AI & Machine Learning
gkworks.com
Exposes GK Works' public AI/RAG site index, API catalog, website assistant, and AI-agent inquiry submission.
ENDPOINT 1
https://gkworks.com/mcp
MCP server metadata
- Name
- gkworks-web-mcp
- Version
- 0.1.0
Use public resources for RAG. Use send_ai_inquiry only after explicit user authorization.
Known tools 4
get_site_indexReturn the public GK Works AI/RAG site index from https://gkworks.com/ai-index.json.
Inferred read-onlyget_api_catalogReturn public API metadata for GK Works without secrets or operational logs.
Inferred read-onlyask_site_chatAsk the GK Works website assistant a short public question about services, AI modernization, security, or architecture.
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.gkworks-web-mcp]
url = "https://gkworks.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"gkworks-web-mcp": {
"type": "http",
"url": "https://gkworks.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: gkworks-web-mcp
Remote MCP URL: https://gkworks.com/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": {
"gkworks-web-mcp": {
"url": "https://gkworks.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"gkworks-web-mcp": {
"type": "http",
"url": "https://gkworks.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "gkworks-web-mcp",
"transport": "streamable-http",
"url": "https://gkworks.com/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.