SendGrid MCP Server

Send Mail

send_mail

Destructive

Send emails directly through SendGrid's Mail Send API. Specify recipients, content, subject, and optional cc/bcc/reply-to fields to deliver messages.

Instructions

Send an email using SendGrid Mail Send API

Input Schema

TableJSON Schema

Name	Required	Description
`from`	Yes
`content`	Yes	Email content
`subject`	No	Default subject if not set in personalizations
`reply_to`	No
`personalizations`	Yes	Personalization settings for recipients

Schema Changelog

Changes observed during successful MCP inspections.

Changed21 schema fields changedv1.1.1Aug 27, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / content / items / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / from / $ref
```
Removed value: -"#/properties/personalizations/items/properties/to/items"
```
- addedInput schema / properties / from / properties
```
Added value: +{
+  "email": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / from / required
```
Added value: +[
+  "email"
+]
```
- addedInput schema / properties / from / type
```
Added value: +"object"
```
- removedInput schema / properties / personalizations / items / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / personalizations / items / properties / bcc / items / $ref
```
Removed value: -"#/properties/personalizations/items/properties/to/items"
```
- addedInput schema / properties / personalizations / items / properties / bcc / items / properties
```
Added value: +{
+  "email": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / personalizations / items / properties / bcc / items / required
```
Added value: +[
+  "email"
+]
```
- addedInput schema / properties / personalizations / items / properties / bcc / items / type
```
Added value: +"object"
```
- removedInput schema / properties / personalizations / items / properties / cc / items / $ref
```
Removed value: -"#/properties/personalizations/items/properties/to/items"
```
- addedInput schema / properties / personalizations / items / properties / cc / items / properties
```
Added value: +{
+  "email": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / personalizations / items / properties / cc / items / required
```
Added value: +[
+  "email"
+]
```
- addedInput schema / properties / personalizations / items / properties / cc / items / type
```
Added value: +"object"
```
- addedInput schema / properties / personalizations / items / properties / substitutions / propertyNames
```
Added value: +{
+  "type": "string"
+}
```
- removedInput schema / properties / personalizations / items / properties / to / items / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / reply_to / $ref
```
Removed value: -"#/properties/personalizations/items/properties/to/items"
```
- addedInput schema / properties / reply_to / properties
```
Added value: +{
+  "email": {
+    "type": "string"
+  },
+  "name": {
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / reply_to / required
```
Added value: +[
+  "email"
+]
```
- addedInput schema / properties / reply_to / type
```
Added value: +"object"
```
Changed2 schema fields changedv1.0.0Jan 3, 2026
- addedInput schema / $schema
```
Added value: +"http://json-schema.org/draft-07/schema#"
```
- addedInput schema / additionalProperties
```
Added value: +false
```
First observedOct 1, 2025

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already mark the operation as non-read-only, non-idempotent, and destructive, so the side-effect profile is partially known. The description adds the context that this goes through the SendGrid Mail Send API, which signals an external delivery side effect, but it does not disclose consequences like immediate delivery, reversibility, or provider limits.

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

Conciseness4/5

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

The description is a single focused sentence with no filler, clearly naming the action and API. It is concise and front-loaded, though it sacrifices useful context for brevity.

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

Completeness2/5

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

This is a side-effecting tool with five parameters, three required, nested objects, and no output schema, but the description is only one sentence. It omits key information such as required fields (personalizations, from, content), how to structure recipients, and what the call returns or whether it is synchronous.

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

Parameters2/5

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

The description adds no parameter-level meaning beyond the schema. With schema description coverage at 60%, some fields are documented in the schema, but the description does not compensate for the uncovered required fields or clarify the nested personalizations, from, content, and cc/bcc structure.

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

Purpose4/5

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

The description states a specific verb ('Send') and resource ('an email') and names the underlying SendGrid Mail Send API, so an agent can tell this is a direct email-sending tool. It does not explicitly differentiate from sibling email-related tools, but none of the siblings appears to perform a raw mail send, so confusion risk is low.

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

Usage Guidelines2/5

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

The description gives no guidance about when to use send_mail versus the many sibling tools such as create_sender, open_single_send_creator, or the email list and template tools. The intended usage is only implied by the verb 'Send an email'.

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

Deploy Server

Send Mail

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools