AI & Machine Learning
sdet.it
Provides information about AI engineering, context engineering, and QA services offered by Dariusz, including service details and landing page content.
ENDPOINT 1
https://sdet.it/mcp
MCP server metadata
- Name
- sdet-it-portal
- Version
- 0.1.0
Known tools 3
list_servicesReturns the 3 services Dariusz offers end-to-end: AI Engineer (audits + custom agents), Context Engineering (jarvis-brain RAG), QA Engineering (CDAT + dispatcher + paired training).
Inferred read-onlyread_serviceReturns the full data of one service identified by slug (from list_services).
Inferred read-onlyread_landingReturns the structured snapshot of the landing page: hero, stats, tech stack, contact channels, and ecosystem links.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.sdet-it-portal]
url = "https://sdet.it/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"sdet-it-portal": {
"type": "http",
"url": "https://sdet.it/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: sdet-it-portal
Remote MCP URL: https://sdet.it/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"sdet-it-portal": {
"url": "https://sdet.it/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"sdet-it-portal": {
"type": "http",
"url": "https://sdet.it/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "sdet-it-portal",
"transport": "streamable-http",
"url": "https://sdet.it/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.