Discord MCP - Discord server management MCP for AI agents

Send webhook message

send_webhook_message

Post a message to a Discord webhook with optional display name, avatar override, embeds, and up to 10 files from public URLs while suppressing mentions.

Instructions

Post through a webhook with an optional display name and avatar override, and up to 10 files fetched from public URLs. Mentions are suppressed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "webhook": "<webhook>"
    },
    "name": "send_webhook_message"
  }
}

Input Schema

Name	Required	Description
`files`	No	Up to 10 files to attach, each fetched from a public URL (20 MiB each). Needs the Attach Files permission.
`guild`	No	Guild (server) name or ID. Omit to use the default guild.
`embeds`	No	Up to 10 embeds. Each needs a title, a description, an author, fields, a footer, or a picture. Discord allows 6,000 characters of text across all of one message's embeds.
`content`	No
`webhook`	Yes	Webhook name or ID.
`username_override`	No
`avatar_url_override`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedv1.4.2Nov 12, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedInput schema / properties / embeds / description

Previous value: -"Up to 10 embeds."New value: +"Up to 10 embeds. Each needs a title, a description, an author, fields, a footer, or a picture. Discord allows 6,000 characters of text across all of one message's embeds."

addedInput schema / properties / embeds / items / additionalProperties
```
Added value: +false
```

addedInput schema / properties / embeds / items / properties / author

Added value: +{
+  "description": "Small line above the title, such as who it is from.",
+  "maxLength": 256,
+  "type": "string"
+}

addedInput schema / properties / embeds / items / properties / fields

Added value: +{
+  "description": "Up to 25 name and value pairs under the description.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "inline": {
+        "description": "Sits beside its neighbours instead of on a row of its own.",
+        "type": "boolean"
+      },
+      "name": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "value": {
+        "maxLength": 1024,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 25,
+  "type": "array"
+}

addedInput schema / properties / embeds / items / properties / footer

Added value: +{
+  "description": "Small line at the bottom.",
+  "maxLength": 2048,
+  "type": "string"
+}

addedInput schema / properties / embeds / items / properties / image_url

Added value: +{
+  "description": "Large picture under the text: an http or https link, or attachment://<filename> for a file that comes with the message.",
+  "maxLength": 2048,
+  "pattern": "^(https?|attachment):\\/\\/\\S+$",
+  "type": "string"
+}

addedInput schema / properties / embeds / items / properties / thumbnail_url

Added value: +{
+  "description": "Small picture in the top corner, given the same way.",
+  "maxLength": 2048,
+  "pattern": "^(https?|attachment):\\/\\/\\S+$",
+  "type": "string"
+}

addedInput schema / properties / embeds / items / properties / timestamp

Added value: +{
+  "description": "A time shown beside the footer: \"now\" for the current time, or ISO 8601, like 2026-11-09T18:00:00Z. With no zone it is read as UTC.",
+  "type": "string"
+}

addedInput schema / properties / embeds / items / properties / url / description
```
Added value: +"Makes the title a link."
```
removedInput schema / properties / embeds / items / properties / url / format
```
Removed value: -"uri"
```
addedInput schema / properties / embeds / items / properties / url / pattern
```
Added value: +"^https?:\\/\\/"
```

addedInput schema / properties / files

Added value: +{
+  "description": "Up to 10 files to attach, each fetched from a public URL (20 MiB each). Needs the Attach Files permission.",
+  "items": {
+    "properties": {
+      "description": {
+        "description": "Alt text describing the file, read by screen readers.",
+        "maxLength": 1024,
+        "type": "string"
+      },
+      "filename": {
+        "description": "Name to show, such as chart.png. Default: taken from the URL.",
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "spoiler": {
+        "description": "Blur it until clicked.",
+        "type": "boolean"
+      },
+      "url": {
+        "description": "Public http or https URL of the file. Local paths are not accepted.",
+        "format": "uri",
+        "type": "string"
+      }
+    },
+    "required": [
+      "url"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "minItems": 1,
+  "type": "array"
+}

Changed2 schema fields changedv1.3.0Aug 12, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- removedInput schema / properties / embeds / items / additionalProperties
```
Removed value: -false
```
First observedv1.0.2Jun 14, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations only say readOnly=false and destructive=false, so the description adds real value by disclosing that mentions are suppressed (a surprising side effect an agent must know) and that files are fetched from public URLs, implying server-side fetching rather than upload. The schema, not the description, carries the Attach Files permission and 20 MiB limit, so a little behavioral context is still off-loaded.

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?

One sentence, front-loaded with the core action, with the qualifiers trailing in a natural order and no filler. It is dense but every clause carries information; the only minor cost is that three separate capabilities are packed into a single line.

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

Completeness3/5

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

For a mutation tool with 7 parameters, no output schema, and a large nested embeds schema, the description omits embeds entirely — the single most complex feature the tool accepts — along with guild targeting and message content. It covers the override and file-attachment surface well, but an agent reading only the description would not know it can build embeds.

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?

With 57% schema coverage and a very richly documented nested schema, the baseline is 3. The description maps loosely to username_override/avatar_url_override and the files array, but adds no syntax, limits, or meaning beyond what the schema already declares (the wholly undescribed 'content' parameter in particular gets no help).

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?

States a specific verb and resource ('Post through a webhook') plus the two distinguishing capabilities: display name/avatar override and file attachments. An agent can tell this apart from a plain channel post, though it never names send_message or send_dm as the non-webhook alternatives.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: 'through a webhook' signals you need a webhook target, and the required 'webhook' parameter reinforces that. There is no explicit when-to-use versus send_message, no prerequisite about the webhook already existing (create_webhook), and no when-not-to-use guidance.

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

Deploy Server