Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Generate platform-native social posts that are humanized, AI-detection scored and illustrated.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
X-API-KeyValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http speedcontent-social https://speedcontent.online/mcp --header 'X-API-Key: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"speedcontent-social": {
"url": "https://speedcontent.online/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"speedcontent-social": {
"type": "http",
"url": "https://speedcontent.online/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
X-API-Key secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
The server did not answer when we last checked, so we could not read its tools.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 10, 2026
The registry name was verified with the GitHub account seotrader, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Did not respond within 6 seconds when we checked
Did not respond within 6 seconds when we checked
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: X-API-Key
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.1) reached the registry 38 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Screencast MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Let AI agents record the Windows screen, watch it as frames, and edit it with ffmpeg
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
Any model can write a LinkedIn post. The difference is what happens after:
| Step | What it does |
|---|---|
| Generate | Written against the platform's own style guide, not one prompt reskinned |
| Humanize | Rewritten so it doesn't read as machine-written |
| Detect | Scored 0–65 by an AI detector; 0 reads as human |
| Emoji | Platform-aware; suppressed on LinkedIn and YouTube |
| Re-humanize | Automatic retry if the score comes back too high |
| Image | Optional, generated to match the post |
The scoring pass is the point. The agent is told how human the copy reads *before* anything is published.
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 mcp add --transport http speedcontent-social \
https://speedcontent.online/mcp \ --header "X-API-Key: sc_your_key_here"
{
"mcpServers": { "speedcontent-social": { "url": "https://speedcontent.online/mcp", "headers": { "X-API-Key": "sc_your_key_here" } } } }
Authorization: Bearer sc_... works too, for clients that prefer it.
If you have already written the post, use score_text and humanize_text — they check and fix your own wording. Use generate_social_post when you need a draft written from scratch.
score_textScore any text against an AI detector. Returns 0–65, where 0 reads as human and above 30 is likely to be flagged. This is the measurement an agent cannot make for itself. 8 credits.
humanize_textRewrite text so it no longer reads as machine-written. Brand names, domains and anything listed in preserve are restored verbatim afterwards, because the humanizer rewrites whole sentences and splits names. 1 credit per 20 words, plus 8 if you pass score_after.
| Parameter | Notes |
|---|---|
text | Required. At least 10 characters. |
preserve | Exact lines that must survive — a tagline, a call to action, a closing question. |
brand_terms | Names the humanizer must not alter or split. |
score_after | Score the result and return it. Adds 8 credits. |
generate_social_postWrites a post from scratch. Starts a job and returns its id; collect the result with check_social_job. Costs credits.
| Parameter | Default | Notes |
|---|---|---|
topic | — | Required. What the post is about. |
platform | — | Required. facebook, instagram, twitter, linkedin, pinterest, youtube, tiktok. |
tone | friendly | professional, casual, friendly, humorous, inspirational, educational. |
language | English | Any language name. |
quantity | 1 | Up to 10 variations. |
word_count | per platform | 10–500. LinkedIn 100, YouTube 150, Facebook/Pinterest 75, Instagram/TikTok 50, X 40. |
generate_image | false over MCP | Adds 10 credits per post. |
detect_ai | automatic | Adds 8 credits per post. Automatic means 150+ words only — short posts score unreliably. |
humanize | automatic | Automatic scores the draft first and humanizes only if it would be flagged, which keeps your wording and saves a credit. |
emoji | automatic | Off on LinkedIn and YouTube, on elsewhere. |
preserve | — | Exact lines that must appear verbatim. |
brand_name, brand_description, brand_tone, brand_audience, brand_keywords | — | Optional brand voice. |
check_social_jobReturns the finished posts, or current progress while the job runs. Free.
list_social_platformsPlatforms with default lengths and emoji policy. Free, no network call.
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.
The live server runs inside the SpeedContent API service. This repo holds the registry manifest and a standalone stdio implementation.
| Path | What it is |
|---|---|
server.json | The MCP Registry manifest, pointing at the hosted endpoint |
src/index.ts | A standalone stdio server, for clients that can't do remote HTTP |
PUBLISHING.md | How 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, and carries the same five tools:
npm install && npm run build
SPEEDCONTENT_API_KEY=sc_... node dist/index.js
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.
MIT