# MisarMail MCP Server (remote · api.misar.io)

Send transactional email, run campaigns, manage contacts and automations, audit deliverability.

- Trust score: 81/100 (high trust)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-26

## Components

- remote · `api.misar.io`: 81/100 (this document), [markdown](https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp.md), [page](https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp)
- npm · `@misarmail/mcp`: 76/100, [markdown](https://verifymcp.io/servers/misar-ai-misarmail-mcp/misarmail-mcp.md), [page](https://verifymcp.io/servers/misar-ai-misarmail-mcp/misarmail-mcp)

## Channel facts

- Endpoint: `https://api.misar.io/mail/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `5.1.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-26.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 89/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 5802 tokens (~100/item across 58 items; 54 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the MisarMail MCP Server server?

MisarMail MCP Server is a hosted endpoint at https://api.misar.io/mail/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http misar-ai-misarmail-mcp 'https://api.misar.io/mail/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "misar-ai-misarmail-mcp": {
      "url": "https://api.misar.io/mail/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "misar-ai-misarmail-mcp": {
      "type": "http",
      "url": "https://api.misar.io/mail/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.misar-ai-misarmail-mcp]
url = "https://api.misar.io/mail/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "misar-ai-misarmail-mcp": {
      "type": "remote",
      "url": "https://api.misar.io/mail/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add misar-ai-misarmail-mcp --url 'https://api.misar.io/mail/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  misar-ai-misarmail-mcp:
    url: "https://api.misar.io/mail/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "misar-ai-misarmail-mcp": {
      "Transport": "http",
      "Url": "https://api.misar.io/mail/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add misar-ai-misarmail-mcp -t streamable-http -u 'https://api.misar.io/mail/mcp'
```

### Other

```json
{
  "mcpServers": {
    "misar-ai-misarmail-mcp": {
      "type": "http",
      "url": "https://api.misar.io/mail/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-26 (score 81, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-24 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-22 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-20 (score 77, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-19 (score 76)

First indexed and scored.

## MCP tools (54)

### `send_email` (~251 tokens)

Send a transactional email from a verified MisarMail account. `from.email` must match an email account you have already verified — use list_domains to check which sender domains are available. Returns the message ID and queue status.

Input parameters:

- `alias_id` (string): Route via a specific alias SMTP pool
- `bcc` (array): BCC recipients (max 50, hidden from other recipients)
- `cc` (array): CC recipients (max 50)
- `from` (object, required): Sender address (must match a verified MisarMail account)
- `html` (string): HTML body (max 500KB, recommended)
- `idempotency_key` (string): Unique key to prevent duplicate sends (max 128 chars)
- `metadata` (object): Custom metadata key-value pairs (max 20 pairs)
- `reply_to` (object): Reply-to address
- `subject` (string, required): Email subject (max 998 chars)
- `tags` (array): Tags for tracking (max 10, each max 64 chars)
- `text` (string): Plain text body (max 500KB, fallback for HTML)
- `to` (array, required): Recipient list (1–100 addresses)

### `list_emails` (~88 tokens)

List emails from a mailbox folder with optional full-text search across subject and body. Use this for reading the unified inbox; use list_campaigns for marketing sends.

Input parameters:

- `folder` (string): Folder to list (default: inbox)
- `limit` (number): Number of emails to return (default 20, max 50)
- `search` (string): Search query across subject and body

### `get_email` (~48 tokens)

Read the full content of a single email by ID, including headers, body, and attachments metadata. Side effect: marks the email as read.

Input parameters:

- `id` (string, required): Email ID (UUID)

### `reply_to_email` (~72 tokens)

Reply to an existing email thread. The sender address and threading headers are derived from the original message, so only the body is required.

Input parameters:

- `email_id` (string, required): ID of the email to reply to
- `html` (string): HTML reply body
- `text` (string): Plain text reply body

### `archive_email` (~121 tokens)

Move one email out of the inbox and into the archive. 

Use it to clear handled mail from the working inbox. This is REVERSIBLE and non-destructive: the message is not deleted, its content is unchanged, and it can be found again through the archive. It does not mark the message read, reply to it, or notify the sender. 

Safe to repeat — archiving an already-archived email changes nothing. Requires an API key. Affects exactly one message per call.

