Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pinchy find working coupon codes for nike.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
· MCP Registry:
com.trypinchy/pinchy · trypinchy.com
MCP server that finds coupon codes for any online store. Remote endpoint: https://mcp.trypinchy.com/mcp
(Streamable HTTP, no auth).
Shopping in a browser yourself? The same codes, tried for you at checkout: Pinchy – Coupon Finder & Auto Apply for Chrome.
{ "mcpServers": { "pinchy": { "type": "http", "url": "https://mcp.trypinchy.com/mcp" } } }Claude Code: claude mcp add --transport http pinchy https://mcp.trypinchy.com/mcp
Clients that only speak stdio can run the npm package instead:
{ "mcpServers": { "pinchy": { "command": "npx", "args": ["-y", "pinchy-mcp"] } } }Related MCP server: GoodRx MCP Server
find_coupons({ store, limit? }) — store is a domain or any URL on the store; limit defaults to 10 (max 50).
Returns { domain, storeName?, coupons: [{ code, description?, expiresAt?, successCount?, lastWorkedAt? }] },
ordered by how likely a code is to work. An unknown store returns an empty list.
pnpm install
pnpm dev # http://127.0.0.1:4020/mcp
pnpm testConfig is read from the environment, see .env.example. The process binds to 127.0.0.1 and trusts
CF-Connecting-IP for rate limiting, so expose it only through a proxy that sets that header.
The server receives a store domain and nothing else: no account, no conversation content, no identifiers. Full policy: https://trypinchy.com/privacy.html · Contact: hi@trypinchy.com
Find coupon / promo / discount codes for an online store. Pass the store domain or any URL from the store (product, cart or checkout page). Returns codes ordered by how likely they are to work: try them at checkout from the top, keep the one that lowers the total the most. Codes can expire or carry store restrictions, so none is guaranteed; an empty list means none are known for that store.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of codes to return | |
| store | Yes | Store domain or any URL on the store, e.g. "momcozy.com" |
| Name | Required | Description |
|---|---|---|
| domain | Yes | |
| coupons | Yes | |
| storeName | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, and the description aligns with these while adding meaningful behavioral context: result ordering is by likelihood of working, results are not guaranteed, and empty lists have a defined meaning. This goes beyond the structured annotations and helps the agent set user expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded: it states the purpose and input format first, then explains result ordering and caveats. Every sentence contributes useful information, with no filler or redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a low-complexity read-only tool with a high-coverage schema and an output schema, the description covers all essential context: what to pass, what the tool returns, how to use the results, and important limitations. Nothing critical is missing for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the input schema already documents both parameters. The description repeats the store parameter semantics but does not add new parameter-level detail beyond the schema. The baseline of 3 is appropriate because the schema carries the parameter documentation burden.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb and resource: find coupon/promo/discount codes for an online store. It also specifies the accepted input format (store domain or any store URL), making it unambiguous. No sibling tools exist, so differentiation is not required.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit usage guidance: pass a store domain or any store URL, and explains how to interpret and act on results (try codes from the top, keep the one that lowers total the most). It also manages expectations by noting codes may expire or carry restrictions, and that an empty list means no known codes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1find_couponsScored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The tool has a single, well-defined purpose.
The sole tool name 'find_coupons' follows a clear verb_noun pattern, which is consistent with good naming conventions even though there is only one tool.
The server has a single tool, which feels thin compared to typical multi-tool servers. However, the narrow purpose of finding coupons justifies a minimal surface, so it is borderline but acceptable.
The tool fully covers the stated domain of finding coupon codes for online stores. It accepts a store URL and returns actionable results, leaving no obvious gaps for its intended use.
Verified deals, store policies & a trust score for thousands of online retailers. No auth.
Search current U.S. gift-card discounts from validated providers. Anonymous and read-only.
Search Shopify stores, enrich domains, and reveal approved contact channels.
Automate any website: discover, run and create browser scripts that work behind logins.
