Unquant is an MCP server with 28 tools an agent can call, among them account_request_upgrade, account_upgrade_status, catalog_describe. It answers at https://unquant.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Financial data MCP for market, company, news, macro, and US Congress research.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
account_request_upgrade | Create a human-reviewed Agent Pro request after Unquant delivers useful work. The result contains a confirmation link. Inputs: request_summary, value_summary, next_step_summary |
account_upgrade_status | Return the current state of an Agent Pro request by upgrade identifier. Inputs: upgrade_id |
catalog_describe | Return the purpose, access state, inputs, and next action for one catalog entry. Inputs: entry_id |
catalog_list | List data, signals, tools, and workflows. Filter the catalog by the agent job, theme, item type, status, or geography. Inputs: query, job_id, theme, item_type, status, geo_archetype |
catalog_preview | Return a labeled preview for one catalog entry with optional symbols, dates, and filters. Inputs: entry_id, inputs |
catalog_request | Save demand for a catalog entry after a preview, with the user goal and the preview action. Inputs: entry_id, action, use_case, expected_volume, organization, contact |
datasets_describe | Return the schema, filters, limits, freshness, and access details for one dataset identifier. Inputs: dataset_id |
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. Inputs: 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. Inputs: category, request, use_case |
macro_calendar | Return economic events in chronological order for a date range, with optional country and impact filters. Inputs: start_day, end_day, country, impact, limit |
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. Inputs: name, start_day, end_day, limit |
market_analyst_ratings | Return the analyst rating consensus and recent rating changes for one ticker. The results are third-party opinions. Inputs: symbol, limit |
market_company_profile | Return the company name, industry, exchange, market value, and basic profile fields for one ticker. Inputs: symbol |
market_earnings | Return reported or scheduled earnings events in a date range, with an optional ticker filter. Inputs: symbol, start_day, end_day, limit |
market_etf_holdings | Return the largest reported holdings for one ETF, with an optional minimum weight filter. Inputs: symbol, limit, min_weight_percent |
market_fundamentals | Return reported financial statements, ratios, and metrics for one company by quarterly or annual period. Inputs: symbol, period, limit |
market_price_history | Return daily prices and volume for one ticker by date range or latest trading-session count. Inputs: symbol, start_day, end_day, limit, order, cursor |
market_quote | Return the latest available end-of-day price and volume for one ticker. This tool does not return a real-time quote. Inputs: symbol |
market_symbol_search | Find ticker symbols by company name or ticker text for security identification. Inputs: query, limit |
news_article | Return one processed news summary by story identifier. The tool does not return full article text or external links. Inputs: story_id |
news_general | Return recent cross-market news summaries with cursor pagination. Inputs: hours, limit, cursor |
news_impacts | Return generated direction, importance, and confidence scores for recent news about selected tickers. These scores do not establish causality. Inputs: symbols, hours, limit, cursor |
news_stock | Return recent news summaries for one ticker. The tool returns summaries and does not return full article text. Inputs: symbol, hours, limit, cursor |
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. Inputs: symbols, days, limit, cursor |
politics_us_congress_trades | Return reported United States congressional transactions. Filter by ticker, member, asset owner, or transaction dates. Inputs: symbols, member_names, asset_owner, days, limit, cursor |
Every block below points at https://unquant.ai/mcp. Pick your client and copy.
claude mcp add --transport http unquant https://unquant.ai/mcp
{
"mcpServers": {
"unquant": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://unquant.ai/mcp"]
}
}
}{
"mcpServers": {
"unquant": {
"url": "https://unquant.ai/mcp"
}
}
}{
"servers": {
"unquant": {
"type": "http",
"url": "https://unquant.ai/mcp"
}
}
}{
"context_servers": {
"unquant": {
"url": "https://unquant.ai/mcp"
}
}
}{
"mcpServers": {
"unquant": {
"serverUrl": "https://unquant.ai/mcp"
}
}
}{
"mcpServers": {
"unquant": {
"url": "https://unquant.ai/mcp"
}
}
}name: Unquant
version: 0.0.1
schema: v1
mcpServers:
- name: Unquant
type: streamable-http
url: https://unquant.ai/mcp{
"mcpServers": {
"unquant": {
"httpUrl": "https://unquant.ai/mcp"
}
}
}{
"mcpServers": {
"unquant": {
"type": "http",
"url": "https://unquant.ai/mcp"
}
}
}{
"mcpServers": {
"unquant": {
"url": "https://unquant.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Funquant.ai%2Fmcp&type=streamable_http&id=unquant&name=Unquant
It answered our last check on 17 October 2026 in 43 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by unquant.ai and served from unquant.ai, the vendor's own domain: https://unquant.ai/mcp.
28, as returned by the server's own tools/list on 8 September 2026: account_request_upgrade, account_upgrade_status, catalog_describe, catalog_list, catalog_preview, catalog_request, datasets_describe, datasets_list, and 20 more.
It answered our last check on 17 October 2026 in 43 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://unquant.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.unquant. Endpoint host: unquant.ai. ARD identifier: urn:air:ai.unquant:mcp:unquant.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.