
| draftId | string | no | Send this draft as is; other fields are ignored. The draft is removed after sending. |
| replyToMessageId | string | no | Thread the message as a reply to this message. |
| replyThreadId | string | no | Thread the message under this thread (replies to its latest message). |
Replies to a message (to the sender, or everyone with replyAll). The original is quoted below the reply and threading headers are set. To reply in a thread, use the id of its latest message from get_thread. body or htmlBody is required. Confirm with the user before sending.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| body | string | no | Plain text body. Do NOT format with Markdown; use htmlBody for rich text. If htmlBody is also given, this is the plain-text alternative. |
| htmlBody | string | no | HTML body (valid HTML tags). |
| replyAll | boolean | no | Reply to all recipients. Default false. |
| to | yes | — | |
| cc | yes | — | |
| bcc | yes | — | |
| attachments | array | no | Attachments. Combined size must not exceed 25MB. |
Forwards a message with its original attachments. Optional comments go above the forwarded message via forwardText (plain) or htmlBody. Confirm with the user before sending.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| messageId | string | yes | — |
| to | yes | — | |
| cc | yes | — | |
| bcc | yes | — | |
| forwardText | string | no | Plain text comments above the forwarded message. No Markdown. |
| htmlBody | string | no | HTML comments above the forwarded message. |
| attachments | array | no | Extra attachments in addition to the original ones (25MB total). |
Creates a draft in the Naver Mail drafts folder (임시보관함). If replyToMessageId is given, threading headers are set and the original message is quoted below the body; recipients default to the original sender. Returns the draft id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | yes | — | |
| cc | yes | — | |
| bcc | yes | — | |
| subject | string | no | — |
| body | string | no | Plain text body. Do NOT format with Markdown; use htmlBody for rich text. If htmlBody is also given, this is the plain-text alternative. |
| htmlBody | string | no | HTML body (valid HTML tags). |
| attachments | array | no | Attachments. Combined size must not exceed 25MB. |
| replyToMessageId | string | no | — |
Updates a draft with merge semantics: given (non-empty) fields overwrite, omitted fields are kept. If only body is given the HTML body is cleared. WARNING: attachments are NOT merged; re-provide them or they are removed. The draft id changes (returned).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| draftId | string | yes | — |
| to | yes | — | |
| cc | yes | — | |
| bcc | yes | — | |
| subject | string | no | — |
| body | string | no | Plain text body. Do NOT format with Markdown; use htmlBody for rich text. If htmlBody is also given, this is the plain-text alternative. |
| htmlBody | string | no | HTML body (valid HTML tags). |
| attachments | array | no | Attachments. Combined size must not exceed 25MB. |
Deletes a draft.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| draftId | string | yes | — |
Lists drafts, optionally filtered by a query (same syntax as search_threads).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| pageSize | integer | no | Default 20, max 50. |
| pageToken | string | no | — |
| view | string | no | DRAFT_VIEW_FULL adds subject and plaintextBody. |
Retrieves a draft by id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| draftId | string | yes | — |
| messageFormat | string | no | — |
- 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 Naver Mail 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 | 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 |
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 (30 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 |
|---|---|---|
| get_profile | no tags | |
| search_threads | untrusted-input | untrusted-input: keyword "read_email" |
| get_thread | no tags | |
| get_message | no tags | |
| get_attachment | no tags | |
| list_labels | no tags | |
| create_label | state-write | state-write: declares readOnlyHint: false |
| update_label | state-write | state-write: declares readOnlyHint: false |
| delete_label | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| label_message | state-write | state-write: declares readOnlyHint: false |
| unlabel_message | state-write | state-write: declares readOnlyHint: false |
| update_message_labels | state-write | state-write: declares readOnlyHint: false |
| label_thread | state-write | state-write: declares readOnlyHint: false |
| unlabel_thread | state-write | state-write: declares readOnlyHint: false |
| trash_message | state-write | state-write: declares readOnlyHint: false |
| trash_thread | state-write | state-write: declares readOnlyHint: false |
| untrash_message | state-write | state-write: declares readOnlyHint: false |
| untrash_thread | state-write | state-write: declares readOnlyHint: false |
| mark_message_spam | state-write | state-write: declares readOnlyHint: false |
| mark_thread_spam | state-write | state-write: declares readOnlyHint: false |
| unmark_message_spam | state-write | state-write: declares readOnlyHint: false |
| unmark_thread_spam | state-write | state-write: declares readOnlyHint: false |
| send_message | external-sink | external-sink: keyword "send_message", declares readOnlyHint: false, openWorldHint: true |
| reply | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| forward | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_draft | state-write | state-write: declares readOnlyHint: false |
| update_draft | state-write | state-write: declares readOnlyHint: false |
| delete_draft | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_drafts | no tags | |
| get_draft | 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 0.1.3. 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 Naver Mail 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.