Input parameters:

- `id` (string, required): Email ID to archive

### `validate_email` (~48 tokens)

Validate an email address before sending: syntax, MX records, disposable-domain and role-account detection. Use this to protect sender reputation on imported lists.

Input parameters:

- `email` (string, required): Email address to validate

### `list_campaigns` (~80 tokens)

List email marketing campaigns with their status, audience size, and headline metrics. Filter by status to find drafts ready to send or campaigns still sending.

Input parameters:

- `limit` (number): Results per page (default 20, max 100)
- `page` (number): Page number (default 1)
- `status` (string): Filter by campaign status

### `get_campaign` (~48 tokens)

Get full details for one campaign: content, audience segment, schedule, and delivery statistics (sent, opened, clicked, bounced, complained).

Input parameters:

- `campaign_id` (string, required): Campaign ID (UUID)

### `create_campaign` (~178 tokens)

Create a new email marketing campaign as a draft. Creating never sends — call send_campaign separately once the content and audience are confirmed.

Input parameters:

- `from_email` (string, required): Verified sender address
- `from_name` (string): Sender display name
- `html` (string): HTML body content
- `name` (string, required): Internal campaign name (not shown to recipients)
- `reply_to` (string): Reply-to address
- `scheduled_at` (string): ISO 8601 timestamp to schedule the send (omit to keep as draft)
- `segment_id` (string): Audience segment to send to
- `subject` (string, required): Subject line recipients will see
- `tags` (array): Contact tags to target
- `template_id` (string): Use a saved template instead of inline HTML
- `text` (string): Plain text body content

### `send_campaign` (~79 tokens)

Send a campaign now, or schedule it for a future time by passing scheduled_at. This delivers real email to real recipients and cannot be undone once sending starts — confirm the audience with get_campaign first.

Input parameters:

- `campaign_id` (string, required): Campaign ID (UUID)
- `scheduled_at` (string): ISO 8601 timestamp to schedule instead of sending immediately

### `list_contacts` (~92 tokens)

List contacts with their subscription status and engagement metrics. Filter by status to find unsubscribed or bounced addresses that should be excluded from sends.

Input parameters:

- `limit` (number): Results per page (default 20, max 100)
- `page` (number): Page number (default 1)
- `search` (string): Search across email, name, and company
- `status` (string): Filter by subscription status

### `create_contact` (~168 tokens)

Add a single contact. Adding a contact records consent to email them — only add addresses that opted in, or the send will damage sender reputation and may breach CAN-SPAM/GDPR.

Input parameters:

- `company` (string): Company name (max 150 chars)
- `custom_fields` (object): Custom key-value attributes
- `email` (string, required): Contact email address
- `first_name` (string): First name (max 100 chars)
- `job_title` (string): Job title (max 100 chars)
- `last_name` (string): Last name (max 100 chars)
- `phone` (string): Phone number (max 50 chars)
- `source` (string): Where this contact came from (max 100 chars)
- `tags` (array): Segmentation tags

### `update_contact` (~128 tokens)

Update an existing contact by email address, including changing subscription status. Setting status to unsubscribed immediately excludes them from every future campaign.

Input parameters:

- `company` (string): Company name
- `custom_fields` (object): Custom key-value attributes to merge
- `email` (string, required): Email address identifying the contact
- `first_name` (string): First name
- `job_title` (string): Job title
- `last_name` (string): Last name
- `phone` (string): Phone number
- `status` (string): New subscription status
- `tags` (array): Replace segmentation tags

### `import_contacts` (~75 tokens)

Bulk-import up to 5,000 contacts in one call. Existing addresses are updated rather than duplicated. Returns per-row results so you can see which rows were rejected and why.

Input parameters:

- `contacts` (array, required): Contacts to import (max 5000)
- `update_existing` (boolean): Update contacts that already exist (default true)

### `get_contact_score` (~67 tokens)

Get engagement score, engagement tier, and churn risk for one contact — or the lowest-engagement contacts across the list when contact_id is omitted. Use before a re-engagement campaign.

Input parameters:

- `contact_id` (string): Contact ID to score (omit to return the lowest-engagement contacts)

### `list_templates` (~152 tokens)

List the saved email templates on the account, with the variable placeholders each one expects. 

Use it to pick a template before composing a send, and to see which variables you must supply — a template rendered with a missing variable goes out with a visible gap. These are the account's own templates; list_marketplace_items covers third-party ones instead. 

