Nevent MCP

nevent_create_campaign

Create a new campaign draft (email, SMS, WhatsApp, push, or multi-channel). PREREQUISITES: call nevent_list_segments to get the target segment_id, and nevent_list_templates to get the template_id. The campaign is always created in DRAFT status — no messages are sent. After creation, call nevent_schedule_campaign to schedule delivery. For EMAIL_ONLY (and email multi-channel): email_subject is required. For SMS_ONLY/WHATSAPP_ONLY/PUSH_ONLY and multi-channel involving those: message is required. Optional fields: from_name, preview_text, template_id, segment_ids, utm_source/medium/campaign/content/term/custom_params, reply_to (email address for reply routing — useful when replies should go to a different mailbox than the From address), sender_identity_id (the sender to send the email campaign with; list the eligible ones and the default with nevent_get_sending_profile; omitted = the organization's default sender; a sender that is not eligible is refused with sender_unavailable). Always confirm the segment audience count with the user before scheduling.

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": {
      "name": "<name>",
      "channel": "<channel>"
    },
    "name": "nevent_create_campaign"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Campaign name (required, max 255 characters)
`channel`	Yes	Delivery channel (nev-api CommunicationChannel enum). Use EMAIL_ONLY, SMS_ONLY, WHATSAPP_ONLY, PUSH_ONLY for single-channel; EMAIL_AND_SMS, EMAIL_AND_WHATSAPP, PUSH_AND_SMS, PUSH_AND_WHATSAPP, SMS_AND_WHATSAPP for multi-channel; ALL_CHANNELS or OMNICHANNEL for broad delivery. Legacy values EMAIL/SMS/WHATSAPP are accepted but deprecated.
`message`	No	Message text body (required when channel=SMS or WHATSAPP)
`reply_to`	No	Reply-To email address (optional). Recipients' replies go to this address instead of the From address. Must be a valid email, max 254 chars. Only meaningful for email-bearing channels.
`utm_term`	No	UTM term parameter — paid search keyword. Max 100 chars.
`from_name`	No	Sender display name (optional, defaults to tenant sender name)
`email_body`	No	HTML body content of the email (optional, can be set later)
`utm_medium`	No	UTM medium parameter (e.g. "email", "sms"). Max 100 chars. Auto-detected from channel if omitted.
`utm_source`	No	UTM source parameter (e.g. "nevent", "newsletter"). Max 100 chars.
`segment_ids`	No	Array of segment IDs to target (optional, can be set later)
`template_id`	No	Template ID to pre-populate campaign content (optional)
`utm_content`	No	UTM content parameter — differentiates links/variants. Max 100 chars.
`preview_text`	No	Inbox preview text (optional, shown in email client summaries)
`utm_campaign`	No	UTM campaign parameter (e.g. "summer-sale-2026"). Max 100 chars. Defaults to slugified campaign name.
`email_subject`	No	Email subject line (required when channel=EMAIL, max 998 chars per RFC 5322)
`utm_custom_params`	No	Custom tracking parameters as key-value pairs appended to tracked links (optional).
`sender_identity_id`	No	Sender to send the email campaign with: an identityId from nevent_get_sending_profile → senders.senders[] with selectable=true. Omit it to use the organization's default sender (senders.defaultIdentityId). Only meaningful for email-bearing channels and when senders.perCampaign is true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / sender_identity_id

Added value: +{
+  "description": "Sender to send the email campaign with: an identityId from nevent_get_sending_profile → senders.senders[] with selectable=true. Omit it to use the organization's default sender (senders.defaultIdentityId). Only meaningful for email-bearing channels and when senders.perCampaign is true.",
+  "maxLength": 64,
+  "minLength": 1,
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses that the campaign is always created in DRAFT status and that no messages are sent, which is the key behavioral fact an agent needs. It also documents a failure mode ('a sender that is not eligible is refused with sender_unavailable') and the default-sender fallback semantics. Missing only a note on what identifier is returned, though with no output schema that is a real remaining gap.

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?

Front-loaded with the verb and object, then prerequisites, then conditional requirements, then optional fields — a sensible ordering with no filler sentences. The one redundancy is the bullet-style listing of optional parameters whose meanings are already fully documented in the schema, which inflates length for little gain.

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 a 17-parameter mutation with nested objects and no output schema, the description covers preconditions, conditional field requirements, creation state, and the natural next step. The remaining omission is return-value information (e.g., the campaign_id needed by nevent_schedule_campaign), which the agent must infer.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, and the description pushes past it by stating channel-conditional requirements (email_subject for email-bearing channels, message for SMS/WhatsApp/push), the reply_to routing rationale, and the sender_identity_id eligibility/default rule tied to nevent_get_sending_profile. The enumeration of optional fields (from_name, preview_text, template_id, segment_ids, UTM fields) largely restates schema content rather than adding to it.

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 first sentence gives a specific verb+resource ('Create a new campaign draft') and enumerates the supported channel families. It is immediately distinguishable from siblings such as nevent_schedule_campaign, nevent_list_campaigns, and nevent_quote_campaign, and the word 'draft' signals the object state created.

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

Usage Guidelines5/5

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

Explicit prerequisites (nevent_list_segments for segment_id, nevent_list_templates for template_id), an explicit follow-up action (nevent_schedule_campaign), and an explicit workflow rule (confirm audience count before scheduling) are all stated. It also names nevent_get_sending_profile as the source for sender_identity_id, so the agent knows which sibling to call first.

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

All Nevent MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.