everypage-mcp

Official

by EveryPageApp

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Create, test or delete a webhook

everypage_manage_webhook

Destructive

Create, test, and delete EveryPage webhook endpoints to receive signed event notifications when documents are opened, viewed, downloaded, or leads are captured; creation returns a signing secret.

Instructions

Manage where EveryPage sends event notifications. Create an endpoint to receive signed deliveries when a document is opened, read, downloaded or a lead is captured; send a test delivery to check an endpoint is reachable; or delete one. Creating returns a signing secret that is shown only once.

Input Schema

Name	Required	Description
`url`	No	create: the https:// endpoint that will receive deliveries.
`file`	No	create: limit deliveries to one document. Omit for the whole account.
`action`	Yes	What to do.
`events`	No	create: which events to deliver. file.opened fires the moment a reader opens a document; file.viewed fires when their reading session ends and carries pages viewed and time spent. gate.completed (captured leads) requires the Pro plan at the time the event happens.
`format`	No	create: json (signed, for your own code) or slack (Slack Block Kit for an incoming webhook). Default json.
`webhook`	No	test/delete: the endpoint's id, from everypage_list_webhooks.

Output Schema

Name	Required	Description
`action`	Yes
`secret`	No	Shown exactly once, at creation. Store it now.
`status`	No
`deleted`	No
`webhook`	No
`delivered`	No
`latencyMs`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.1.1Oct 15, 2026

changedInput schema / properties / events / description

Previous value: -"create: which events to deliver. gate.completed (captured leads) requires the Pro plan at the time the event happens."New value: +"create: which events to deliver. file.opened fires the moment a reader opens a document; file.viewed fires when their reading session ends and carries pages viewed and time spent. gate.completed (captured leads) requires the Pro plan at the time the event happens."

changedInput schema / properties / events / items / enum

Previous value: -[
-  "file.viewed",
-  "file.downloaded",
-  "gate.completed",
-  "note.created",
-  "receipt.confirmed",
-  "file.burned",
-  "content.replaced",
-  "invite.viewed",
-  "proofing.updated"
-]New value: +[
+  "file.opened",
+  "file.viewed",
+  "file.downloaded",
+  "gate.completed",
+  "note.created",
+  "receipt.confirmed",
+  "file.burned",
+  "content.replaced",
+  "invite.viewed",
+  "proofing.updated"
+]

First observedv0.1.0Aug 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered structurally. The description still adds real behavioral value beyond them: deliveries are signed, a test delivery is non-persistent, and the signing secret is shown only once — an irreversible once-only exposure the agent must warn about.

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 compact sentence-cluster with the resource front-loaded and the three actions following in order. Every clause does work, though the packed semicolon structure makes it slightly dense for scanning.

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?

An output schema exists, so return shapes need not be described, and annotations carry the destructive/read-only profile. The description fills the remaining gaps an agent needs (signing secret exposure, test vs real delivery), leaving only plan/auth prerequisites unstated.

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 100% and the enum-per-action scoping ('create:', 'test/delete:') is already encoded in the schema, so the description adds little parameter detail. It reinforces the event semantics (opened vs viewed, lead capture) but that is largely duplicated in the events parameter description, making 3 the correct baseline.

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 concrete verb+resource — managing webhooks that receive EveryPage event notifications — and enumerates the three sub-actions (create endpoint, send test delivery, delete). It is clearly distinguishable from list-only siblings by describing the mutation surface, though it never names everypage_list_webhooks as its read counterpart.

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

Usage Guidelines4/5

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

Each action carries its own usage context: create to receive signed deliveries, test to check an endpoint is reachable, delete to remove one. That is clear when-to-use guidance, but there are no exclusions or prerequisites stated (e.g. plan requirements, auth scopes), so it stops short of 5.

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

Deploy Server