AFFiNE MCP Server

List Notifications

list_notifications

Read-onlyIdempotent

Fetch a server page of current-user AFFiNE notifications with cursor or offset pagination, preserving edge cursors, pageInfo, and total count; filter unread on the fetched page.

Instructions

List one server page of current-user AFFiNE notifications in a stable envelope. The response preserves each edge cursor, server pageInfo, and serverTotalCount. unreadOnly is a client-side filter over only the fetched page; it does not change server counts or pageInfo.

Input Schema

Name	Required	Description
`after`	No	Cursor from pagination.pageInfo.endCursor. Mutually exclusive with offset.
`first`	No	Number of notifications to fetch (default 20, maximum 100).
`offset`	No	Zero-based offset pagination. Mutually exclusive with after.
`unreadOnly`	No	Return only unread notifications from the fetched server page; this is not a server-wide unread query.

Output Schema

Name	Required	Description	Default
`ok`	No
`code`	No
`kind`	No
`error`	No
`items`	No
`details`	No
`causeCode`	No
`retryable`	No
`recoveryGuidance`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.10.2Oct 27, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the response envelope behavior (edge cursors, pageInfo, serverTotalCount preserved) and, critically, warns that unreadOnly is a client-side filter over only the fetched page and does not affect server counts or pageInfo — a subtle semantic trap an agent would otherwise fall into.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with what is listed and scoped to a page, then the return shape, then the one behavioral caveat that matters. No wasted text.

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?

With an output schema present and 100% schema coverage, the description needn't restate return values or defaults; it covers scope, envelope, and filter semantics. Minor gaps remain around sort order and how to chain pages forward/backward.

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 earns an extra point by reinforcing the unreadOnly semantics (page-scoped, does not alter counts or pageInfo) and tying the cursor to preserved pageInfo, which clarifies how `after` is obtained.

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 (List ... current-user AFFiNE notifications) and scopes it precisely to 'one server page', which implicitly separates it from read_all_notifications. It stops short of naming that sibling, so the differentiation is inferred rather than stated.

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 only implied: the phrase 'one server page' suggests this for paginated browsing, but there is no explicit instruction on when to pick this over read_all_notifications, nor any prerequisite or exclusion guidance.

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

Deploy Server