Reads only; no template is created, edited, or sent. Requires an API key. An empty list means none have been saved yet, which is not an error.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)
- `type` (string): Filter by template type

### `create_template` (~111 tokens)

Create a reusable email template. Use {{variable}} placeholders for personalisation — they are substituted at send time and previewable via render_template.

Input parameters:

- `html` (string, required): HTML body (supports {{variables}})
- `name` (string, required): Template name
- `subject` (string, required): Default subject line (supports {{variables}})
- `text` (string): Plain text fallback body
- `type` (string): Template type (default: marketing)
- `variables` (array): Declared variable names used in the template

### `render_template` (~67 tokens)

Render a template with sample variables and return the resulting HTML and subject. Use this to preview personalisation before sending anything.

Input parameters:

- `template_id` (string, required): Template ID to render
- `variables` (object): Variable values to substitute, e.g. { "first_name": "Ada" }

### `list_automations` (~157 tokens)

List automation workflows on the account — welcome series, re-engagement, drip sequences — with their status and enrolment counts. 

Use it to see what is running before adding another workflow that might overlap, and to find an automation id for get_automation or toggle_automation. Listing does not reveal the individual steps; get_automation does that. 

Reads only; nothing is activated, paused, or enrolled. Requires an API key. An automation may exist while inactive, so read the status rather than assuming a listed workflow is sending.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)
- `status` (string): Filter by automation status

### `get_automation` (~137 tokens)

Get one automation workflow in full: its trigger, every step with its settings, and current enrolment counts. 

Use it to understand exactly what an automation will do to contacts before activating it — the step list is where sends, waits and branches become visible. For the list of automations, use list_automations; to start or pause one, toggle_automation. 

Reads only; reading a workflow does not enrol anyone or trigger a step. Requires an API key. An automation can be defined but inactive, so check its state rather than assuming it is running.

Input parameters:

- `automation_id` (string, required): Automation ID (UUID)

### `create_automation` (~109 tokens)

Create an automation workflow from a trigger and an ordered list of steps. Created paused by default — call toggle_automation to activate once the steps are reviewed.

Input parameters:

- `active` (boolean): Start active immediately (default false)
- `name` (string, required): Automation name
- `steps` (array): Ordered workflow steps
- `trigger` (string, required): Event that starts the workflow
- `trigger_config` (object): Trigger parameters, e.g. { "tag": "trial" } for tag_added

### `toggle_automation` (~129 tokens)

Activate or pause one automation workflow. 

This is consequential in one direction: ACTIVATING starts enrolling contacts, which means real emails begin going out on the workflow's schedule without further confirmation. Pausing stops new enrolments. Read the workflow with get_automation first so you know what activating will actually send. 

Contacts already part-way through a paused workflow are held rather than dropped, so pausing is not a cancellation. Safe to repeat. Requires an API key.

Input parameters:

- `active` (boolean, required): true to activate, false to pause
- `automation_id` (string, required): Automation ID (UUID)

### `list_ab_tests` (~158 tokens)

List A/B tests on the account with each variant's results and whether a winner has been picked yet. 

Use it to see which tests are still running and which are waiting on a decision. Reading results here is safe and has no effect on the test — declaring a winner is a separate, irreversible action that sends to the held-back audience. 

Reads only. Requires an API key. A test with no winner selected is still open; treat early results with care, since a lead that looks decisive on a small sample often is not.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)
- `type` (string): Filter by what is being tested

### `create_ab_test` (~111 tokens)

Create an A/B test on a campaign with two or more variants. A sample percentage is sent first; the winner goes to the remainder once selected.

Input parameters:

- `campaign_id` (string, required): Campaign to test
- `sample_percentage` (number): Percent of the audience used for the test (default 20)
- `type` (string, required): What to test
- `variants` (array, required): Test variants (2–5)
- `winner_metric` (string): Metric used to pick the winner (default open_rate)

### `select_ab_test_winner` (~87 tokens)

Select the winning variant and send it to the remaining audience. This triggers a real send to everyone who was held back — it cannot be undone.

Input parameters:

- `metric` (string): Metric the decision was based on (default open_rate)
- `test_id` (string, required): A/B test ID
- `winner_variant` (string, required): Label of the winning variant, e.g. B

### `get_analytics` (~136 tokens)

Get delivery and engagement analytics — sent, delivered, opened, clicked, bounced, and complained — for the account or one campaign, grouped by day/week/month.

