Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
Missive 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.
96/100
trust score
12
downloads a day
local
runs on your machine
307
downloads in 30d
What it does
MCP server and CLI for the Missive REST API
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user missive-mcp '--' npx -y missive-mcp
# 2 — ask your agent for something these tools do
# missive_create_analytics_report, missive_get_analytics_report, missive_list_contact_books and 24 more
Missive costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OUAll 1 server
oursky1 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 Missive 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 missive-mcp '--' npx -y missive-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
27 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.
Create an analytics report for an organization over a date range. Returns a report ID to poll.
No parameter schema on file.
Get an analytics report by ID. Poll until status is 'complete'. Reports expire 60 seconds after completion. A 404 response means the report is still generating — keep polling every few seconds.
No parameter schema on file.
List all contact books accessible to the authenticated user.
No parameter schema on file.
List contact groups or organizations within a contact book.
No parameter schema on file.
Create one or more contacts in a contact book.
No parameter schema on file.
Update one or more contacts by ID. When passing infos or memberships arrays, include ALL items — missing items are deleted.
No parameter schema on file.
List contacts in a contact book.
No parameter schema on file.
Get a single contact by ID.
No parameter schema on file.
List conversations. A mailbox filter (inbox, all, assigned, closed, snoozed, flagged, trashed, junked, drafts) OR a label/team filter (shared_label, team_inbox, team_closed, team_all, organization) is REQUIRED — omitting both will result in a 400 error. Optionally combine with one contact filter…
No parameter schema on file.
Get a single conversation by ID. Supports output_format: 'full' (default) or 'summary' for agent-friendly output.
No parameter schema on file.
List messages in a conversation, newest first.
No parameter schema on file.
List comments in a conversation, newest first.
No parameter schema on file.
List drafts in a conversation, newest first.
No parameter schema on file.
List posts in a conversation, newest first.
No parameter schema on file.
Merge a conversation into a target conversation.
No parameter schema on file.
Create a draft message. Set send=true to send immediately, or send_at for scheduled send.
No parameter schema on file.
Create a reply draft to a conversation. Automatically fetches the last message, populates recipients based on mode, and sets quote_previous_message=true. Use mode='reply-all' to include all original recipients.
No parameter schema on file.
Delete a draft by ID.
No parameter schema on file.
Create an inbound message on a custom channel. Not for email/SMS — use missive_create_draft for those.
No parameter schema on file.
Get one or more messages by ID. Supports batch retrieval with comma-separated IDs.
No parameter schema on file.
Find messages by their email Message-ID header. Returns up to 10 matches.
No parameter schema on file.
List all organizations the authenticated user belongs to.
No parameter schema on file.
List response templates.
No parameter schema on file.
Get a single response template by ID.
No parameter schema on file.
Create one or more response templates. Must specify either organization or user.
No parameter schema on file.
Update one or more response templates by ID. Cannot update responses from external integrations. Attachments array must be complete.
No parameter schema on file.
Delete one or more response templates by ID. Cannot delete external integration responses; org responses require admin role.
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 Missive 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 96 / 100
Release 2.0.2 · scanned 13 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 score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest6cb53863daaf9b7de3ec2ff81e2fc745bf24d5ea0a9c347f0a0935a0ca353f0b
Score vectorthreat 100 → client 96
| 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 |
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 (27 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/analytics.js:6) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/analytics.js:30) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/contact-books.js:6) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/contact-groups.js:6) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/contacts.js:32) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/contacts.js:49) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/contacts.js:67) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/contacts.js:89) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:7) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:58) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:81) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:107) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:125) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/conversations.js:143) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/conversations.js:161) — 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 27 recovered tools are registered only when actions.has("write") || actions.has("send") holds (dist/tools/drafts.js:8) — 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 27 recovered tools are registered only when (actions.has("write") || actions.has("send")) && enabled.has("conversations") holds (dist/tools/drafts.js:54) — 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 27 recovered tools are registered only when actions.has("delete") holds (dist/tools/drafts.js:104) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/messages.js:7) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/messages.js:45) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/messages.js:61) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/organizations.js:6) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/responses.js:20) — 