Daily MCP server rankings from public npm, PyPI, and GitHub data.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
One MCP server from the current snapshot: stars, weekly downloads, growth, install hints from registry package metadata, and links (GitHub, npm/PyPI, its MCP Morning page). Identify by slug, owner/repo, GitHub URL, or registry name. Install snippets are unverified — we do not run servers.
Slug (e.g. browser-use-browser-use), GitHub URL, or owner/repo.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcpmorning https://mcpmorning.com/mcp
One MCP server from the current snapshot: stars, weekly downloads, growth, install hints from registry package metadata, and links (GitHub, npm/PyPI, its MCP Morning page). Identify by slug, owner/repo, GitHub URL, or registry name. Install snippets are unverified — we do not run servers.
| Argument | Type | Description |
|---|---|---|
| id* | string | Slug (e.g. browser-use-browser-use), GitHub URL, or owner/repo. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Slug (e.g. browser-use-browser-use), GitHub URL, or owner/repo."
}
},
"additionalProperties": false
}Today's MCP Morning newsletter: title, date, up to 5 featured items with links, and the archive URL. Snapshot date included. Editorial, not a test report.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Search the MCP Morning snapshot by name, slug, GitHub repo, description or registry name. limit≤25, paginate with offset. Returns snapshot date and mcpmorning.com page URLs. Does not mean MCP Morning ran the server.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | Substring to match. |
| offset | integer |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 100,
"minLength": 1,
"description": "Substring to match."
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
}
},
"additionalProperties": false
}Ranked MCP servers from the latest MCP Morning snapshot. list=most_used (weekly downloads + GitHub stars/forks), rising (week-over-week download growth; requires 25 stars or 1,000 prior-week downloads), or new (repo created in the last 30 days). Optional language (GitHub primary language) and category (database, browser, files, search, dev, comms, cloud, ai, commerce, marketing, memory, finance). limit≤25, paginate with offset. Returns snapshot date and item page URLs. Popularity only — MCP Morning does not run or test servers.
| Argument | Type | Description |
|---|---|---|
| list | string | Ranking to return: most_used, rising, or new. |
| limit | integer | Page size, max 25. |
| offset | integer | Number of rows to skip for pagination. |
| category | string | Job category slug or label: database (Databases & data), browser (Browser & web scraping), files (Files & documents), search (Search & knowledge), dev (Dev tools & GitHub), comms (Messaging & collaboration), cloud (Cloud & infrastructure), ai (AI models & media), commerce (Payments & commerce), marketing (Marketing & SEO), memory (Memory & context), finance (Finance & crypto). |
| language | string | Filter by GitHub primary language, e.g. TypeScript or Python. |
{
"type": "object",
"properties": {
"list": {
"enum": [
"most_used",
"rising",
"new"
],
"type": "string",
"default": "most_used",
"description": "Ranking to return: most_used, rising, or new."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1,
"description": "Page size, max 25."
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0,
"description": "Number of rows to skip for pagination."
},
"category": {
"type": "string",
"description": "Job category slug or label: database (Databases & data), browser (Browser & web scraping), files (Files & documents), search (Search & knowledge), dev (Dev tools & GitHub), comms (Messaging & collaboration), cloud (Cloud & infrastructure), ai (AI models & media), commerce (Payments & commerce), marketing (Marketing & SEO), memory (Memory & context), finance (Finance & crypto)."
},
"language": {
"type": "string",
"description": "Filter by GitHub primary language, e.g. TypeScript or Python."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 9, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.