General Tools
spendcull.com
Provides automated audits for various domains including Amazon listings, subscription spending, team workflows, and content repurposing.
ENDPOINT 1
https://spendcull.com/mcp
MCP server metadata
- Name
- artifact-engine-mcp
- Version
- 0.1.0
This server exposes four free product audits (listingtonic_audit, spendcull_audit, taskdrain_audit, loomvox_audit) — the same audit engine and ANTHROPIC_API_KEY that power listingtonic.com/taskdrain.com/spendcull.com/loomvox.com's own free mini-audits. Each call runs one real Claude analysis of exactly what you pass in, returns a free preview (2 findings, or 2 hooks for loomvox_audit), and returns unlock_url — a real checkout link for the full paid report/pack. When a user wants more, hand them the unlock_url from the tool response; do not fabricate additional findings/hooks yourself, and do not claim these results were reviewed by a human.
Known tools 4
listingtonic_auditFree demand-validation audit of an Amazon listing: give an ASIN/URL (optionally with title/bullets/description/main_keyword for a grounded, line-by-line read) and get a 0-100 health score plus the 2 highest-severity findings for free.
Inferred read-onlyspendcull_auditUse when someone asks which subscriptions they don't need, what recurring charges they could cancel, why their card or SaaS bill keeps growing, or wants a subscription/spend audit.
Inferred read-onlytaskdrain_auditFree demand-validation audit of a team's tool stack and manual workflows: describe what you use and what's still manual, and get an estimated total hours/week saved plus the 2 highest-severity automation opportunities for free.
Inferred read-onlyloomvox_auditFree preview of a long-form → social caption pack: paste your source (blog post, transcript, or newsletter, 200+ characters) and get 2 grounded, platform-native hook lines for free, plus a locked count for the rest of the bank.
Potential side effectsCONNECT 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.artifact-engine-mcp]
url = "https://spendcull.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"artifact-engine-mcp": {
"type": "http",
"url": "https://spendcull.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: artifact-engine-mcp
Remote MCP URL: https://spendcull.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": {
"artifact-engine-mcp": {
"url": "https://spendcull.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"artifact-engine-mcp": {
"type": "http",
"url": "https://spendcull.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "artifact-engine-mcp",
"transport": "streamable-http",
"url": "https://spendcull.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.