Input parameters:

- `campaign_id` (string): Limit to one campaign (omit for account-wide)
- `end_date` (string): End date, ISO 8601
- `group_by` (string): Time bucket for the series (default day)
- `period` (string): Shorthand window used when start_date is omitted (default 30d)
- `start_date` (string): Start date, ISO 8601 (e.g. 2026-01-01)

### `generate_report` (~98 tokens)

Generate a structured analytics report over a date range. Report types: campaign_performance, engagement_funnel, cohort_analysis, and send_time_heatmap (best hour/day to send).

Input parameters:

- `date_from` (string): Start date, ISO 8601 (default: 30 days ago)
- `date_to` (string): End date, ISO 8601 (default: today)
- `report_type` (string, required): Type of report to generate

### `get_revenue_attribution` (~58 tokens)

Attribute ecommerce revenue to email — revenue per campaign, per contact, and average order value from tracked conversions.

Input parameters:

- `campaign_id` (string): Limit to one campaign
- `period` (string): Time window (default 30d)

### `get_monetization_stats` (~135 tokens)

Get newsletter monetization figures: paid subscribers, monthly recurring revenue, churn, and revenue trend. 

Use it for 'how is the paid newsletter doing' questions. These are account-level totals over a trailing window, so they cannot be broken down per campaign — use get_revenue_attribution for that. 

Reads only; no billing state is changed and no subscriber is charged. Requires an API key. Revenue figures are reported in minor currency units unless stated otherwise, so check before presenting them as dollars. Zero paid subscribers is a real answer.

Input parameters:

- `period` (string): Time window (default 30d)

### `get_deliverability_score` (~48 tokens)

Get the account deliverability score (0–100) and letter grade (A–F) with the factors dragging it down. Start here when asked why emails are landing in spam.

### `run_deliverability_audit` (~48 tokens)

Run a full deliverability audit across authentication (SPF/DKIM/DMARC), domain reputation, list hygiene, content signals, and blocklist status. Returns prioritized findings.

### `get_warmup_status` (~45 tokens)

Get IP/domain warm-up progress and today's remaining send capacity. Exceeding warm-up capacity on a new domain is the fastest way to get throttled or blocklisted.

### `check_dmarc` (~62 tokens)

Check live SPF, DKIM, and DMARC DNS records for a domain and report alignment problems with the exact record to publish. Works for any domain, not only your own.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com

### `list_domains` (~67 tokens)

List sending domains with verification status and their DKIM/SPF/DMARC records. Check here first when a send fails with an unverified-sender error.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)

### `add_domain` (~50 tokens)

Add a sending domain and return the DNS records to publish. The domain cannot send until those records are live and verify_domain succeeds.

Input parameters:

- `domain` (string, required): Domain to add, e.g. example.com

### `verify_domain` (~51 tokens)

Re-check a domain's DNS records and mark it verified if they resolve. Safe to retry — DNS propagation can take up to 48 hours.

Input parameters:

- `domain_id` (string, required): Domain ID returned by add_domain

### `configure_inbound_domain` (~85 tokens)

Configure inbound email routing for a subdomain so replies land in the MisarMail unified inbox. Returns the MX record to publish.

Input parameters:

- `domain` (string, required): Root domain, e.g. example.com
- `subdomain` (string, required): Inbound subdomain label, e.g. reply
- `webhook_url` (string): Optional HTTPS URL to POST inbound messages to

### `list_forms` (~157 tokens)

List signup forms on the account with their embed status and conversion counts. 

Use it to find a form id before get_form or get_form_submissions, and to compare how forms are performing against each other. It returns the forms themselves, not the people who filled them in — that is get_form_submissions. 

Reads only; no form is created, published, or unpublished. Requires an API key. A form that exists is not necessarily embedded anywhere, so a zero conversion count may mean it was never installed rather than that it converts badly.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)
- `status` (string): Filter by form status

### `get_form` (~131 tokens)

Get one signup form in full: its fields, its embed code, and where it redirects after submission. 

Use it when you need the embed snippet to install the form, or need to know which fields it collects before interpreting submissions. For the submitted data itself, use get_form_submissions; for the list of forms, list_forms. 

