Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
Mailagent 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
3
downloads a day
local
runs on your machine
66
downloads in 30d
What it does
MailAgent MCP server (stdio) for Cursor and AI agents — email verification inboxes
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mailagent-mcp '--' npx -y --package=@mailagent/mcp mailagent-mcp
# 2 — ask your agent for something these tools do
# mailagent_issue_access, mailagent_plan_next, mailagent_start_run and 34 more
Mailagent costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ALAll 1 server
alex0nder1 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 Mailagent 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 mailagent-mcp '--' npx -y --package=@mailagent/mcp mailagent-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 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
37 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.
Issue a short-lived scoped API key for one autonomous MailAgent run. Requires an unrestricted DB team key.
No parameter schema on file.
Autopilot planner: return the next best MailAgent tool and ready payloads from current signup/login state. Use when unsure what to do next.
No parameter schema on file.
Start a server-side autonomous agent run session and return the first autopilot plan.
No parameter schema on file.
Resume an agent run and return the next best tool/payload from saved session state.
No parameter schema on file.
Report run progress/failure, append a timeline step, update saved state, and return the next plan.
No parameter schema on file.
Workspace Agent preview: summarize supplied mail/thread messages, action items, decisions, and open questions.
No parameter schema on file.
Workspace Agent preview: draft a reply from supplied messages. Draft-only; never sends.
No parameter schema on file.
Workspace Agent preview: suggest reminders/follow-ups from supplied messages. Does not create reminders yet.
No parameter schema on file.
Workspace Agent preview: persist a reminder/follow-up. Does not send email or create calendar events.
No parameter schema on file.
Workspace Agent preview: list saved reminders/follow-ups for the current team or API key.
No parameter schema on file.
Workspace Agent preview: mark a saved reminder/follow-up as completed.
No parameter schema on file.
Workspace Agent preview: log what the agent did for a reminder/thread.
No parameter schema on file.
Workspace Agent preview: list logged Workspace actions, optionally scoped by reminderId or threadId.
No parameter schema on file.
Read the Workspace Agent autonomy policy. Default is draft_only.
No parameter schema on file.
Show DeepSeek/Qwen readiness and fallback order without exposing secrets.
No parameter schema on file.
Admin-only: configure policy-gated autonomous replies.
No parameter schema on file.
Policy-gated autonomous reply from a real inbound message. Use dryRun first; idempotencyKey is required to send.
No parameter schema on file.
Suggest service preset, expectFrom, subjectContains, flow, and snippets from a sample auth email From/Subject/body. Use before verify when sender or service is unclear.
No parameter schema on file.
Create a temporary email inbox for agent workflows (signups, OTP, magic links). Returns inbox id and email address to use on external forms.
No parameter schema on file.
Preferred agent flow: create inbox (or reuse inboxId), wait for verification email, return agent.primaryAction with OTP or magic link and clear instruction. Use service preset (github, google, dribbble, …).
No parameter schema on file.
One-shot agent flow: optionally create inbox, wait via SSE for first allowed email, return OTP + links, delete inbox by default. Use service=dribbble for Dribbble signup.
No parameter schema on file.
List active inboxes by label (QA: debug failed CI run, find address/ids).
No parameter schema on file.
Block until the first email arrives (SSE, fallback poll). Use after submitting a form to the inbox address.
No parameter schema on file.
List all messages received for an inbox (newest first).
No parameter schema on file.
Get OTP code and links from the latest email in the inbox (pre-parsed at ingest). Best after a message arrived.
No parameter schema on file.
Inject test OTP email without SMTP (QA/dev, sim_* provider).
No parameter schema on file.
Send outbound email from inbox (two-way agent mail).
No parameter schema on file.
List threads or messages in a thread.
No parameter schema on file.
When wait/verify fails: messages, callbacks, hints, debugUiUrl, troubleshooting.
No parameter schema on file.
Get inbox status: address, expiry, message count.
No parameter schema on file.
Delete inbox and all messages early (cleanup after verification).
No parameter schema on file.
Delete all inboxes matching a labelPrefix, or an agent run via runId.
No parameter schema on file.
Download archived .eml metadata or body (base64 via API when includeBody). Use when extract finds no OTP.
No parameter schema on file.
Check email syntax, disposable, role, MX (DNS). ONLY for app validation tests — NOT before verify_signup.
No parameter schema on file.
Read multi-step agent run state (JSON + step log) by runId.
No parameter schema on file.
Read normalized agent run timeline events by runId.
No parameter schema on file.
Merge state and/or append a step for multi-step agent flows.
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 Mailagent 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 0.2.16 · scanned 14 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 score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digeste6c61a10cb4095b9137c2aa634c792af764a58c3d14d029ab8816cc1538d47df
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 (37 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 |
|---|---|---|
| mailagent_issue_access | no tags | |
| mailagent_plan_next | no tags | |
| mailagent_start_run | no tags | |
| mailagent_next_run | no tags | |
| mailagent_report_run | no tags | |
| mailagent_workspace_summarize | untrusted-input | untrusted-input: keyword "read_message" |
| mailagent_workspace_draft_reply | no tags | |
| mailagent_workspace_suggest_reminders | no tags | |
| mailagent_workspace_create_reminder | no tags | |
| mailagent_workspace_list_reminders | no tags | |
| mailagent_workspace_complete_reminder | no tags | |
| mailagent_workspace_log_action | no tags | |
| mailagent_workspace_list_actions | no tags | |
| mailagent_workspace_get_policy | no tags | |
| mailagent_workspace_model_status | no tags | |
| mailagent_workspace_set_policy | no tags | |
| mailagent_workspace_execute_reply | no tags | |
| mailagent_suggest_preset | no tags | |
| mailagent_create_inbox | no tags | |
| mailagent_verify_signup | no tags | |
| mailagent_wait_and_extract | no tags | |
| mailagent_list_inboxes | no tags | |
| mailagent_wait_for_message | no tags | |
| mailagent_list_messages | no tags | |
| mailagent_extract_verification | no tags | |
| mailagent_simulate_message | no tags | |
| mailagent_send_message | external-sink | external-sink: keyword "send_message" |
| mailagent_list_threads | no tags | |
| mailagent_diagnose_inbox | no tags | |
| mailagent_get_inbox | no tags | |
| mailagent_delete_inbox | no tags | |
| mailagent_cleanup_inboxes | no tags | |
| mailagent_get_raw_message | untrusted-input | untrusted-input: keyword "download" |
| mailagent_check_email | no tags | |
| mailagent_get_run_session | no tags | |
| mailagent_get_run_timeline | no tags | |
| mailagent_patch_run_session | 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 digeste6c61a10cb4095b9
Scanned2026-10-14
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 0.2.16. Pin a release below and the command asks for exactly that one.
0.2.16
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 Mailagent 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.