Find products launched since ChatGPT by what they do, and see what people said about them.
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.
Get one product by id: full description, links, GitHub repository and stars, whether its link responded when last checked, and every reaction with its source, title, number, date, and original discussion URL.
Product id from search_products or similar_products
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http tangerine-index https://tangerineindex.com/mcp
Get one product by id: full description, links, GitHub repository and stars, whether its link responded when last checked, and every reaction with its source, title, number, date, and original discussion URL.
| Argument | Type | Description |
|---|---|---|
| id* | string | Product id from search_products or similar_products |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[0-9a-f]{10}$",
"description": "Product id from search_products or similar_products"
}
}
}Find existing products launched since ChatGPT's release (Nov 30, 2022) that already do what you need — check here before building something new. Describe the job in short plain English, e.g. "extract tables from PDF to CSV" or "self-hosted dashboard for coding agents"; English works much better than other languages. Results are ranked by relevance (keyword + semantic). Each result has a one-line description, links, forms, an open-source flag, and community reactions labeled by source (e.g. HN 112 pts). Numbers are shown as each source reports them and are never combined; Tangerine Index does not rate products. Use get_product for the full description and every reaction.
| Argument | Type | Description |
|---|---|---|
| need* | string | What the product should do, as a short plain-English description, e.g. "extract tables from PDF to CSV" |
| forms | array | Only return products that have ALL of these forms |
| limit | integer | Maximum number of results (default 8) |
| open_source | boolean | true: only open-source products (GitHub repositories); false: only the others |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"need"
],
"properties": {
"need": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "What the product should do, as a short plain-English description, e.g. \"extract tables from PDF to CSV\""
},
"forms": {
"type": "array",
"items": {
"enum": [
"CLI",
"Library",
"Desktop",
"Mobile",
"Browser Extension",
"Self-hosted"
],
"type": "string"
},
"maxItems": 6,
"description": "Only return products that have ALL of these forms"
},
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Maximum number of results (default 8)"
},
"open_source": {
"type": "boolean",
"description": "true: only open-source products (GitHub repositories); false: only the others"
}
}
}List up to 5 products whose descriptions are closest to the given product's description. Similarity is by description embedding only — not quality, popularity, or recency.
| Argument | Type | Description |
|---|---|---|
| id* | string | Product id from search_products or similar_products |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[0-9a-f]{10}$",
"description": "Product id from search_products or similar_products"
}
}
}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 1, 2026.