Skip to main content
Glama
thenavidm

Beehiiv MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Create subscription export

create_export
Destructive

Create a subscription export for a Beehiiv publication, optionally scoped to a segment and with full or basic columns. Set confirm=true to run this account-changing action.

Instructions

Create subscription export. Changes account state and requires confirm=true for the user-requested action. OAuth integrations require subscriptions:write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
accountNoNamed private account from BEEHIIV_ACCOUNTS. Defaults to BEEHIIV_DEFAULT_ACCOUNT or the first configured account.
confirmNoSet true only when the user asked for exactly this action.
payloadNoComplete JSON body instead of individual body flags. Supports nullable fields and nested bulk structures. Cannot be combined with body flags or payload_file.
variantNoWhich column set the export uses
segment_idNo
payload_fileNoLocal JSON request body file, at most 5 MB. Contents are validated before the API call and are never logged.
publication_idYesThe prefixed ID of the publication object

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv3.0.1
    • addedInput schema / $defs
      Added value: +{
+  "SegmentId": {
+    "description": "Optional prefixed ID of a segment to scope the export to. When omitted the export covers the whole publication. A segment that does not exist, or belongs to another publication, answers 404.",
+    "pattern": "^(seg_[0-9a-fA-F\\-]+)$",
+    "title": "SegmentId",
+    "type": "string"
+  }
+}
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true for every account mutation. Confirms only the user-requested action."New value: +"Set true only when the user asked for exactly this action."
    • addedInput schema / properties / payload / properties / segment_id / $ref
      Added value: +"#/$defs/SegmentId"
    • removedInput schema / properties / payload / properties / segment_id / description
      Removed value: -"Optional prefixed ID of a segment to scope the export to. When omitted the export covers the whole publication. A segment that does not exist, or belongs to another publication, answers 404."
    • removedInput schema / properties / payload / properties / segment_id / pattern
      Removed value: -"^(seg_[0-9a-fA-F\\-]+)$"
    • removedInput schema / properties / payload / properties / segment_id / title
      Removed value: -"SegmentId"
    • removedInput schema / properties / payload / properties / segment_id / type
      Removed value: -"string"
    • addedInput schema / properties / segment_id / $ref
      Added value: +"#/$defs/SegmentId"
    • removedInput schema / properties / segment_id / description
      Removed value: -"Optional prefixed ID of a segment to scope the export to. When omitted the export covers the whole publication. A segment that does not exist, or belongs to another publication, answers 404."
    • removedInput schema / properties / segment_id / pattern
      Removed value: -"^(seg_[0-9a-fA-F\\-]+)$"
    • removedInput schema / properties / segment_id / title
      Removed value: -"SegmentId"
    • removedInput schema / properties / segment_id / type
      Removed value: -"string"
  2. First observedv2.0.0

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds meaningful context on top: it changes account state, it gates on confirm=true, and OAuth integrations need the subscriptions:write scope. The auth requirement and confirm gate are genuine value-adds. It stops short of 5 because it does not say whether the export is asynchronous, where the artifact lands, or what the returned reference is.

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?

Three short sentences, front-loaded with the action, then the safety gate, then the auth requirement. No waste, though the opening sentence is redundant with the title and could have been spent on differentiating content.

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 destructive, non-idempotent mutation with no output schema and seven parameters, the description covers the confirm gate and auth scope but omits the outcome: what the export yields, whether it is a long-running job, and how the result is retrieved (get_export/list_exports). The exclusion between payload and body flags is left entirely to the schema.

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 86%, so the schema already documents account, payload, variant, segment_id, payload_file, and publication_id in detail. The description only touches confirm, and even that largely restates the schema's own "Set true only when the user asked for exactly this action." Baseline 3 is appropriate.

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

Purpose3/5

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

The first sentence, "Create subscription export," is essentially a verbatim restatement of the tool title, so it adds no information beyond the name. It is a clear verb+resource but never explains what an export is, what it produces, or how it differs from siblings like get_export and list_exports. Adequate but with a real gap.

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?

"Requires confirm=true for the user-requested action" implies the tool should only be invoked on an explicit user request, which is useful gating. However, no alternatives are named (get_export, list_exports) and no when-not-to-use conditions are given. Usage is implied rather than stated.

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

Deploy Server

Other Tools