# Thesingulariti Graviti MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.thesingulariti%2Fgraviti
Registry id: `mcp-registry/ai.thesingulariti/graviti`
Status: live (checked 2026-10-26T21:28:37.985Z)

## Verdict

Thesingulariti Graviti MCP server answered 99.97% of Glimind's liveness checks over 30 days, better than 40% of MCP servers, with 586 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (92/100) across 7 tools, costing an agent about 1,618 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.97% | 40% of MCP servers |
| Median handshake latency | 586 ms | 45% of MCP servers |
| p95 handshake latency | 2604 ms | — |
| Checks in 30 days | 4,889 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 92/100 (A) | 73% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~1,618 tokens | 57% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "thesingulariti-graviti-mcp-server": {
      "type": "http",
      "url": "https://graviti.thesingulariti.ai/api/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http thesingulariti-graviti-mcp-server https://graviti.thesingulariti.ai/api/mcp
```

## Tools (7)

- `category_landscape`: Comparison-table view of every brand in a category across disclosed attributes, with verification status marked per entry. Entries with captured ingredient/spec
- `get_accountability_log`: Public, machine-readable log of every seal lifecycle change: flags, degradations, revocations, and restorations, with dates and reasons — plus confirmation-loop
- `get_gap_report`: What 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 ingredien
- `get_ledger`: Append-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 brea
- `get_verified_claims`: Structured claims for one brand: provenance URLs, freshness timestamps, corroboration counts, and verification status (verified means the brand pays for auditin
- `match_intent`: Takes a natural-language buyer question plus optional intent profile; returns recommendations ranked purely by fit score. Verification status is disclosed but n
- `report_conversion`: Appends one attributed-transaction event to a log — the demo stub of the pay-on-real-acquisition loop. It moves no money, calls no external service, and never d

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.