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

ghl-mcp-server-v2

by zackscriven

ghl_social_csv_upload

Upload a CSV of social media posts for bulk scheduling in GoHighLevel; provide a pre-encoded multipart/form-data payload.

Instructions

multipart/form-data upload, body.file (binary CSV) required — there is no URL-based alternative for this endpoint (unlike media upload). This tool does not construct the multipart payload for you; the body argument is sent to GHL verbatim as the request body, so the caller must already have a valid pre-encoded multipart/form-data payload (with boundary) to pass through. Upload CSV Upload a CSV file containing social media posts for bulk scheduling Endpoint: POST /social-media-posting/{locationId}/csv (Version header: v3; source: v3/social-planner-v3.json) Requires a Sub-Account (location) token. OAuth scopes: socialplanner/csv.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": {
      "locationId": "<locationId>",
      "body": "<body>"
    },
    "name": "ghl_social_csv_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).
locationIdYesLocation ID (also known as Sub-Account ID) for the business location.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / file / anyOf
      Added value: +[
      +  {
      +    "description": "CSV file to upload containing social media posts",
      +    "example": "sample.csv",
      +    "format": "binary",
      +    "type": "string"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "filePath": {
      +        "type": "string"
      +      },
      +      "filename": {
      +        "type": "string"
      +      },
      +      "mimeType": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "filePath"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedInput schema / properties / body / properties / file / example
      Removed value: -"sample.csv"
    • removedInput schema / properties / body / properties / file / format
      Removed value: -"binary"
    • removedInput schema / properties / body / properties / file / type
      Removed value: -"string"
    • changedInput schema / properties / locationId / description
      Previous value: -"Location Id"New value: +"Location ID (also known as Sub-Account ID) for the business location."
    • addedInput schema / properties / locationId / example
      Added value: +"ve9EPM428h8vShlRW1KT"
  2. First observedv2.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (which only say non-readonly, non-idempotent, openWorld) by disclosing the auth requirement (Sub-Account token), the OAuth scope (socialplanner/csv.write), and critically that the body is passed verbatim as a pre-encoded multipart payload with boundary — a real behavioral trap an agent must know.

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?

The most important constraint (no payload construction, pre-encoded multipart) is front-loaded, followed by concise purpose and metadata lines. The endpoint/version/source boilerplate is slightly redundant but small.

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?

Covers upload mechanics, auth, and scopes well for a mutation tool with no output schema. The notable gap is the surrounding workflow — it doesn't indicate that a finalize/list step likely follows, which matters for this bulk-scheduling endpoint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3), but the description adds crucial semantics the schema obscures: `body` is not constructed by the tool and must already be a valid boundary-terminated multipart/form-data payload. This corrects a misleadingly simple nested-object schema.

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?

States a specific verb and resource ('Upload a CSV file containing social media posts for bulk scheduling') plus the endpoint and version. It proactively distinguishes itself from the media upload sibling by noting there is no URL-based alternative for this endpoint.

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?

Gives clear context: CSV upload for bulk scheduling, sub-account token required, and explicitly contrasts with the media upload endpoint's URL option. It does not, however, reference the related csv_finalize / csv_list siblings that an agent would likely need next.

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