Reads only; the form is not modified and no submission is created. Requires an API key. The embed code is meant to be pasted into a site, so returning it does not publish anything by itself.

Input parameters:

- `form_id` (string, required): Form ID (UUID)

### `get_form_submissions` (~154 tokens)

List the submissions a signup form has received, including the values entered in each field. 

Use it to see who signed up and what they told you. This returns PERSONAL DATA — email addresses and whatever else the form collects — so handle it accordingly and do not paste it into shared transcripts. For the form's own definition, use get_form. 

Reads only; submissions are not deleted, and nobody is subscribed or emailed as a result. Requires an API key. No submissions is a normal answer, not an error.

Input parameters:

- `form_id` (string, required): Form ID (UUID)
- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)

### `create_landing_page` (~112 tokens)

Create a hosted landing page with an email capture form. Returns the public URL; subscribers flow straight into your contact list.

Input parameters:

- `cta_text` (string): Call-to-action button text
- `headline` (string, required): Headline shown to visitors
- `name` (string, required): Internal page name
- `slug` (string): URL slug (auto-generated when omitted)
- `subheadline` (string): Supporting line under the headline
- `tags` (array): Tags applied to contacts who sign up here

### `list_marketplace_items` (~164 tokens)

Browse the MisarMail marketplace for ready-made email and automation templates. 

Use it to find a starting point instead of authoring from scratch. This is browse only: it installs nothing, and no template is added to the account by listing it. Inspect a candidate with get_marketplace_item before adopting it. 

Reads only. Requires an API key. Listings are third-party authored, so quality varies. For templates the account already owns, use list_templates instead — these two return different things.

Input parameters:

- `category` (string): Filter by category, e.g. newsletter, ecommerce
- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)
- `search` (string): Search marketplace listings

### `get_marketplace_item` (~127 tokens)

Get one marketplace listing in full, with its preview, author, and installation instructions. 

Use it after list_marketplace_items to inspect a template before adopting it — this is the read step, and it does NOT install anything into the account or create a template. Nothing changes until you act on the instructions it returns. 

Reads only. Requires an API key. Marketplace items are authored by third parties, so review the preview before recommending one; the listing describes what the author claims, not something MisarMail has verified.

Input parameters:

- `item_id` (string, required): Marketplace item ID

### `list_inbox_conversations` (~126 tokens)

List unified-inbox conversations (threads) with their status and detected intent. Use this for triage; use list_emails for individual messages in a folder.

Input parameters:

- `channel` (string): Filter by channel, e.g. email
- `intent` (string): Filter by detected intent, e.g. interested, unsubscribe, question
- `limit` (number): Results to return (default 20)
- `offset` (number): Offset for pagination
- `q` (string): Free-text search across the thread
- `status` (string): Filter by conversation status

### `get_inbox_conversation_messages` (~126 tokens)

Get every message in one inbox conversation, oldest first, with sender and timestamp. 

Use it to read a thread in full before replying or summarising — it is the detail view behind a conversation listing. It covers one conversation, and it does not send, reply, or mark anything as read. 

Reads only. Requires an API key. Message bodies are real customer correspondence, so treat the contents as confidential. Returns the whole thread rather than a page, so long conversations return a lot of text.

Input parameters:

- `conversation_id` (string, required): Conversation ID (UUID)

### `categorize_inbox_emails` (~61 tokens)

Run AI categorisation over a batch of inbox emails to label intent and priority. Consumes AI credits — pass only the emails you actually need triaged.

Input parameters:

- `email_ids` (array, required): Email IDs to categorise (max 50 per call)

### `list_api_keys` (~124 tokens)

List the API keys on the account with their scopes and when each was last used. 

Use it to audit access — to spot keys that are unused, over-scoped, or forgotten. It lists key METADATA only: the secret values are not returned by this or any other tool, so a key that has been lost must be rotated rather than recovered. 

Reads only; no key is created, revoked, or rotated. Requires an API key. Scope and last-used data is security-relevant, so treat the listing as sensitive even though it contains no secrets.

### `generate_subject_lines` (~90 tokens)

Generate AI subject-line variants for a campaign topic, optionally tuned to a tone and audience. Good input for create_ab_test.

Input parameters:

- `audience` (string): Who the email is for
- `count` (number): How many variants to generate (default 5, max 10)
- `tone` (string): Desired tone (default professional)
- `topic` (string, required): What the email is about

### `list_integrations` (~163 tokens)

List every third-party integration connected to the account, with its sync status and when it last ran. 

