Skip to content
Find logo

Find MCP server

Which servers in the official MCP registry are Find's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to Find

Whose server it is
  • Registry namecodes.find/verified-codesverified in the MCP registry

The registry name sits under find.codes. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools3
  • Server calls itselffind-codes
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 93 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

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.

Measured dailydaily checks: 3, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer215 ms
  • Space in an agent's context≈ 286 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →

Tools it offers3 tools · read 2026-10-24
  • list_brands

    Returns a brands array with each brand's category, offer and code (if any). Optionally filter by category: crypto-exchange, crypto-card, hardware-wallet, trading-tools, travel-esim, creator-tools, dining, home-design, ai-tools.

  • get_code

    Returns the full verified-code record for one brand: the code, the benefit, how to apply it, last-verified date, availability notes, and the guide/review URLs. Match by brand name or slug (e.g. 'kraken', 'Bybit Card').

  • search_codes

    Free-text search across brands, categories and offers, e.g. 'stock perps discount', 'esim', '20% off exchange'. Returns matching verified-code records.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "verified-codes": {
      "type": "http",
      "url": "https://find.codes/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http find https://find.codes/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://find.codes/api/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.