CraftedTrust MCP server

Which servers in the official MCP registry are CraftedTrust'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 CraftedTrust

Whose server it is

Registry namecom.craftedtrust/mcp-shieldverified in the MCP registry

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

When we asked itchecked 2026-10-24

Stateanswerschecked 2026-10-24
Tools4
Server calls itselfCraftedTrust
Server version1.0.0
Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 163 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.

Once connected

For "run a public scan on an MCP server before connecting", the likely first call is scan_server.

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 answer193 ms
Space in an agent's context≈ 415 tokensthe definitions of all its tools (4), which an agent carries on every turn
Tool definitionsB · 83 of 100
Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once

Not saying whether it only reads or can destroy: 4 of 4

What an agent can do with it

not sure · search public MCP servers by URL, package or publisher
can do · run a public scan on an MCP server before connecting
not sure · review tool risk and auth signals in a server's checklist

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

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 offers4 tools · read 2026-10-24

check_trust
Look up the trust score for any MCP server by URL or npm package name. Returns score, grade, findings summary, and certification status.
scan_server
Trigger a live trust scan of an HTTP or HTTPS MCP server. Returns trust score, grade, and security findings.
search_registry
Search the CraftedTrust registry overlay for indexed MCP packages and servers. Filter by grade, certification, or scan type.
get_stats
Get CraftedTrust ecosystem statistics: total indexed servers, live verified count, average trust scores, flagged count, and more.

How to connect

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

{
  "mcpServers": {
    "mcp-shield": {
      "type": "http",
      "url": "https://mcp.craftedtrust.com/api/v1/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http craftedtrust https://mcp.craftedtrust.com/api/v1/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.craftedtrust.com/api/v1/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.