SpeedContent Social

io.github.seotraderv0.1.0Updated Oct 2, 2026

Generate platform-native social posts that are humanized, AI-detection scored and illustrated.

VerifiedStreamable HTTPWeb executableMedia & DesignProductivity & Workflow

Overview

AI-generated overview

Lets an assistant draft platform-specific social media posts, rewrite them to read as human-written, score them for AI detection, and optionally add images.

What it does
Wraps the SpeedContent Social Post API so an assistant can generate posts for seven platforms (Facebook, Instagram, X, LinkedIn, Pinterest, YouTube, TikTok). Each post is written to the platform's conventions, rewritten to read as human-authored, scored 0-65 by an AI detector, and optionally illustrated. Generation runs as a job: generate_social_post returns an id, and check_social_job collects the result or progress. list_social_platforms returns platform defaults and emoji policy.
When to use it
Use it when you want social copy that is tuned per platform and checked for how machine-written it reads before publishing, rather than a single generic model prompt. Useful for marketing or content workflows that need multiple variations, brand voice, or optional images.
Requirements
A remote HTTP endpoint; nothing to install. Requires a SpeedContent API key sent in the X-API-Key header (Authorization: Bearer also works), created free at the provider's site. Network access to the hosted endpoint. An optional standalone stdio build exists for older clients and needs Node.js and the SPEEDCONTENT_API_KEY environment variable.
Before you install
The X-API-Key header carries a secret credential; keep it out of shared configs. Generation costs credits, with image generation and AI detection adding credits per post, so usage can spend money. Posts are generated by a third-party service, so topics and any brand details you supply are sent to that provider.

Installation

In SourceWeft

  1. Open SpeedContent Social in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "speedcontent-social": {
      "type": "http",
      "url": "https://generatecontentwithaiservice-g5zrtckfda-ue.a.run.app/mcp"
    }
  }
}

README

SpeedContent Social MCP

Give an AI agent the ability to write social media posts that don't read like AI wrote them.

An MCP server for the SpeedContent Social Post API. Agents can draft posts for seven platforms; each one is written to that platform's conventions, rewritten to read as human-authored, scored against AI detection, and optionally illustrated.

Listed in the official MCP Registry as io.github.seotrader/speedcontent-social.

Why this and not a plain model call

Any model can write a LinkedIn post. The difference is what happens after:

StepWhat it does
GenerateWritten against the platform's own style guide, not one prompt reskinned
HumanizeRewritten so it doesn't read as machine-written
DetectScored 0–65 by an AI detector; 0 reads as human
EmojiPlatform-aware; suppressed on LinkedIn and YouTube
Re-humanizeAutomatic retry if the score comes back too high
ImageOptional, generated to match the post

The scoring pass is the point. The agent is told how human the copy reads before anything is published.

Setup

This is a remote server — there is nothing to install. Get an API key at app.speedcontent.online/APIKeys (free credits on signup, no card), then point your client at the URL.

Claude Code

bash
claude mcp add --transport http speedcontent-social \  https://generatecontentwithaiservice-g5zrtckfda-ue.a.run.app/mcp \  --header "X-API-Key: sc_your_key_here"

Claude Desktop, Cursor, and other clients

json
{  "mcpServers": {    "speedcontent-social": {      "url": "https://generatecontentwithaiservice-g5zrtckfda-ue.a.run.app/mcp",      "headers": {        "X-API-Key": "sc_your_key_here"      }    }  }}

Authorization: Bearer sc_... works too, for clients that prefer it.

Tools

generate_social_post

Starts a job and returns its id. Generation takes 20–90 seconds; collect the result with check_social_job. Costs credits.

ParameterDefaultNotes
topic—Required. What the post is about.
platform—Required. facebook, instagram, twitter, linkedin, pinterest, youtube, tiktok.
tonefriendlyprofessional, casual, friendly, humorous, inspirational, educational.
languageEnglishAny language name.
quantity1Up to 10 variations.
word_countper platform10–500. LinkedIn 100, YouTube 150, Facebook/Pinterest 75, Instagram/TikTok 50, X 40.
generate_imagetrueAdds 10 credits per post.
detect_aiautomaticAdds 8 credits per post. Automatic means 150+ words only — short posts score unreliably.
brand_name, brand_description, brand_tone, brand_audience, brand_keywords—Optional brand voice.

check_social_job

Returns the finished posts, or current progress while the job runs. Free.

list_social_platforms

Platforms with default lengths and emoji policy. Free, no network call.

Credits

Per post: 20 base (up to 200 words), +1 per 10 words beyond 200, +10 for an image, +8 for AI detection. Multiplied by quantity. Refunded in full if generation fails.

A 100-word LinkedIn post with an image costs 30 credits.

What's in this repo

The live server runs inside the SpeedContent API service. This repo holds the registry manifest and a standalone stdio implementation.

PathWhat it is
server.jsonThe MCP Registry manifest, pointing at the hosted endpoint
src/index.tsA standalone stdio server, for clients that can't do remote HTTP
PUBLISHING.mdHow this gets published and listed

The stdio build is not on npm and isn't needed for normal use. It exists as a fallback for older MCP clients that only support subprocess transport:

bash
npm install && npm run buildSPEEDCONTENT_API_KEY=sc_... node dist/index.js

Reselling

Volume and white-label pricing is per post rather than per seat, and your users don't need SpeedContent accounts of their own. Get in touch.

Licence

MIT

Source: README.md at commit e2ca6c9

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 2, 2026