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 27 recovered tools are registered only when actions.has("read") holds (dist/tools/responses.js:38) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/responses.js:54) — 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 27 recovered tools are registered only when actions.has("write") holds (dist/tools/responses.js:74) — 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 27 recovered tools are registered only when actions.has("delete") holds (dist/tools/responses.js:92) — 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 actions.has("write") holds (dist/tools/analytics.js:6) · (2) 1 only when actions.has("read") holds (dist/tools/analytics.js:30) · (3) 1 only when actions.has("read") holds (dist/tools/contact-books.js:6) · (4) 1 only when actions.has("read") holds (dist/tools/contact-groups.js:6) · (5) 1 only when actions.has("write") holds (dist/tools/contacts.js:32) · (6) 1 only when actions.has("write") holds (dist/tools/contacts.js:49) · (7) 1 only when actions.has("read") holds (dist/tools/contacts.js:67) · (8) 1 only when actions.has("read") holds (dist/tools/contacts.js:89) · (9) 1 only when actions.has("read") holds (dist/tools/conversations.js:7) · (10) 1 only when actions.has("read") holds (dist/tools/conversations.js:58) · (11) 1 only when actions.has("read") holds (dist/tools/conversations.js:81) · (12) 1 only when actions.has("read") holds (dist/tools/conversations.js:107) · (13) 1 only when actions.has("read") holds (dist/tools/conversations.js:125) · (14) 1 only when actions.has("read") holds (dist/tools/conversations.js:143) · (15) 1 only when actions.has("write") holds (dist/tools/conversations.js:161) · (16) 1 only when actions.has("write") || actions.has("send") holds (dist/tools/drafts.js:8) · (17) 1 only when (actions.has("write") || actions.has("send")) && enabled.has("conversations") holds (dist/tools/drafts.js:54) · (18) 1 only when actions.has("delete") holds (dist/tools/drafts.js:104) · (19) 1 only when actions.has("write") holds (dist/tools/messages.js:7) · (20) 1 only when actions.has("read") holds (dist/tools/messages.js:45) · (21) 1 only when actions.has("read") holds (dist/tools/messages.js:61) · (22) 1 only when actions.has("read") holds (dist/tools/organizations.js:6) · (23) 1 only when actions.has("read") holds (dist/tools/responses.js:20) · (24) 1 only when actions.has("read") holds (dist/tools/responses.js:38) · (25) 1 only when actions.has("write") holds (dist/tools/responses.js:54) · (26) 1 only when actions.has("write") holds (dist/tools/responses.js:74) · (27) 1 only when actions.has("delete") holds (dist/tools/responses.js:92) — typically when a key or option is configured. All 27 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| missive_create_analytics_report conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/analytics/reports") at dist/tools/analytics.js:23 |
| missive_get_analytics_report conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_contact_books conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_contact_groups conditional (4) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_create_contacts conditional (5) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/contacts") at dist/tools/contacts.js:42 |
| missive_update_contacts conditional (6) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP PATCH ( client.patch(path) at dist/tools/contacts.js:60 |
| missive_list_contacts conditional (7) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_get_contact conditional (8) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_conversations conditional (9) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_get_conversation conditional (10) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_conversation_messages conditional (11) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_conversation_comments conditional (12) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_conversation_drafts conditional (13) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_conversation_posts conditional (14) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_merge_conversations conditional (15) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP POST ( client.post(/conversations/${id}/merge) at dist/tools/conversations.js:172 |
| missive_create_draft conditional (16) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/drafts") at dist/tools/drafts.js:47 |
| missive_create_reply_draft conditional (17) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/drafts") at dist/tools/drafts.js:96 |
| missive_delete_draft conditional (18) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP DELETE ( client.delete(/drafts/${id}) at dist/tools/drafts.js:113 |
| missive_create_message conditional (19) | external-sink | external-sink: keyword "sms", declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/messages") at dist/tools/messages.js:38 |
| missive_get_messages conditional (20) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_messages_by_email_id conditional (21) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_organizations conditional (22) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_list_responses conditional (23) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_get_response conditional (24) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| missive_create_responses conditional (25) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST ( client.post("/responses") at dist/tools/responses.js:67 |
| missive_update_responses conditional (26) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP PATCH ( client.patch(path) at dist/tools/responses.js:85 |
| missive_delete_responses conditional (27) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP DELETE ( client.delete(/responses/${ids.join(",")}) at dist/tools/responses.js:101 |
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 digest6cb53863daaf9b7d
Scanned2026-10-13
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 2.0.2. Pin a release below and the command asks for exactly that one.
2.0.2
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 Missive 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.