
HotRepo MCP server
Which MCP servers are HotRepo's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry nameai.hotrepo/hotrepoverified in the MCP registry
The registry name sits under hotrepo.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools6
- Server calls itselfHotRepo
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 546 ms.
- Its tools do every use case we checked: read AI-written reviews before trying a project; scan trending topics and reports for new projects.
Once connected
- Parameters are untyped or undescribed in 3 of 7 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score98 of 100answers 100 · does the job 100 · definitions 93 · context 100 · connects 100
- What an agent can do with it2 of 2 use cases
- Answered100% of days7 of 7 daily checks
- Median first answer489 ms
- Space in an agent's context≈ 1,527 tokensthe definitions of all its tools (7), which an agent carries on every turn
- Tool definitionsA · 93 of 100
- Typed results7 of 7 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 7
What an agent can do with it
- not sure · browse trending GitHub repositories by language and time range
- can do · read AI-written reviews before trying a project
- can do · scan trending topics and reports for new projects
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_trendingGet a HotRepo trending board: the repositories on GitHub Trending (or HotRepo's new-repository board) for one UTC day, ranked by stars gained in the period, each with HotRepo's one-line review when available. best_github_rank_that_day is…
get_repoRead HotRepo's full review of a repository (Markdown), with its stats, topic, daily trending history (the all-languages board; each day's best_github_rank_that_day is the best position it reached on GitHub's page that day, null before…
search_reposSearch repositories that HotRepo has reviewed, newest reviews first. Use get_repo for the full review.
list_topicsList HotRepo's topics (each reviewed project belongs to exactly one, by what it helps people do) with the number of reviewed projects in each.
get_topicList reviewed repositories in one topic, most recently trending first.
get_monthly_reportGet a HotRepo monthly report: the repositories that gained the most stars on the daily trending board during a month, the most notable new repositories, and leaders per topic, with an editorial introduction.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"hotrepo": {
"type": "http",
"url": "https://hotrepo.ai/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http hotrepo https://hotrepo.ai/mcpclaude.ai, ChatGPT and other clients: add https://hotrepo.ai/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.