analyze_profileLABSCO SUMMARY
Judgement about a profile, not a metrics dump.
Worth being clear about what the numbers are: the vendor describes engagement rates and hashtag popularity as estimates, which makes this a tool for direction — which themes land, when to post, which tags belong together — rather than a substitute for the platform's own analytics. The server asking for your own OpenAI key tells you where the analysis actually happens.
What it is
Four analysis tools over social media presence, run as a server you host yourself. Each one returns an interpretation — patterns, estimates, recommendations — rather than a platform export, and the vendor's own descriptions say so: engagement rates and hashtag popularity come back as estimates.
What you get
- A profile and brand read: posting patterns, content themes, audience indicators and growth recommendations
- Engagement scoring: rate estimates, content effectiveness, posting-time analysis and benchmarks
- Trend detection: viral content patterns, emerging topics, sentiment shifts and opportunity alerts
- Hashtag research: popularity estimates, related tags, niche classification and recommended sets
Requirements
Bun, an OpenAI API key and an admin secret, since the analysis runs on a model. The server mints its own API keys through /api/keys/provision; send the key as the x-api-key header to http://localhost:4202/mcp.
Setup effort
Build from source — git clone https://github.com/ezbiz-services/mcp-social-media.git
USE CASES
01
Sizing up a competitor's presence
Point it at their handle on one platform and get posting cadence, recurring themes and audience signals back as a description you can act on rather than a follower count.
02
Working out why posts stopped landing
Score engagement against benchmarks and read the posting-time analysis, which is usually where a drop turns out to be schedule rather than content.
03
Deciding what to publish this week
Check what is emerging in your niche and where sentiment has moved, then use that to pick the angle before writing rather than after.
04
Building the tag set for a campaign
Research the tags for a topic and get a recommended set with related ones and a niche classification, instead of copying whatever the last post used.
05
Preparing a client pitch
Read the prospect's profile, score its engagement, and pair both with current trends in their category — the three pieces a pitch deck usually needs and nobody has time to assemble.
4 tools
Listed in project docs. Your client may show a different list.
score_engagementdetect_trendsresearch_hashtagsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- Bun
- An OpenAI API key
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/ezbiz-services/mcp-social-media.git
cd mcp-social-media
bun install
cp .env.example .envSet OPENAI_API_KEY and ADMIN_SECRET in .env
TERMINAL
bun run server.tsLeave that server running, and in a second terminal mint the API key your client sends as x-api-key:
TERMINAL
curl -X POST http://localhost:4202/api/keys/provision -H "x-admin-secret: <YOUR_ADMIN_SECRET>" -H "Content-Type: application/json" -d '{"email":"<YOUR_EMAIL>","tier":"business"}'MCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"social-media-analytics": {
"url": "http://localhost:4202/mcp",
"headers": {
"x-api-key": "<YOUR_API_KEY>"
}
}
}
}
