Name: Missive
Author: usefulapi

Missive MCP

Read email/chat conversations, messages, contacts and teams; draft, send and update threads.

Tool-list grade A Remote · Streamable HTTP No auth needed 19 tools v1.11.1

No reviews yet by usefulapiGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Read email/chat conversations, messages, contacts and teams; draft, send and update threads.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http usefulapi-missive-mcp https://missive.usefulapi.io/mcp

# 2 — ask your agent for something these tools do
#   missive_list_conversations, missive_get_conversation, missive_list_conversation_messages and 16 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

usefulapi334 servers

24 categories

All 334 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

List conversations (email/chat threads). Missive requires EXACTLY ONE mailbox-type filter — one of inbox / assigned / closed / flagged / snoozed / trashed / all / shared_label / team_inbox / team_all / organization. Missive: GET /conversations.

Parameter	Type	Required	Notes
limit	integer	no	Max conversations to return (default 25, max 50).
until	number	no	Unix timestamp cursor — return records older than this (offset-less pagination).
inbox	boolean	no	Conversations in your inbox.
assigned	boolean	no	Conversations assigned to you.
closed	boolean	no	Closed conversations.
flagged	boolean	no	Flagged conversations.
snoozed	boolean	no	Snoozed conversations.
trashed	boolean	no	Trashed conversations.
all	boolean	no	All conversations.
shared_label	string	no	Conversations under a shared label id.
team_inbox	string	no	Conversations in a team's inbox (team id).
team_all	string	no	All of a team's conversations (team id).
organization	string	no	Filter to an organization id.
email	string	no	Filter to conversations involving this email address.
contact_organization	string	no	Filter to a contact organization id.

Get a single conversation by id. Missive: GET /conversations/{id}.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).

List the messages (emails) in a conversation. Missive: GET /conversations/{id}/messages.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).
limit	integer	no	Max messages to return (default 10, max 10).
until	number	no	Unix timestamp cursor — return records older than this (offset-less pagination).

Get a single message, including the full body. Missive: GET /conversations/{conversation_id}/messages/{id}.

Parameter	Type	Required	Notes
conversation_id	string	yes	The conversation id the message belongs to.
id	string	yes	The message id.

List internal comments (team chat) on a conversation. Missive: GET /conversations/{id}/comments.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).
limit	integer	no	Max records to return.
until	number	no	Unix timestamp cursor — return records older than this (offset-less pagination).

List draft messages on a conversation. Missive: GET /conversations/{id}/drafts.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).
limit	integer	no	Max records to return.
until	number	no	Unix timestamp cursor — return records older than this (offset-less pagination).

List posts (integration/app-generated items) on a conversation. Missive: GET /conversations/{id}/posts.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).
limit	integer	no	Max records to return.
until	number	no	Unix timestamp cursor — return records older than this (offset-less pagination).

List contacts in a contact book. Missive: GET /contacts.

Parameter	Type	Required	Notes
contact_book	string	yes	The contact book id to list contacts from (required).
search	string	no	Free-text search over contacts.
order	string	no	Sort order (default "last_name").
limit	integer	no	Max contacts to return (default 50, max 200).
offset	integer	no	Number of records to skip (offset pagination).
modified_since	number	no	Unix timestamp — only contacts modified since.
include_deleted	boolean	no	Include deleted contacts.

Get a single contact by id. Missive: GET /contacts/{id}.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).

List contact books (address books). Missive: GET /contact_books.

Parameter	Type	Required	Notes
limit	integer	no	Max contact books to return (default 50, max 200).
offset	integer	no	Number of records to skip (offset pagination).

List contact groups or organizations within a contact book. Missive: GET /contact_groups.

Parameter	Type	Required	Notes
contact_book	string	yes	The contact book id (required).
kind	string	yes	Which kind to list: "group" or "organization".
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

List teams in the organization(s). Missive: GET /teams.

