Skip to content
PrimeZen LLC logo

PrimeZen LLC MCP server

Which MCP servers are PrimeZen LLC'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 2026-10-27

← Back to PrimeZen LLC

Whose server it is
  • Registry namecom.recallsapi/recallsapiverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools4
  • Server calls itselfrecallsapi
  • Server version0.1.2
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 130 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 1 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 2 of 4 tools: check arguments before calling.

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: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer101 ms
  • Space in an agent's context≈ 865 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 92 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 4

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 offers4 tools · read 2026-10-27
  • check_product

    Is this product recalled? Give whatever you have: a product name and brand, a UPC/EAN/GTIN barcode, a model number, an NDC drug code or a lot code. Returns matching recalls from 9 US agencies (CPSC, FDA, NHTSA, US Coast Guard, FAA and…

  • search_recalls

    Full-text search across recall records from 9 US agencies (CPSC, FDA, NHTSA, US Coast Guard, FAA and more), newest and most relevant first. Filter by category and date.

  • check_vehicle

    NHTSA recall campaigns for a vehicle, by 17-character VIN (decoded with NHTSA vPIC) or by make, model and year, plus live NHTSA consumer complaint counts for that make, model and year (not verified by NHTSA, not a safety determination)…

  • get_recall

    Full record for one recall id (for example "cpsc-24116", "fda-H-1339-2026", "nhtsa-26V631000", "fsis-001-2016"), with every identifier and the agency source link.

How to connect

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

{
  "mcpServers": {
    "recallsapi": {
      "type": "http",
      "url": "https://api.recallsapi.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http recallsapi https://api.recallsapi.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.recallsapi.com/mcp as a custom connector in the settings.

OpenAPI spec

27 paths, read 2026-10-27. Open the spec ↗

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.