MCP Email Server

Overview Schema Source Related Servers Discussions Admin

send_email

Send an email from your account with recipients, CC, BCC, attachments, and reply-threading. Get per-recipient delivery status and the accepted message's RFC Message-ID.

Instructions

Send one email using the specified account. Supports reply threading. Partial or ambiguous SMTP delivery reports per-recipient succeeded/failed/unknown status and reports the independent Sent-copy outcome separately; ambiguous effects are not retried automatically. The response names the delivered message's RFC Message-Id once the provider accepts the message data, and reports no identifier for an ambiguous delivery.

Input Schema

TableJSON Schema

Name	Required	Description
`cc`	No	A list of CC email addresses.
`bcc`	No	A list of BCC email addresses.
`body`	Yes	The body of the email.
`html`	No	Whether to send the email as HTML (True) or plain text (False).
`subject`	Yes	The subject of the email.
`reply_to`	No	Email address to set as the Reply-To header. When set, email clients will reply to this address instead of the From address.
`recipients`	Yes	A list of recipient email addresses.
`references`	No	Space-separated Message-IDs for the thread chain. Simple IDs may be bare or bracketed; bare IDs gain RFC angle brackets during composition. Usually includes in_reply_to plus ancestors.
`attachments`	No	A list of file paths to attach. Relative paths are resolved against the server process working directory; absolute paths are recommended.
`in_reply_to`	No	Message-ID of the email being replied to. Simple IDs may be bare or bracketed; bare IDs gain RFC angle brackets during composition.
`account_name`	Yes	The name of the email account to send from.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.5.2Aug 28, 2026

changedInput schema / properties / in_reply_to / description

Previous value: -"Message-ID of the email being replied to. Enables proper threading in email clients."New value: +"Message-ID of the email being replied to. Simple IDs may be bare or bracketed; bare IDs gain RFC angle brackets during composition."

changedInput schema / properties / references / description

Previous value: -"Space-separated Message-IDs for the thread chain. Usually includes in_reply_to plus ancestors."New value: +"Space-separated Message-IDs for the thread chain. Simple IDs may be bare or bracketed; bare IDs gain RFC angle brackets during composition. Usually includes in_reply_to plus ancestors."

Addedv1.1.1Aug 1, 2026
Removedv1.0.1Jul 25, 2026

Changed1 schema field changedv0.10.0May 29, 2026

addedInput schema / properties / reply_to

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Email address to set as the Reply-To header. When set, email clients will reply to this address instead of the From address.",
+  "title": "Reply To"
+}

Addedv0.8.0May 26, 2026
Removedv0.7.0May 22, 2026

Changed5 schema fields changedv1.0.0Jan 3, 2026

addedInput schema / properties / attachments

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "A list of absolute file paths to attach to the email. Supports common file types (documents, images, archives, etc.).",
+  "title": "Attachments"
+}

addedInput schema / properties / html

Added value: +{
+  "default": false,
+  "description": "Whether to send the email as HTML (True) or plain text (False).",
+  "title": "Html",
+  "type": "boolean"
+}

addedInput schema / properties / in_reply_to

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Message-ID of the email being replied to. Enables proper threading in email clients.",
+  "title": "In Reply To"
+}

addedInput schema / properties / references

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Space-separated Message-IDs for the thread chain. Usually includes in_reply_to plus ancestors.",
+  "title": "References"
+}

changedOutput schema / properties / result / type
```
Previous value: -"null"New value: +"string"
```

First observedAug 15, 2025

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavioral detail beyond the annotations: per-recipient succeeded/failed/unknown delivery status, separate Sent-copy outcome reporting, no automatic retry on ambiguous delivery, and Message-Id reporting only after provider acceptance. These details give an agent accurate expectations for side effects and response behavior, and they are consistent with the readOnly=false and idempotent=false annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the first sentence states the action, and subsequent sentences add necessary delivery-reporting caveats. There is no redundant information or filler, and the technical details are organized logically without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter mutation tool with an output schema, the description covers the most critical behavioral nuances: delivery ambiguity, per-recipient status, no automatic retries, and Message-Id response. It could additionally mention constraints related to allowed recipients or senders suggested by sibling tools, but those are discoverable via list_allowed_recipients and list_allowed_senders. Overall, the description is sufficiently complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 11 parameters and their meanings. The description adds no parameter-specific details beyond mentioning reply threading, which maps to in_reply_to/references but is already explained in the schema. A baseline of 3 is appropriate when the schema carries the parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Send one email using the specified account'), making the core function unambiguous. It distinguishes from sibling tools by clearly indicating this is the sending action, not a listing, retrieval, or forwarding operation. The mention of reply threading adds a useful capability marker without obscuring the primary purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly conveys that this tool is for sending a single email, providing strong contextual signal for when to use it. However, it does not explicitly name alternatives such as forward_email or state when not to use this tool, so exclusion guidance is left implicit. The usage context is clear but not fully explicit about sibling boundaries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server