Security & Testing
thesingulariti.ai
Provides a transparency and verification service for brand claims, offering fit-scored recommendations, verified claims with provenance, category landscapes, accountability logs, and a tamper-evident ledger.
ENDPOINT 1
https://graviti.thesingulariti.ai/api/mcp
MCP server metadata
- Name
- graviti
- Version
- 0.2.0
Known tools 7
match_intentTakes a natural-language buyer question plus optional intent profile; returns recommendations ranked purely by fit score.
Inferred read-onlyget_verified_claimsStructured claims for one brand: provenance URLs, freshness timestamps, corroboration counts, and verification status (verified means the brand pays for auditing — always disclosed).
Inferred read-onlycategory_landscapeComparison-table view of every brand in a category across disclosed attributes, with verification status marked per entry.
Inferred read-onlyget_accountability_logPublic, machine-readable log of every seal lifecycle change: flags, degradations, revocations, and restorations, with dates and reasons — plus confirmation-loop events (event: confirmation_request / confirmation_resolved), where the audit asked a brand to confirm a claim it couldn't re-verify: a visible ask, never a penalty.
Inferred read-onlyget_ledgerAppend-only version history of the index: each entry commits to the SHA-256 of the canonical index content and the previous entry's hash (rewriting history breaks every hash after it), is Ed25519-signed, and is anchored to Bitcoin via OpenTimestamps.
Inferred read-onlyget_gap_reportWhat stands between a brand and top-of-category: attribute gaps vs the category leader, open flags, cohort blind spots per buyer-intent voice, and the ingredient/spec disclosure dimension — the brand's info_quality score with the exact publishable fixes that would raise it (publishing more truth, not paying Graviti).
Inferred read-onlyreport_conversionAppends one attributed-transaction event to a log — the demo stub of the pay-on-real-acquisition loop.
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.graviti]
url = "https://graviti.thesingulariti.ai/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"graviti": {
"type": "http",
"url": "https://graviti.thesingulariti.ai/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: graviti
Remote MCP URL: https://graviti.thesingulariti.ai/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": {
"graviti": {
"url": "https://graviti.thesingulariti.ai/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"graviti": {
"type": "http",
"url": "https://graviti.thesingulariti.ai/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "graviti",
"transport": "streamable-http",
"url": "https://graviti.thesingulariti.ai/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.