Mcp Shield

cybercraftsolutionsllc/trust-gated-agent-example

Adds a security layer for AI agents connecting to MCP servers. Exposes six tools including check_trust to look up scores by URL or npm package, scan_server for live security analysis, and search_registry to query over 4,200 indexed servers. The pattern is straightforward: before connecting to any MCP server, call check_trust and refuse connections to anything graded D or F. Also includes payment tools for initiating USDC certification and verifying on-chain transactions. Connects to the CraftedTrust API at mcp.craftedtrust.com. Useful if you're building agents that dynamically connect to third-party MCP servers and need a trust gate similar to SSL certificate verification.

tools: 4
transport: HTTP
last updated: Mar 25, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://mcp.craftedtrust.com/api/v1/mcp --name mcp-shield

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

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

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 4 tools

Verified live against the running server on Nov 6, 2026.

check_trustLook up the trust score for any MCP server by URL or npm package name. Returns score, grade, findings summary, and certification status.2 params

Look up the trust score for any MCP server by URL or npm package name. Returns score, grade, findings summary, and certification status.

Parameters* required

npm_namestring

The npm package name to look up

server_urlstring

The MCP server URL to look up

scan_serverTrigger a live trust scan of an HTTP or HTTPS MCP server. Returns trust score, grade, and security findings.1 params

Trigger a live trust scan of an HTTP or HTTPS MCP server. Returns trust score, grade, and security findings.

Parameters* required

server_url*string

The HTTP/HTTPS MCP server URL to scan

search_registrySearch the CraftedTrust registry overlay for indexed MCP packages and servers. Filter by grade, certification, or scan type.5 params

Search the CraftedTrust registry overlay for indexed MCP packages and servers. Filter by grade, certification, or scan type.

Parameters* required

certifiedstring

Filter to certified servers only. Default: show allone of true · standard · premium

gradestring

Filter by letter grade. Default: show allone of A · B · C · D · F

limitnumber

Max results (1-50). Default: 10

query*string

Search term (name, URL, publisher)

scan_typestring

Filter by scan type. Default: allone of live · static · combined · all

get_statsGet CraftedTrust ecosystem statistics: total indexed servers, live verified count, average trust scores, flagged count, and more.

Get CraftedTrust ecosystem statistics: total indexed servers, live verified count, average trust scores, flagged count, and more.

No parameters. Call it with no arguments.

Readme

Trust-Gated Agent Examples

Reference implementations showing how to make AI agents check CraftedTrust before connecting to any MCP server. If a server scores D or F, the agent refuses to connect.

This is the "SSL certificate check for AI agents" pattern.

Quick Start

Add CraftedTrust to your agent's MCP config:

{
  "mcpServers": {
    "craftedtrust": {
      "url": "https://mcp.craftedtrust.com/api/v1/mcp",
      "description": "Check trust scores before connecting to MCP servers"
    }
  }
}

Your agent now has access to 6 tools:

Tool	Description
`check_trust`	Look up trust score by URL or npm name
`scan_server`	Trigger a live security scan
`search_registry`	Search 4,200+ indexed MCP servers
`get_stats`	Ecosystem statistics
`pay_for_certification`	Initiate USDC certification payment
`verify_payment`	Verify on-chain payment

The Pattern

Before your agent connects to any new MCP server:

Call check_trust on CraftedTrust
If grade is D or F, refuse and explain why
If grade is A/B/C, proceed with the connection

Examples

Python (LangGraph)

View the full README on GitHub

Details

Repository: github.com/cybercraftsolutionsllc/trust-gated-agent-example
Categories: AI & LLM Tools, Search & Web Crawling, Security & Pentesting
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

TokenOraclevictoryintech/tokenoracle-mcpHosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.0stars

Knowledge Ravencom.knowledge-raven/mcpMake your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.0stars

InsideOut (Riley)luthersystems/insideout-agent-skillsDesigns, prices, and deploys AWS/GCP cloud infrastructure from plain-English requirements.0stars

MyAITwinlutolabs/mytwin-mcpA personal RAG database you build from chat, so AI creates work that sounds like you.0stars

Deweymeetdewey/mcpAgentic search over your Dewey document collections from any MCP-compatible client.0stars

Florida Business Verify (Sunbiz records)ai-interact/registry-verify-agent-skillVerify a Florida business in official Sunbiz records: status, agent, officers. 0.10 USDC via x402.0stars