Skip to main content
Glama
ignytehq

plunk-mcp

Official
by ignytehq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Track event

plunk_track_event

Record a contact event to drive workflow triggers and segment filters. Auto-creates the contact if missing; omit subscribed to keep opt-out state.

Instructions

Purpose: Record that a contact did something. Events drive workflow triggers and segment filters, and the contact is created if it does not exist.

Not for: Reading events back — that is plunk_list_events or plunk_get_contact_events. This writes one.

Returns: Confirmation that the event was recorded.

Use when: Something happened that automation should react to, or that you want to segment on later.

Note: Omitting subscribed preserves the contact's current subscription state; passing true would resubscribe someone who opted out. Works with or without PLUNK_PUBLIC_KEY: with it, one request; without it, the contact is upserted first and the event recorded against it. Pass idempotencyKey to make a retry safe after a timeout.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoEvent/contact data. Use {value, persistent: false} to scope to workflows only.
emailYesContact email. Contact is auto-created if missing.
eventYesEvent name, e.g. 'user-signup'
subscribedNoSubscription state to apply. Omit to preserve the contact's current state (new contacts default to subscribed). Pass false to track an event without resubscribing an unsubscribed contact.
idempotencyKeyNoOptional. A unique string of your choosing that makes a retry safe: if this key was already used by the project, Plunk refuses the request with 409 instead of sending twice. Keys are remembered for 24 hours. Plunk v0.13+.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.0.0
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / data / propertyNames
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / idempotencyKey
      Added value: +{
+  "description": "Optional. A unique string of your choosing that makes a retry safe: if this key was already used by the project, Plunk refuses the request with 409 instead of sending twice. Keys are remembered for 24 hours. Plunk v0.13+.",
+  "maxLength": 255,
+  "type": "string"
+}
  2. First observedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover only the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), while the description discloses the real traps: the contact is auto-created/upserted as a side effect, omitting 'subscribed' preserves state whereas true would resubscribe an opt-out, behavior differs with and without PLUNK_PUBLIC_KEY, and idempotencyKey makes a timed-out retry safe with a 409 on duplicate.

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 bolded Purpose/Not for/Returns/Use when labels, and each section carries operational value rather than boilerplate. It is slightly longer than necessary because the subscription-preservation warning is stated twice (once in the Note, once implicitly in the schema), but no section is filler.

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

Completeness5/5

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

For a mutating, side-effect-bearing tool with five parameters and no output schema, the description covers the return ('confirmation that the event was recorded'), the auto-create side effect, auth-mode variation, and retry safety. An agent has everything needed to call it correctly and safely.

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; the description goes further by explaining the behavioral consequence of omitting 'subscribed' (preserves state, new contacts default subscribed) and why to pass idempotencyKey. It also documents environment-dependent behavior of the call that no parameter description captures, though some of the 'subscribed' note restates the schema.

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?

States a specific verb and resource ('Record that a contact did something') and immediately scopes it as an event-ingestion write. It names the sibling read tools (plunk_list_events, plunk_get_contact_events) as the non-overlapping alternatives, so an agent can route without opening either schema.

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 when-to-use ('something happened that automation should react to, or that you want to segment on later') plus an explicit 'Not for' exclusion naming the two read alternatives. Nothing about selection is left to inference.

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