Parameter	Type	Required	Notes
organization	string	no	Filter to an organization id.
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

List users (team members). Missive: GET /users.

Parameter	Type	Required	Notes
organization	string	no	Filter to an organization id.
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

List shared labels (team-shared folders/tags). Missive: GET /shared_labels.

Parameter	Type	Required	Notes
organization	string	no	Filter to an organization id.
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

List organizations you belong to. Missive: GET /organizations.

Parameter	Type	Required	Notes
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

List canned responses / templates. Missive: GET /responses.

Parameter	Type	Required	Notes
organization	string	no	Filter to an organization id.
limit	integer	no	Max records to return.
offset	integer	no	Number of records to skip (offset pagination).

Create a draft email/message. WARNING: setting send=true SENDS a real email immediately (send_at schedules it) instead of saving a draft. Attach to an existing thread with conversation. Missive: POST /drafts.

Parameter	Type	Required	Notes
body	string	yes	The message body (HTML) — required.
subject	string	no	The subject line.
to_fields	array	no	Recipients ({address, name?}).
cc_fields	array	no	Cc recipients.
bcc_fields	array	no	Bcc recipients.
from_field	object	no	The sender ({address, name?}).
conversation	string	no	Attach the draft to an existing conversation id.
references	array	no	Message-ID references (for threading).
send	boolean	no	If true, SEND the email immediately instead of saving a draft.
send_at	number	no	Unix timestamp to schedule the send.
organization	string	no	Organization id to send from.
add_assignees	array	no	User ids to assign to the conversation.
add_shared_labels	array	no	Shared label ids to apply.

Update a conversation — assign/unassign users, add/remove shared labels, close/reopen, move to inbox, or set subject/color/team. Missive: PATCH /conversations/{id}.

Parameter	Type	Required	Notes
id	string	yes	The resource id (a UUID-like string).
add_assignees	array	no	User ids to assign.
remove_assignees	array	no	User ids to unassign.
add_shared_labels	array	no	Shared label ids to add.
remove_shared_labels	array	no	Shared label ids to remove.
close	boolean	no	Close (archive) the conversation.
reopen	boolean	no	Reopen the conversation.
add_to_inbox	boolean	no	Move the conversation back to the inbox.
subject	string	no	Set the conversation subject.
color	string	no	Set the conversation color.
organization	string	no	Organization id (context for the update).
team	string	no	Team id to move the conversation to.

Create a contact in the given contact book. Missive: POST /contacts.

Parameter	Type	Required	Notes
contact_book	string	yes	The contact book id to create the contact in (required).
first_name	string	no	First name.
last_name	string	no	Last name.
starred	boolean	no	Whether the contact is starred.
infos	array	no	Contact info entries (email/phone/etc. objects).
memberships	array	no	Group/organization membership objects.

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

Nothing here is billable: mcprush charges nothing to install Missive or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.11.1 · scanned 20 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 · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest6b70766abee34dd8ae77474a23b27a728978d7fe0af3135d4a260cc8674cbd29

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
missive_list_conversations	no tags
missive_get_conversation	no tags
missive_list_conversation_messages	no tags
missive_get_message	no tags
missive_list_conversation_comments	no tags
missive_list_conversation_drafts	no tags
missive_list_conversation_posts	no tags
missive_list_contacts	no tags
missive_get_contact	no tags
missive_list_contact_books	no tags
missive_list_contact_groups	no tags
missive_list_teams	no tags
missive_list_users	no tags
missive_list_shared_labels	no tags
missive_list_organizations	no tags
missive_list_responses	no tags
missive_create_draft	state-write	state-write: declares destructiveHint: true
missive_update_conversation	state-write	state-write: declares destructiveHint: true
missive_create_contact	state-write	state-write: declares destructiveHint: true

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 digest6b70766abee34dd8

Scanned2026-10-20

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.

Where are you running it?

Tool surface

Release history

Missive MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also