INDIVIDUAL MCP TOOL
get_provenance
Source records alone for one field of one model: URLs, labels, document model-years, staleness flags.
LIVE ENDPOINT
https://api.thirdrowreality.com/mcp
Connect to this endpoint to inspect the live schema for get_provenance and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT 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.thirdrowreality-spec-feed]
url = "https://api.thirdrowreality.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"thirdrowreality-spec-feed": {
"type": "http",
"url": "https://api.thirdrowreality.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: thirdrowreality-spec-feed
Remote MCP URL: https://api.thirdrowreality.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": {
"thirdrowreality-spec-feed": {
"url": "https://api.thirdrowreality.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"thirdrowreality-spec-feed": {
"type": "http",
"url": "https://api.thirdrowreality.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "thirdrowreality-spec-feed",
"transport": "streamable-http",
"url": "https://api.thirdrowreality.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
search_models— Deterministically filter the 3-row SUV directory (luxury and family) (not semantic search).get_model_specs— Full spec sheet for one model by slug: pricing, interior/exterior dimensions, cargo, towing, seating, third-row safety hardware, and derived persona scores — each field with provenance.get_field— One field for one model, with full provenance and any disagreement records.compare_models— Aligned comparison of two or more models on chosen fields, per-cell provenance.list_capabilities— Dataset coverage: models tracked, spec and safety field keys, verification-status definitions, and dataset stats.