Start here when a question involves external data — it tells you which integrations exist and whether they are actually syncing. For one integration's configuration and scopes, follow up with get_integration; to turn one on or off, use toggle_integration. 

Reads only; nothing is connected, disconnected, or re-synced. Requires an API key. An integration listed as connected can still be failing to sync, so check the status rather than assuming. An empty list means nothing is connected yet, which is not an error.

Input parameters:

- `limit` (number): Results per page (default 20)
- `page` (number): Page number (default 1)

### `get_integration` (~135 tokens)

Get one integration in full: its configuration, the scopes it was granted, and the result of its last sync. 

Use it to diagnose an integration that list_integrations shows as unhealthy, or to check which scopes were granted before relying on a capability. Covers a single integration — list_integrations gives the overview. 

Reads only; it does not re-run a sync or change any setting. Requires an API key. The response describes what the integration is permitted to do, which is not the same as what it has successfully done — read the last sync result for that.

Input parameters:

- `integration_id` (string, required): Integration ID

### `toggle_integration` (~141 tokens)

Turn one third-party integration on or off. 

This changes live behaviour: DISABLING stops all syncing through that integration, so data quietly stops flowing until it is re-enabled. It does not disconnect the integration or revoke its credentials — the connection and its scopes survive, which is why re-enabling picks up where it left off. 

Safe to repeat: setting an integration to the state it is already in changes nothing. Requires an API key. Call list_integrations first so you know the current state rather than toggling blind.

Input parameters:

- `enabled` (boolean, required): true to enable, false to disable
- `integration_id` (string, required): Integration ID

### `list_sandbox_sends` (~39 tokens)

List emails captured by sandbox mode. Sandbox intercepts sends instead of delivering them — use it to verify templates and automations without emailing anyone.

### `clear_sandbox` (~109 tokens)

Delete every email captured in the sandbox. 

The sandbox holds messages intercepted during testing so they are never delivered to real recipients. This DELETES ALL of them and cannot be undone — but it touches only intercepted test mail, never sent campaigns, real inbox messages, contacts, or templates. 

Takes no parameters and offers no filter: it is all or nothing. Requires an API key. Clearing an already-empty sandbox is harmless. Read anything you still need from the sandbox before calling this.

### `upgrade` (~97 tokens)

Show the current MisarMail plan, how much of each quota is left, and what upgrading unlocks. Call it any time — not only after hitting a limit. Set open=true to open the checkout page in the default browser.

Input parameters:

- `open` (boolean): Open the upgrade/checkout page in the default browser.
- `plan` (string): Plan slug to open (e.g. 'pro', 'max'). Defaults to the recommended plan.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp#diagnostics

## Score history

- 2026-08-26: 81
- 2026-08-25: 79
- 2026-08-24: 79
- 2026-08-23: 78
- 2026-08-22: 78
- 2026-08-21: 77
- 2026-08-20: 77
- 2026-08-19: 76

## Common questions

### What is the MisarMail MCP Server server?

MisarMail MCP Server is listed in the public MCP registry as io.github.Misar-AI/misarmail-mcp. Send transactional email, run campaigns, manage contacts and automations, audit deliverability. This page covers its hosted endpoint (https://api.misar.io/mail/mcp).

### Is the MisarMail MCP Server server safe to use?

MisarMail MCP Server scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MisarMail MCP Server server expose?

MisarMail MCP Server exposes 54 tools: send_email, list_emails, get_email, reply_to_email, archive_email, and 49 more. Their descriptions and schemas cost roughly 5,700 tokens of context every time the server is loaded.

### Does the MisarMail MCP Server server require authentication?

Yes. MisarMail MCP Server asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the MisarMail MCP Server server still maintained?

MisarMail MCP Server is still listed as active in the MCP registry. We last reached this channel on 26 August 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.misar.io/mail/mcp
- Authorisation metadata: https://api.misar.io/.well-known/oauth-protected-resource/mail/mcp
- Repository: https://github.com/Misar-AI/misarmail-mcp
- Website: https://www.misarmail.com/
- Changelog RSS feed: https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp.json
- HTML version of this page: https://verifymcp.io/servers/misar-ai-misarmail-mcp/mail-mcp