instagram-mcp

Get inbox

instagram_get_inbox

Read-onlyIdempotent

Review recent comments and webhook events in one paginated triage feed, with unanswered and handled flags to prioritize replies.

Instructions

Unified triage feed: recent top-level comments on your latest media, tags, and stored webhook events, with unanswered (no reply from you) and handled flags. Window = since or last days days. Offset-paginated over the merged list.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "instagram_get_inbox"
  }
}

Input Schema

Name	Required	Description
`days`	No	Window in days (default 7).
`limit`	No	Page size (default 25, max 100).
`since`	No	ISO 8601 start of the window; overrides days.
`cursor`	No	Opaque cursor from a previous next_cursor.
`account`	No	Account alias; defaults to the configured default account.
`include_handled`	No
`unanswered_only`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered by structured data. The description adds useful context on the merged data sources, the unanswered/handled flag semantics, and the window rule, but says nothing about ordering, response shape, or how the merged list is composed.

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 tight sentences with the core identity front-loaded and no filler. The pagination clause placement at the end is slightly awkward given it contradicts the cursor parameter, but the text is dense and every sentence carries information.

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?

With no output schema, the description carries the burden of explaining what comes back. It describes the merged list and the per-item unanswered/handled flags, but never mentions the response envelope or how next_cursor is surfaced for the next page, which an agent needs in order to paginate.

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 71%, so the schema documents most parameters, and the description adds the precedence rule that 'since' overrides 'days' plus the meaning of the flags. However, the description's claim of being 'offset-paginated' conflicts with the schema's opaque 'cursor' parameter sourced from next_cursor, which is likely to confuse an agent about how to page.

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 names a specific verb/resource pair ('Unified triage feed') and enumerates its three constituents: recent top-level comments on latest media, tags, and stored webhook events. This lets an agent distinguish it from instagram_list_comments and instagram_list_mentions, which cover only one source each, though those siblings are never named explicitly.

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?

Use is implied by 'triage feed' and the unanswered/handled flags, but there is no explicit guidance on when to pick this over instagram_list_comments, instagram_list_mentions, or instagram_list_conversations. No exclusions or preconditions are stated.

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

Deploy Server