Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_social_create_comment

Create top-level comments on social posts or reply to existing comments across supported platforms, with platform-specific content limits and optional mentions or attachments where supported.

Instructions

Create a comment or reply Create a top-level comment on a post (isParentThread: true, parentId = postId) or a reply to an existing comment (isParentThread: false, parentId = commentId). Per-platform content max length: Facebook 8000, Instagram 2200, Linkedin 3000, Community 8000, Tiktok 150, Bluesky 300, Youtube 10000, Threads 500.

Optional-field platform support:

  • attachments — supported on Facebook only. Ignored on Instagram, LinkedIn, TikTok, Bluesky, Community (Community processes the field but external URLs are not rendered due to its bucket restriction).

  • mentions — supported on Facebook, LinkedIn, and Community only. Ignored on Instagram, TikTok, Bluesky.

  • notifyAllGroupMembers — supported on Community only. When true, all group members get a push/in-app notification (equivalent to an @everyone broadcast). Independent of the mentions array and of @everyone text in content. Default false. Endpoint: POST /social-media-posting/comments/{platform} (Version header: v3; source: v3/social-planner-v3.json) Requires a Sub-Account (location) token. OAuth scopes: socialplanner/comments.write

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "platform": "<platform>",
      "locationId": "<locationId>",
      "body": "<body>"
    },
    "name": "ghl_social_create_comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).
platformYesSupported Comments Platforms
locationIdYesLocation ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed17 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / attachments / example
      Added value: +[
      +  {
      +    "type": "image",
      +    "url": "https://example.com/image.jpg"
      +  }
      +]
    • addedInput schema / properties / body / properties / attachments / items / title
      Added value: +"AttachmentDTO"
    • changedInput schema / properties / body / properties / content / example
      Previous value: -"This is a comment"New value: +"Great post, Alex Morgan!"
    • changedInput schema / properties / body / properties / mentions / description
      Previous value: -"Mentions for the comment. **Supported on:** Facebook, LinkedIn, Community. **Ignored on:** Instagram, TikTok, Bluesky — the field is accepted but mentions are not rendered on these platforms."New value: +"Mentions for the comment. **Supported on:** Facebook, LinkedIn, Community. **Ignored on:** Instagram, TikTok, Bluesky — the field is accepted but mentions are not rendered on these platforms.\n\n`offset`/`length` must locate `name` inside `content` exactly — `content.substring(offset, offset + length) === name` — otherwise the request is rejected with 400. The example below aligns with the `content` example above."
    • addedInput schema / properties / body / properties / mentions / example
      Added value: +[
      +  {
      +    "id": "102694781978972",
      +    "length": 11,
      +    "name": "Alex Morgan",
      +    "offset": 12
      +  }
      +]
    • changedInput schema / properties / body / properties / mentions / items / properties / length / description
      Previous value: -"Mention length"New value: +"Character length of `name` — `content.substring(offset, offset + length)` must equal `name`."
    • changedInput schema / properties / body / properties / mentions / items / properties / length / example
      Previous value: -"106"New value: +11
    • changedInput schema / properties / body / properties / mentions / items / properties / name / description
      Previous value: -"Mention name"New value: +"Mention name. Must appear verbatim in `content` at `offset`."
    • changedInput schema / properties / body / properties / mentions / items / properties / name / example
      Previous value: -"Test"New value: +"Alex Morgan"
    • changedInput schema / properties / body / properties / mentions / items / properties / offset / description
      Previous value: -"Mention offset"New value: +"Zero-based character index in `content` where `name` starts. For content `\"Great post, Alex Morgan!\"` the mention `\"Alex Morgan\"` starts at 12."
    • changedInput schema / properties / body / properties / mentions / items / properties / offset / example
      Previous value: -"106"New value: +12
    • addedInput schema / properties / body / properties / mentions / items / title
      Added value: +"MentionsDTO"
    • changedInput schema / properties / body / properties / parentId / description
      Previous value: -"For top-level comments (`isParentThread: true`): pass the post ID returned by the posts API. For replies (`isParentThread: false`): pass the parent comment ID returned by the list-comments API. In both cases this must be a valid 24-character Highlevel ID — not the native platform ID."New value: +"For top-level comments (`isParentThread: true`): pass the post ID returned by the posts API. For replies (`isParentThread: false`): pass the parent comment ID returned by the list-comments API. In both cases this must be a valid 24-character internal ID — not the native platform ID."
    • addedInput schema / properties / body / properties / pollOptions
      Added value: +{
      +  "description": "Poll options for Threads reply (2-4 options)",
      +  "example": {
      +    "option_a": "Yes",
      +    "option_b": "No",
      +    "option_c": "Maybe"
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / body / properties / textAttachment
      Added value: +{
      +  "description": "Text attachment for Threads reply with optional styling info",
      +  "example": {
      +    "plaintext": "Styled text content",
      +    "textWithStylingInfo": [
      +      {
      +        "length": 5,
      +        "offset": 0,
      +        "styling_info": [
      +          "bold"
      +        ]
      +      }
      +    ]
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / body / properties / threadLocationId
      Added value: +{
      +  "description": "Location ID for Threads reply location tagging",
      +  "example": "123456",
      +  "type": "string"
      +}
    • addedInput schema / properties / body / title
      Added value: +"CommentsCreateBodyDTO"
  2. First observedv2.0.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare write/non-idempotent/open-world, but the description goes well beyond them: it discloses that attachments and mentions are silently accepted-but-ignored on unsupported platforms (a significant no-op trap), per-platform content ceilings, and the notifyAllGroupMembers broadcast semantics for Community. It also states the auth prerequisites (Sub-Account token, socialplanner/comments.write scope) and the endpoint/version, which annotations cannot convey.

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-loaded with the core create-comment/reply distinction before the platform matrix, and the bolded field headers make it scannable. It is somewhat long and duplicates platform-support text already present in the schema, but every block is decision-relevant rather than filler.

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 a nested-DTO write tool with no output schema, the description covers the pieces an agent would otherwise guess at: the two creation modes, per-platform constraints, silently-ignored optional fields, authentication requirements, and the target endpoint. Nothing essential to a correct call is left implicit.

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 coverage is 100% and the nested DTO descriptions already document platform support, mention offset/length constraints, and the 24-char internal-ID requirement. The description largely restates that same platform-support matrix rather than adding new semantics, so the baseline 3 for high-coverage schemas applies.

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 ("Create a comment or reply") and immediately disambiguates the two modes via isParentThread/parentId semantics. An agent can distinguish this from ghl_social_post_create (posts vs comments) and ghl_social_get_comment_list (read vs write) without opening any schema.

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?

Explicit routing between top-level comment and reply, including which ID to supply for each case, so the agent can pick the right mode. It stops short of naming sibling tools as alternatives (e.g. directing to the list-comments endpoint to obtain a parent comment ID), so no explicit when-not-to-use guidance.

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

Deploy Server

Other Tools