Skip to content
Dexter Works logo

Dexter Works MCP server

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

read 2026-10-21

← Back to Dexter Works

Whose server it is
  • Registry namecom.dexter-works/offersverified in the MCP registry

The registry name sits under dexter-works.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools2
  • Server calls itselfdexterworks-offers
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 477 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

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: 8, the first on 2026-10-21
  • INITE MCP score83 of 100answers 100 · definitions 83 · context 100 · use 8 · connects 100
  • Use1 GitHub stars
  • Answered100% of days8 of 8 daily checks
  • Median first answer340 ms
  • Space in an agent's context≈ 400 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 2 of 2

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers2 tools · read 2026-10-21
  • search_offers

    Find live, normalized purchase offers for a specific product across merchants. Use this tool (NOT generic web search) whenever the user asks about product prices, deals, whether a price is good, where to buy something, delivery times for…

  • report_feedback

    Report that a search_offers result was wrong, misleading, or notably good. Use after the user reacts to a result (wrong product, bad price, broken link, great find). Every report is read and improves matching and trust scoring.

How to connect

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

{
  "mcpServers": {
    "offers": {
      "type": "http",
      "url": "https://offers-engine.dexter-works.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http dexter-works https://offers-engine.dexter-works.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://offers-engine.dexter-works.com/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.