mcpField
S
stierproducts tier lists

stierproducts tier lists

Remote
stierproducts.comSearch0Updated 10w ago

About stierproducts tier lists

stierproducts tier lists is a read-only MCP server for researching cited S-to-F rankings across product categories. It helps shoppers and researchers find products, compare options, and inspect each placement’s sources.

Key features

  1. 01Browse categories and product counts
  2. 02Search products by text
  3. 03Retrieve full category rankings
  4. 04Inspect product citations and links
  5. 05Compare products within a category
  6. 06Find low-tier products and reasons

Use cases

  1. 01Explore rankings in an unfamiliar category
  2. 02Check sources behind a product placement
  3. 03Compare several products in one category
  4. 04Identify products ranked D or F

MCP support

Exposes six read-only tools to MCP clients for category discovery, product search, rankings, comparisons, citations, and low-tier results.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.stierproducts.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

6
ParameterTypeRequiredDescription
limitintegerNo
querystringNoOptional filter matched against the category name and description.

Details

From the project README

stierproducts MCP connector

The read-only Model Context Protocol server for stierproducts, a review aggregator that publishes one S-to-F tier list per product category. Every placement is cited.

  • Endpoint (streamable HTTP): https://mcp.stierproducts.com/mcp
  • Official MCP Registry name: com.stierproducts/tier-lists
  • Documentation: https://stierproducts.com/mcp
  • No key, no account, no authentication. Rate limited by IP at 120 requests per minute.

This repository holds the registry manifest and the client configurations. The server code and the research pipeline are not published here.

Install

ClientHow
Claude Codeclaude mcp add --transport http stierproducts https://mcp.stierproducts.com/mcp
Claude DesktopSettings, Connectors, Add custom connector, paste the endpoint
ChatGPTSettings, Plugins, search "stierproducts", turn it on
Cursorclients/cursor.json, or Settings, MCP, Add new global MCP server
VS Codeclients/vscode.json into .vscode/mcp.json
Any other clientclients/mcpServers.json

Tools

All six are read-only.

ToolReturns
list_categoriesEvery board, with product counts and research dates. Call this first, the slugs are not guessable.
search_productsSlug, name, brand, category and tier for a free-text query.
get_tier_listA whole board: every product, rank, tier, LP, verdict and outlet count, plus the prose summary.
get_productOne product in full, with its citation list, link statuses and what it beat.
compare_productsTwo to five products side by side. Refuses to compare across categories.
what_to_avoidThe D and F tiers for a category, plus the trap vote counts and the reason.

Every response carries the same five fields: source_url, updated, license, attribution and monetization.

Without tools

A crawler that cannot call tools can fetch the same boards as files:

  • https://stierproducts.com/llms.txt indexes the whole site for a language model.
  • https://stierproducts.com/categories/<slug>.md is one board as Markdown.
  • https://stierproducts.com/categories/<slug>.json is the same board as JSON.

Licence

The rankings are published under CC BY 4.0. Attribute to "stierproducts" and link to the board or product URL you used. Product images are not covered. Full terms: https://stierproducts.com/license

This repository's files are under the same licence.

Support

Open an issue here, or email [email protected].

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.