Upload-Post

Official

by Upload-Post

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Hide, like or pin a comment

comment_action

Destructive

Moderate or react to comments on your own posts across TikTok, Facebook, Instagram, YouTube, and Threads by hiding, liking, pinning, editing, approving, or holding them with a confirmation preview.

Instructions

Moderate or react to a comment on one of the profile's own posts. One endpoint for every network, chosen with platform; each network supports its own verbs and answers 400 platform_not_supported / invalid action otherwise. TikTok: hide/unhide (postId), like/unlike (no postId), pin/unpin (postId). Facebook: hide/unhide, like/unlike, edit (needs message). Instagram: hide/unhide a comment, or enable_comments/disable_comments on a post (postId, no commentId). YouTube: hide/unhide/hold (postId; banAuthor only with hide). Threads: hide/unhide, approve/ignore. Most actions have an inverse; edit does not keep the previous text and banAuthor bans the commenter from the YouTube channel, so both need the user's approval of the exact change. Deleting a comment is a different tool: delete_comment. TikTok: Requires the 'comments' capability on the profile's TikTok account (see the capabilities array in list_users). It is granted at connection time, so an account connected earlier has to reconnect TikTok before this works. Needs the user's approval: call it first without confirmed to get a preview (nothing is sent), show the user exactly what will go out, and repeat the call with confirmed: true only after they approve.

Input Schema

Name	Required	Description
`user`	Yes	Upload-Post profile name.
`action`	Yes	What to do. Lowercase; each value already carries its direction, so there is no separate 'undo' flag. Which values a platform accepts is listed in the tool description.
`postId`	No	Post the comment belongs to (TikTok: the video id). Required for TikTok hide/unhide and pin/unpin, YouTube moderation and Instagram enable_comments/disable_comments; not used by like/unlike.
`message`	No	Facebook `edit` only: the new comment text.
`platform`	Yes	Social platform the comment lives on.
`banAuthor`	No	YouTube `hide` only: also ban the comment's author from the channel.
`commentId`	No	Comment to act on (from get_post_comments). Sent as `comment_id`. Required except Instagram enable_comments/disable_comments.
`confirmed`	No	Set to true only after the user has seen the preview this tool returns without it and approved it. Without it nothing is sent.

Output Schema

Name	Required	Description	Default
`result`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.17.2Oct 29, 2026

addedInput schema / properties / confirmed

Added value: +{
+  "description": "Set to true only after the user has seen the preview this tool returns without it and approved it. Without it nothing is sent.",
+  "type": "boolean"
+}

Changed8 schema fields changedv0.11.4Oct 1, 2026

changedInput schema / properties / action / description

Previous value: -"What to do. Lowercase; each value already carries its direction, so there is no separate 'undo' flag."New value: +"What to do. Lowercase; each value already carries its direction, so there is no separate 'undo' flag. Which values a platform accepts is listed in the tool description."

changedInput schema / properties / action / enum

Previous value: -[
-  "hide",
-  "unhide",
-  "like",
-  "unlike",
-  "pin",
-  "unpin"
-]New value: +[
+  "hide",
+  "unhide",
+  "like",
+  "unlike",
+  "pin",
+  "unpin",
+  "edit",
+  "hold",
+  "approve",
+  "ignore",
+  "enable_comments",
+  "disable_comments"
+]

addedInput schema / properties / banAuthor

Added value: +{
+  "description": "YouTube `hide` only: also ban the comment's author from the channel.",
+  "type": "boolean"
+}

changedInput schema / properties / commentId / description

Previous value: -"Comment to act on (from get_post_comments). Sent as `comment_id`."New value: +"Comment to act on (from get_post_comments). Sent as `comment_id`. Required except Instagram enable_comments/disable_comments."

addedInput schema / properties / message

Added value: +{
+  "description": "Facebook `edit` only: the new comment text.",
+  "type": "string"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "tiktok"
-]New value: +[
+  "tiktok",
+  "facebook",
+  "instagram",
+  "youtube",
+  "threads"
+]

changedInput schema / properties / postId / description

Previous value: -"Post the comment belongs to (TikTok: the video id). Required for hide/unhide and pin/unpin; not used by like/unlike."New value: +"Post the comment belongs to (TikTok: the video id). Required for TikTok hide/unhide and pin/unpin, YouTube moderation and Instagram enable_comments/disable_comments; not used by like/unlike."

changedInput schema / required

Previous value: -[
-  "user",
-  "platform",
-  "commentId",
-  "action"
-]New value: +[
+  "user",
+  "platform",
+  "action"
+]

Addedv0.11.1Sep 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare destructiveHint=true and openWorldHint=true, and the description goes well past them: it warns that `edit` does not retain prior text, that `banAuthor` bans the commenter channel-wide, that unsupported combos return 400 `platform_not_supported`, that TikTok actions need the 'comments' capability granted at connection time (with reconnect required), and that nothing is sent until `confirmed: true`.

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-loads the primary intent and the `platform` selector, and every sentence carries real information. The dense platform-by-platform enumeration and the capability paragraph make it long and somewhat run-on for a description that must be parsed quickly, but there is little wasted text.

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 an 8-parameter, 5-platform polymorphic mutation tool with an output schema, the description covers the aspects the schema cannot: platform/action compatibility, capability prerequisites, error behavior, irreversibility of edit and banAuthor, and the two-step confirmation protocol. Nothing an agent needs to invoke it safely is missing.

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 description coverage is 100%, so the baseline would be 3, but the description adds conditional semantics the schema only partially captures — postId applicability per platform/action, `message` being Facebook-edit-only, `banAuthor` valid only with YouTube hide, and commentId being unnecessary for Instagram enable_comments/disable_comments.

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?

Opens with a specific verb+resource ('Moderate or react to a comment on one of the profile's own posts') and explicitly frames this as one polymorphic endpoint selected by `platform`. It distinguishes itself from the sibling per-action tools (hide_comment, like_comment, pin_comment) and from delete_comment by naming that tool as a different operation.

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?

Gives an explicit per-platform matrix of supported actions (TikTok hide/like/pin, Facebook edit, Instagram enable_comments, YouTube hold, Threads approve/ignore) and states the failure mode when an action isn't supported. It also spells out the decision procedure for the approval flow: call without `confirmed` first to preview, then repeat with `confirmed: true` after user approval.

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

Deploy Server