Product Hunt Launches Feed MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | Yes | Your Apify API token, obtained from https://console.apify.com/account/integrations. Required to run the actor; the server lists its tool without a token but a call needs one. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_product_hunt_launchesA | Get the Product Hunt launches of the days you pick, one flat row per launch: name, tagline, daily rank, votes, comments, topics, maker names with their headlines, maker profile links, the product's website and company domain, and its X and LinkedIn links, plus one free summary row per day. Filter by topic, keyword, or minimum votes; only_new returns only launches an earlier run did not. Public pages are read through the Apify proxy with robots.txt obeyed; an optional Product Hunt developer token of your own reads the daily lists from the official API and adds unfeatured launches. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN and is billed per launch row. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between overlapping tools. Its purpose (fetch Product Hunt launch rows for chosen days with filters) is stated unambiguously in the description.
The single name get_product_hunt_launches follows a clear verb_noun snake_case convention. With one tool there is no risk of mixed conventions, and the name is self-describing.
The domain is a single read-only feed operation, and the one tool absorbs filtering, topic/keyword/vote thresholds, and incremental 'only_new' behavior, so it genuinely earns its place rather than being a trivial wrapper. It is still a one-tool surface, which feels thin if consumers later want per-product detail or comment retrieval.
For a feed reader the surface is largely complete: daily rows, maker metadata, links, topic/keyword/vote filters, incremental runs, and error reporting with run IDs. Minor gaps remain around deeper per-launch detail (e.g., comment bodies or multi-day historical backfill beyond the picked days), but core read workflows are covered.