score_tweetLABSCO SUMMARY
The weights are the argument.
Advice about posting is usually taste; this one quotes the signal weights out of the open-source ranking code and scores against them, which makes a claim you can check rather than agree with. The numbers reward what the code rewards — a reply is worth 27.0× while a report is -369× — so read the score as a fit to those weights, not as a prediction of reach.
What it is
A toolkit built on X's open-source recommendation algorithm, shipped as a React web app and an MCP server. The MCP half puts the scoring engine behind eleven tools, so an assistant can score a draft, test its opening line, check it against the quality filters and plan posting cadence.
What you get
- A draft scored against the algorithm's signal weights —
score_tweet, andfull_auditfor everything at once - The opening line tested on its own, against the penalty that fires when a reader scrolls past —
analyze_hook - The 18 quality and safety gates run over a draft —
check_filters, withdetect_spam_patternsalongside - Posting cadence from the author-diversity decay formula —
diversity_penaltyandget_optimal_schedule - Two drafts compared, a niche classified, and thread strategy —
compare_tweets,classify_niche,get_thread_strategy - The raw reference data as MCP resources —
x-algorithm://weights,x-algorithm://filters,x-algorithm://niches - The weights themselves, named and signed: Reply at 27.0×, Bookmark at 10.0×, Follow at 4.0×, against Report at -369× and Not Interested at -74×
Requirements
For the MCP server, Node: build it from the mcp folder of your clone (cd mcp && npm install && npm run build) and point your client at mcp/dist/index.js. The README's npx and global npm install lines name a package npm does not have. No key is needed for scoring, filters and analysis. The web app is separate: clone, npm install, npm run dev, and it opens on http://localhost:5173; its AI rewrite, generate and thread features are the only part that takes an API key, added in Settings.
Setup effort
Build from source — git clone https://github.com/MrChartist/x-algorithm-toolkit.git
USE CASES
01
Editing a draft before it goes out
Score the draft, then rewrite the parts that lose the most against the weights.
02
Fixing a weak opening line
Test the hook on its own against the scroll-past penalty before rewriting the rest.
03
Checking a post will not trip a filter
Run the quality and safety gates over the draft and look for spam patterns first.
04
Planning how often to post
Read the diversity penalty and the suggested schedule rather than guessing at cadence.
05
Choosing between two drafts
Put both through the same scoring and compare them directly.
11 tools
Listed in project docs. Your client may show a different list.
check_filtersanalyze_hookget_signalsget_optimal_schedulecompare_tweetsdetect_spam_patternsdiversity_penaltyclassify_nicheget_thread_strategyfull_auditBEFORE YOU INSTALL
What to know first
Tools you get
11 tools named in the project's documentation.
Requires
Node.js with npm, to build the mcp/ folder and run mcp/dist/index.js
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/MrChartist/x-algorithm-toolkit.git
cd x-algorithm-toolkit
cd mcp && npm install && npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"x-algorithm": {
"command": "node",
"args": [
"<YOUR_PATH_TO_X_ALGORITHM_TOOLKIT>/mcp/dist/index.js"
]
}
}
}<YOUR_PATH_TO_X_ALGORITHM_TOOLKIT> is the full path of your clone.
