MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds useful behavior beyond the annotations: session-only login versus a permanent non-expiring config connection, and what the no-args call returns (a link). The idempotentHint and destructiveHint in annotations are not contradicted, though side effects of setting up a session are only implied.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loads the purpose, then lists the config route and the session-only call forms. The structure is slightly run-on with the Best and Or alternatives, but every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single optional parameter with no output schema, the description covers both call forms, the login link result, and the permanent config alternative. It does not explain failure or invalid-token outcomes, but an agent has enough information to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description carries the full meaning of the token parameter: it is a JWT pasted by the user, passed as { token: '<jwt>' }, and may be omitted to get the login link. It could additionally clarify invalid-token behavior, but the parameter itself is well explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource (MCP.AI for IDE agents) and a clear action: authenticate by logging in through the browser and capturing an access token. It clearly distinguishes this from the Instagram action siblings and generic tools like show_version.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit invocation modes: pass a JWT token for session-only login, or call with no arguments to get the login link, and recommends the config-header approach for a permanent connection. It does not explicitly contrast itself with sibling tools like connect, but the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools pair up with near-identical purposes (instagram_actions_list_comments vs instagram_get_ig_media_comments, instagram_create_carousel_container vs instagram_post_ig_user_media, instagram_actions_send_message vs instagram_send_text_message), so an agent can easily select the wrong one. The detailed descriptions clarify the differences, but the overlapping unofficial-actions and official-API surfaces still create ambiguity.
Most Instagram tools follow snake_case verb_noun naming with an instagram_ prefix, but the prefix is applied inconsistently (generic tools like authenticate, connect, and marketplace lack it) and verbs vary among actions_*, get_*, list_all_*, post_*, send_*, and create_*. The names are readable but do not form one predictable pattern.
33 tools is well above the 25-tool threshold, and the set includes several non-Instagram platform tools (marketplace, report_bug, show_version, toolkit_info) that belong to the MCP platform rather than an Instagram domain. The Instagram-specific surface is broad enough that splitting or trimming would improve coherence.
The server covers a broad range of Instagram workflows: auth, follow/unfollow, likes, comments, stories, messaging, media publishing, and insights. However, obvious lifecycle counterparts are missing—no unlike, no delete/update media, and no delete/unlike comments—so the surface has notable gaps.