AI & Machine Learning
subagentfinance.com
Provides access to a repository of AI-related cassettes and vendors, along with engineering guides.
ENDPOINT 1
https://www.subagentfinance.com/api/mcp
Known tools 10
list_vendorsList all active llms.txt vendors with metadata (name, slug, domain, category)
Inferred read-onlylist_guidesList available engineering guide topics (prompt-engineering, context-engineering, agent-sdk, tool-engineering)
Inferred read-onlyget_upgrade_infoGet current tier, all available tiers with pricing and features, tool availability per tier, and checkout API endpoint
Inferred read-onlyget_usageGet current API usage stats: requests today, daily limit, remaining quota, and reset time
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.subagentfinance-com]
url = "https://www.subagentfinance.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"subagentfinance-com": {
"type": "http",
"url": "https://www.subagentfinance.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: subagentfinance-com
Remote MCP URL: https://www.subagentfinance.com/api/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": {
"subagentfinance-com": {
"url": "https://www.subagentfinance.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"subagentfinance-com": {
"type": "http",
"url": "https://www.subagentfinance.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "subagentfinance-com",
"transport": "streamable-http",
"url": "https://www.subagentfinance.com/api/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.