Questions it answers
Post Stats reads the public numbers of social posts: views, likes, comments, shares and saves, and when each post went up. It covers YouTube videos and Shorts, TikTok videos and X posts.
Every number says where it came from (the watch page, the channel page, the video page, a free API) and when it was read, and whether the platform rounded it (5.8M is not exact). A number the platform does not show to a logged-out visitor is listed under not_public with the reason, never guessed.
compare_posts ranks up to 10 posts by views, across platforms, with likes per thousand views, so you can see which videos to make more of. list_channel_stats lists the latest posts of a YouTube channel with their views, and a TikTok profile's totals.
On YouTube and TikTok it reads only public pages, as a logged-out visitor would, names itself as PostStats/1.0 (+https://tools.openkrill.app/; support@openkrill.app) and honours robots.txt on the pages it reads. X posts are read through X's public guest API, as the X post reader does. It never signs in, passes a bot check or runs page scripts, spaces out its requests to each platform, and keeps each answer for 15 minutes. When a platform changes its page so the numbers are no longer where the reader looks, the answer is a shape_changed error, not a wrong number.
Free, and nothing about the caller is stored.
The idea behind it, in one live picture: how Post Stats works.
What it can do
- Views, likes, comments, shares, saves and post time of one YouTube, TikTok or X post
- The source and read time of every number, and whether the platform rounded it
- Ranks 2 to 10 posts by views across platforms, with likes per thousand views
- Lists the latest Shorts and videos of a YouTube channel with their views
- Says which numbers a platform keeps private, and why, instead of guessing
Tools
get_post_stats, Get a post's public stats. Read the public numbers of one post: views, likes, comments, shares, saves and the post time, for a YouTube video or Short, a TikTok video, or an X post. Each number comes with its source (which public page or free API), when it was read, and whether the platform rounded it. Numbers the platform keeps private are listed in not_public with the reason. It never signs in, so private posts and account analytics are out of reach.compare_posts, Compare posts by views. Read 2 to 10 public posts (YouTube, TikTok and X can be mixed) and rank them by views, with likes per thousand views for each. Every row has the same fields as get_post_stats; a post that could not be read stays in the list with its error, ranked last.list_channel_stats, List a channel's latest posts. List the latest posts of a YouTube channel with the view count its public channel page shows, newest Shorts first, then videos. For a TikTok profile it returns followers, total likes and video count (TikTok's public profile page lists no videos). X timelines need a login, so an X profile is refused with the reason.
Add Post Stats in Pi
Pi does not speak MCP on its own. The pi-mcp-adapter extension (these steps match version 2.34.0) loads remote servers and keeps their schemas out of the prompt until you ask. Install it once, then restart Pi:
pi install npm:pi-mcp-adapterAdd the server to a shared MCP file. Use .mcp.json in the project if only that project needs Post Stats, or ~/.config/mcp/mcp.json if you want it in every project. Pi also reads ~/.agents/mcp.json. A Pi-only override lives in ~/.pi/agent/mcp.json or .pi/mcp.json and wins over the shared file.
{
"mcpServers": {
"post-stats": {
"url": "https://poststats.openkrill.app/mcp",
"lifecycle": "eager"
}
}
}The url is enough. Do not set command: that field is for a local process. No API key header. lifecycle is eager so Pi connects at startup and can search tool names before the first call. A config that omits it still works: the first call connects. After restart, run /mcp and confirm the server is listed. Ask: How many views does https://www.youtube.com/shorts/8bE_lGbtjyY have? The adapter should offer get_post_stats, compare_posts, list_channel_stats.
Leave directTools off unless you want those schemas in every turn. With a handful of tools the cost is small. The default proxy is the better fit: search for the tool, then call it. /mcp disable post-stats writes a project override in .pi/mcp.json without editing the shared file. Run /reload after that change.
Pi will not find this server by scanning Cursor or Claude config unless you run /mcp setup and import it. Putting the url in .mcp.json is the direct path and the one this page tests against. The server is the same public endpoint the other clients use, with the same limits and the same privacy rules.
If it does not work
The tool does not show up
Run /mcp to see the servers the adapter loaded. If it is missing, check the url entry in .mcp.json, then run /reload or restart Pi.
429 or rate_limited
Each server takes 60 calls a minute from one network, and some tools take fewer. Past that the call comes back as a tool error that starts with rate_limited: wait a minute and ask again. daily_limit means the server reached its shared daily cap, which resets at 00:00 UTC. A limit is not an answer, so do not read it as no results. For higher limits, ask support@openkrill.app for a key.
A call checked on 2026-10-11
A public Short on our own Daily Chart Facts channel, so the example reads our post and no one else's. The request below was posted to https://poststats.openkrill.app/mcp as tools/call. HTTP 200. Source: the Post Stats server, read 2026-10-11.
{
"method": "tools/call",
"params": {
"name": "get_post_stats",
"arguments": {
"url": "https://www.youtube.com/shorts/8bE_lGbtjyY"
}
}
}- status. ok
- title. How fast is solar power growing? #shorts
- url. https://www.youtube.com/watch?v=8bE_lGbtjyY
Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.
Using it in production
Nothing to install and nothing to run: no package, no Python or Node.js version and no environment variable. Post Stats runs on our servers, and your client only needs the URL https://poststats.openkrill.app/mcp.
| Rate limit | 60 tool calls a minute from one network. initialize and tools/list do not count. |
|---|---|
| Daily cap | 5000 tool calls a day per server, shared by every caller. It resets at 00:00 UTC. |
| At a limit | The call comes back as a tool error that starts with rate_limited (wait a minute) or daily_limit (try after 00:00 UTC), never as a partial answer. |
| Key | None. Do not add an Authorization header or a key field. |
| Higher limits | Email support@openkrill.app with the server name, the calls a day you expect and what they are for. We answer within 1 business day. |
| Freshness | Some answers come from a short cache. Each guide shows the date of its checked call; repeat a call when you need a newer reading. |
| Uptime | Scheduled test calls check the servers through the same endpoint. There is no SLA yet. |
| Data | What each server receives and keeps is on the privacy page. |
Use it in other apps
Frequently asked questions
How do I install the Post Stats MCP server in Pi?
Run pi install npm:pi-mcp-adapter once, add post-stats with the url https://poststats.openkrill.app/mcp to .mcp.json, then restart Pi and run /mcp to see it.
Do I need an API key to run Post Stats in Pi?
No. This server takes no API key. For higher limits, email support@openkrill.app with the server name (Post Stats), the calls a day you expect and what they are for. We answer within 1 business day.
What should I do if Post Stats does not connect in Pi?
Check that the entry has a url and no command field, then run /reload or restart Pi and run /mcp.