# Unquant MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.unquant%2Funquant
Registry id: `mcp-registry/ai.unquant/unquant`
Status: live (checked 2026-10-27T09:00:57.340Z)

## Verdict

Unquant MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 898 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (91/100) across 28 tools, costing an agent about 5,853 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 898 ms | 22% of MCP servers |
| p95 handshake latency | 3307 ms | — |
| Checks in 30 days | 4,959 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 3 min | — |
| Agent-readiness score | 91/100 (A) | 70% of MCP servers |
| Tools | 28 | — |
| Tool-list size for an agent | ~5,853 tokens | 36% of MCP servers |
| Days observed | 29 | — |

## Install

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

Claude Code:

```sh
claude mcp add --transport http unquant-mcp-server https://unquant.ai/mcp
```

## Tools (28)

- `account_request_upgrade`: Create a human-reviewed Agent Pro request after Unquant delivers useful work. The result contains a confirmation link.
- `account_upgrade_status`: Return the current state of an Agent Pro request by upgrade identifier.
- `catalog_describe`: Return the purpose, access state, inputs, and next action for one catalog entry.
- `catalog_list`: List data, signals, tools, and workflows. Filter the catalog by the agent job, theme, item type, status, or geography.
- `catalog_preview`: Return a labeled preview for one catalog entry with optional symbols, dates, and filters.
- `catalog_request`: Save demand for a catalog entry after a preview, with the user goal and the preview action.
- `datasets_describe`: Return the schema, filters, limits, freshness, and access details for one dataset identifier.
- `datasets_list`: List available datasets with access, freshness, and coverage details for dataset selection.
- `datasets_search`: Search dataset identifiers, names, and descriptions with a plain-language financial-data query.
- `feedback_submit`: Save a product request for a missing tool, dataset, or feature. Examples include backtesting and options pricing. This request helps improve coverage.
- `macro_calendar`: Return economic events in chronological order for a date range, with optional country and impact filters.
- `macro_current_conditions`: Return generated themes for current United States macroeconomic conditions. The result includes its time and method version.
- `macro_indicator`: Return observations for one economic indicator, with optional dates for the observation period.
- `market_analyst_ratings`: Return the analyst rating consensus and recent rating changes for one ticker. The results are third-party opinions.
- `market_company_profile`: Return the company name, industry, exchange, market value, and basic profile fields for one ticker.
- `market_earnings`: Return reported or scheduled earnings events in a date range, with an optional ticker filter.
- `market_etf_holdings`: Return the largest reported holdings for one ETF, with an optional minimum weight filter.
- `market_fundamentals`: Return reported financial statements, ratios, and metrics for one company by quarterly or annual period.
- `market_price_history`: Return daily prices and volume for one ticker by date range or latest trading-session count.
- `market_quote`: Return the latest available end-of-day price and volume for one ticker. This tool does not return a real-time quote.
- `market_symbol_search`: Find ticker symbols by company name or ticker text for security identification.
- `news_article`: Return one processed news summary by story identifier. The tool does not return full article text or external links.
- `news_general`: Return recent cross-market news summaries with cursor pagination.
- `news_impacts`: Return generated direction, importance, and confidence scores for recent news about selected tickers. These scores do not establish causality.
- `news_stock`: Return recent news summaries for one ticker. The tool returns summaries and does not return full article text.
- `ping`: Return the Unquant MCP server status for an availability check.
- `politics_us_congress_aggregate`: Return ticker-level totals from reported United States congressional transactions. The totals do not show current holdings or intent.
- `politics_us_congress_trades`: Return reported United States congressional transactions. Filter by ticker, member, asset owner, or transaction dates.

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